NDA Review

Canonical path: skills/contracts/nda-review/SKILL.md

Example output not yet available.

{
  "schema_version": "2.0",
  "skill_id": "contracts/nda-review",
  "inherits": [
    "core/business-stakeholder-communication.md"
  ],
  "gates": {
    "custom": [
      {
        "id": "specialist-transaction-context",
        "condition": "The NDA is part of an M&A, employment, or investment transaction.",
        "action": "stop-and-escalate",
        "reason": "The confidentiality terms require transaction-specific specialist review rather than stand-alone commercial NDA triage."
      },
      {
        "id": "non-confidentiality-obligations",
        "condition": "The document contains standstill, exclusivity, non-solicitation, non-competition, IP assignment, license, right-of-first-refusal, most-favored-nation, or similarly broader obligations.",
        "action": "require-attorney-confirmation",
        "reason": "The document may be more than an NDA and cannot be routed for signature on confidentiality review alone."
      }
    ]
  },
  "execution_modes": [
    {
      "id": "quick-triage",
      "enabled": true,
      "purpose": "Confirm the document is a stand-alone commercial NDA, identify missing inputs, scan for obligations beyond confidentiality, and return only the preliminary escalation posture.",
      "output_detail": "minimal",
      "quality_checks": [
        "attorney-review-gate",
        "source-validation-check"
      ]
    },
    {
      "id": "standard",
      "enabled": true,
      "purpose": "Produce the standard NDA triage rating, key-term summary, risk table, negotiation priorities, and attorney-verification items.",
      "output_detail": "standard",
      "quality_checks": [
        "attorney-review-gate",
        "source-validation-check",
        "assumption-audit",
        "legal-prose-polish"
      ]
    },
    {
      "id": "deep-review",
      "enabled": true,
      "purpose": "Run the complete clause-category, red-flag, market-benchmark, negotiability, internal-consistency, and stakeholder-summary workflow with all applicable reference modules.",
      "output_detail": "expanded",
      "quality_checks": [
        "attorney-review-gate",
        "source-validation-check",
        "assumption-audit",
        "hallucination-red-team",
        "output-format-compliance-check",
        "privilege-confidentiality-check",
        "legal-prose-polish"
      ]
    }
  ],
  "input_schema": [
    {
      "id": "clients-role-disclosing-receiving-or-mutual",
      "label": "Client role",
      "type": "enum",
      "required": true,
      "description": "The client's role under the NDA.",
      "source_requirement": "user-provided",
      "may_infer": false,
      "sensitive": false,
      "enum": [
        "disclosing",
        "receiving",
        "mutual"
      ]
    },
    {
      "id": "transaction-context",
      "label": "Transaction context",
      "type": "enum",
      "required": true,
      "description": "The transaction setting used to determine whether stand-alone NDA triage is appropriate.",
      "source_requirement": "user-provided",
      "may_infer": false,
      "sensitive": false,
      "enum": [
        "standalone-commercial",
        "m-and-a",
        "employment",
        "investment",
        "other"
      ]
    }
  ],
  "output_schema": [
    {
      "id": "structured-risk-summary",
      "label": "Structured risk summary",
      "type": "table",
      "required": true,
      "description": "Material NDA provisions, exact section evidence, client risk, severity, preferred position, fallback position, and attorney action.",
      "attorney_review_required": true
    },
    {
      "id": "prioritized-redline-points-for-attorney-review",
      "label": "Prioritized redline points for attorney review",
      "type": "checklist",
      "required": true,
      "description": "High, medium, and low negotiation points with preferred and fallback positions and no final clause language unless attorney-directed.",
      "attorney_review_required": true
    }
  ],
  "evidence_schema": {
    "required_fields": [
      "support_text"
    ],
    "fields": [
      {
        "id": "provision_name",
        "type": "text",
        "description": "The provision or clause category supporting the issue."
      },
      {
        "id": "client_position",
        "type": "text",
        "description": "The client role and playbook position used in the analysis."
      }
    ]
  },
  "modules": [
    {
      "id": "nda-risk-table-template",
      "kind": "template",
      "path": "skills/contracts/nda-review/templates/nda-risk-table.md",
      "required": true,
      "load_when": "standard or deep-review mode"
    },
    {
      "id": "contract-red-flags",
      "kind": "reference",
      "path": "skills/contracts/references/red-flags.md",
      "required": true,
      "load_when": "all enabled modes"
    },
    {
      "id": "negotiability-ratings",
      "kind": "reference",
      "path": "skills/contracts/references/negotiability-ratings.md",
      "required": false,
      "load_when": "standard or deep-review mode when negotiation prioritization is requested"
    },
    {
      "id": "market-benchmark-framework",
      "kind": "reference",
      "path": "skills/contracts/references/market-benchmark-framework.md",
      "required": false,
      "load_when": "deep-review mode or when market practice is requested"
    },
    {
      "id": "contracts-practice-profile",
      "kind": "profile",
      "path": "practice-profiles/contracts.md",
      "required": false,
      "load_when": "a populated and attorney-approved contracts profile is available"
    }
  ]
}

Issue:               [clause name or topic]
Current posture:     [counterparty-favorable / neutral / missing]
Negotiability:       [Must Push / Strong Push / Business Call /
                      Acceptable if Balanced / Low Priority /
                      Do Not Spend Leverage]
Basis:               [one to two sentences identifying the key factors]
Preferred position:  [what the client wants]
Fallback position:   [what the client would accept]
Attorney note:       [CONFIRM: ...] or [ATTORNEY TO CONFIRM: ...]

Clause / Term:        [name of the clause or issue]
Characterization:     [Common / Aggressive / Unusual /
                       Depends on Leverage / Needs Attorney Confirmation]
Basis:                [why the reviewer chose this label]
Supporting source:    [client playbook / attorney comparable /
                       counterparty prior form / attorney-supplied norm /
                       NONE — drafting heuristic only]
Verification status:  [UNVERIFIED — attorney confirmation required]
                      OR [CONFIRMED by: (attorney / playbook / comparables)]

Benchmark Observation
Clause / Term:        [name of the clause or issue]
Observed term:        [what the reviewed contract says, quoted or precisely described]
Benchmark source:     [one of the four permitted sources; identify the specific source]
Benchmark position:   [what the benchmark source says about this term]
Deviation:            [how the reviewed contract departs from the benchmark, if at all]
Verification status:  [UNVERIFIED — attorney confirmation required]
                      OR [CONFIRMED by: (attorney / playbook / comparables)]

---
name: NDA Review
description: "Use when reviewing a non-disclosure or confidentiality agreement to produce a triage rating (route, flag, or stop), a structured risk summary, and prioritized redline points for attorney review."
practice_area: contracts
task_type: review
jurisdictions: []
risk_level: medium
requires_attorney_review: true
inputs:
  - "The full NDA or confidentiality agreement text"
  - "The client's role: disclosing, receiving, or mutual"
  - "The business and transaction context"
  - "Optional: the client's standard NDA positions or playbook"
outputs:
  - "Triage rating (route, flag, or stop)"
  - "Structured risk summary"
  - "Prioritized redline points for attorney review"
related_skills:
  - skills/contracts/contract-risk-review/SKILL.md
  - skills/contracts/redline-summary/SKILL.md
tags:
  - contracts
  - nda
  - confidentiality
  - contract-review
  - risk-triage
---

# NDA Review

## Purpose

Produce a structured, attorney-ready review of a non-disclosure agreement (NDA) or confidentiality agreement. The skill identifies key terms, flags risk-allocation issues, assigns an overall triage rating, and proposes prioritized redline points. It produces draft legal work product for attorney review — not legal advice and not a final negotiating position.

## Use When

- A user asks to "review this NDA," "check this confidentiality agreement," or "tell me what's risky here."
- A counterparty has sent an NDA and the user needs a first-pass risk read.
- The user wants a route / flag / stop call on whether an NDA can move toward signature.
- The user wants a redline priority list before negotiation.
- The user wants a plain-language summary of an NDA's obligations.

## Required Inputs

- The full NDA text (uploaded or pasted). Do not review from a description alone.
- The client's role: disclosing party, receiving party, or mutual.
- The business context: what is being shared and why.
- The transaction context: whether this is a stand-alone commercial NDA, or part of an M&A, employment, or investment deal.
- Optional but recommended: the client's standard NDA positions or playbook — acceptable terms, "never accept" terms, mutuality default, required carve-outs, term and survival caps, and governing-law preferences. The review benchmarks against these where they are provided.
- Optional: the practice group's `practice-profiles/contracts.md` if it has been populated and is loaded alongside this skill. If present, the skill uses its Standard Positions and Escalation Thresholds tables to benchmark the output and to gate escalation. If absent, the skill proceeds without practice-profile benchmarking and asks the user to supply standing positions inline if needed.

If the NDA text is not provided, stop and request it. Do not reconstruct or assume contract language.

## Do Not Use When

- The document is not an NDA (use `contract-risk-review` for general commercial agreements).
- The user needs a summary of tracked edits between drafts (use `redline-summary`).
- The confidentiality terms are one section of a larger commercial agreement (use `contract-risk-review`).
- The NDA is part of an M&A, employment, or investment transaction — confidentiality terms in those contexts carry deal-specific risk and should be reviewed with specialist counsel rather than triaged as a stand-alone commercial NDA.
- The request is for a statement of legal advice or a final negotiating position — those require an attorney.

## Legal Safety Rules

- **Source and citation discipline.** Follow `core/source-and-citation-discipline.md`. Never invent legal authority, citations, quotations, statutes, cases, regulations, filing deadlines, or procedural rules. Label what is a provided source, a user-provided fact, an assumption, a legal inference, or an item requiring attorney verification, and use a citation placeholder such as `[Attorney to insert authority]` when no source is available.
- Produce draft legal work product for attorney review. This is not legal advice.
- Review only the language actually present in the provided document. Quote it accurately.
- Do not invent contract terms, defined terms, section numbers, or quotations.
- Do not invent statutes, regulations, or case law. If legal authority is relevant, mark it as an attorney verification item.
- Do not invent or assume deadlines. Treat any signing or negotiation deadline as user-supplied or unverified.
- A triage rating of GREEN ("clear to route for signature") is a workflow signal, not authorization to sign. Attorney review and sign-off remain required before any NDA is signed.
- Do not draft new clause language or restructure provisions. Propose the direction of a change and route substantive drafting to an attorney.
- Distinguish what the contract says from what you assume and from what the attorney must confirm.
- Preserve confidentiality and privilege: the review is attorney work product. Do not place client-sensitive facts into reusable templates.
- Flag every point of uncertainty rather than resolving it silently.
- **Severity floor.** Once an issue has been rated High priority in the prioritized redline points or risk table, that rating must not be silently downgraded. Any reduction in priority is an explicit attorney decision and must be recorded as such (e.g., "Downgraded from High to Medium by [attorney], [date], reason: [brief rationale]"). This applies regardless of the counterparty's explanation or commercial commonness of the provision.
- **Profile reference is optional, not authoritative.** Where `practice-profiles/contracts.md` is loaded, its Standard Positions and Escalation Thresholds inform the draft but never substitute for attorney judgment. The profile is a configuration record approved by the practice group; it is not legal advice and does not override the skill's normal attorney-verification gates. If the profile's standing positions conflict with the matter facts or with what the supervising attorney concludes, the attorney prevails.

## Workflow

This skill draws on shared contract-review reference material in `skills/contracts/references/`: `red-flags.md` (red-flag catalogue), `negotiability-ratings.md` (six-rating negotiability rubric), `market-benchmark-framework.md` (benchmarking discipline and market-practice vocabulary), `fallback-language-bank.md` (sample preferred and fallback positions by clause type), `document-type-checklists.md` (per-document-type checklists), `clause-category-checklist.md` (cross-document clause-category completeness sweep), `market-standard-baselines.md` (open-standard baseline comparisons), and `redline-output-guidance.md` (how to frame redline direction). Consult them at the steps noted below.

1. **Confirm inputs.** Verify you have the full NDA text, the client's role, and the transaction context. If anything is missing, request it before proceeding.
2. **Transaction-context check.** If the NDA is part of an M&A, employment, or investment transaction, stop and route the matter to specialist counsel (see Do Not Use When). Continue only for stand-alone commercial NDAs.
3. **Identify the structure.** Locate and label the core provisions: parties, definition of Confidential Information, permitted use, standard exclusions, term and survival, return/destruction, remedies, and governing law. Use the NDA checklist in `skills/contracts/references/document-type-checklists.md` to confirm nothing is overlooked, and run the formation/term and restrictive-covenant groups of `skills/contracts/references/clause-category-checklist.md` as a fast completeness pass across clause categories before the deeper review.
4. **Red flags quick scan.** Run a fast first pass against the red-flag catalogue in `skills/contracts/references/red-flags.md`. Record each red-flag pattern present, or note that none surfaced in the scan. This scan orients the deeper review; it does not replace it.
5. **Scope check.** Scan for obligations that go beyond confidentiality — for example a standstill, exclusivity, non-solicitation, non-competition, IP assignment, a licensing grant, a right of first refusal, a most-favored-nation clause, broad arbitration, or a governing-law clause reaching beyond confidentiality disputes. Any such term means the document is more than an NDA: flag it prominently and raise the triage rating accordingly.
6. **Summarize each key term** in plain language, citing the section number as written.
7. **Assess risk allocation from the client's role.** A receiving party and a disclosing party care about opposite asymmetries; analyze from the client's actual position.
8. **Benchmark against the client's standard positions.** If a playbook was provided — either inline by the user or via the loaded `practice-profiles/contracts.md` Standard Positions section — note where the NDA matches it, where it deviates, and where any term hits a "never accept" position. Where the profile is loaded but a specific term is silent in its Standard Positions, treat that term as not addressed by the playbook and flag for attorney review. Record any market comparison using the discipline in `skills/contracts/references/market-benchmark-framework.md`: characterize each relevant term with the controlled vocabulary (Common, Aggressive, Unusual, Depends on Leverage, Needs Attorney Confirmation), state the basis and supporting source, and flag every characterization not backed by a playbook, comparable, counterparty prior form, or attorney-supplied norm as an attorney-verification item. AgentCounsel does not supply market data. For a stand-alone mutual or unilateral NDA, also consider a baseline comparison against the oneNDA open standard using `skills/contracts/references/market-standard-baselines.md`.
9. **Flag missing or one-sided terms** — for example, no standard exclusions, a perpetual term on all information, broad injunctive-relief language, or unilateral obligations in a document labeled "mutual."
10. **Build the risk table** using `templates/nda-risk-table.md`.
11. **Rate negotiability.** For each material issue, assign one of the six negotiability ratings from `skills/contracts/references/negotiability-ratings.md` — Must Push, Strong Push, Business Call, Acceptable if Balanced, Low Priority, or Do Not Spend Leverage — with a one-line rationale drawn from leverage, who drafted the form, the deal value, and any regulatory floor.
12. **Draft prioritized redline points.** Rank issues High / Medium / Low. For each, following `skills/contracts/references/redline-output-guidance.md`, state: the issue, why it matters, a **Preferred Position**, a **Fallback Position**, and a **Suggested Redline Direction** — the direction of the change, not final clause language unless the user asks for it. Use `skills/contracts/references/fallback-language-bank.md` to help articulate preferred and fallback positions. Route substantive drafting to an attorney.
13. **Internal consistency check.** Confirm that defined terms, party names, cross-references, and section numbers are used consistently throughout the NDA. Flag any defined-but-unused term, used-but-undefined term, broken cross-reference, mismatched party label, or numbering gap.
14. **Assign an overall triage rating:**
    - **GREEN — clear to route for signature.** Terms are consistent with the client's role and standard positions; no obligations beyond confidentiality; no missing protection that matters for the client's role. Attorney sign-off is still required.
    - **YELLOW — flag for negotiation or approver review.** One or more terms deviate from the client's standard positions or are one-sided but not dealbreakers; or a playbook is silent on a material term; or the scope check found a non-confidentiality term that needs review.
    - **RED — stop and escalate.** A term hits a "never accept" position; there is a structural mismatch (such as unilateral obligations in a "mutual" NDA, or a perpetual term on all information); or the document carries significant non-confidentiality obligations or arises in an M&A, employment, or investment context.
15. **List attorney verification items** — governing-law implications, enforceability questions, every unverified benchmark, and anything requiring legal judgment.
16. **Draft a business-friendly summary.** Produce a short, plain-language summary for non-lawyer stakeholders: the overall posture, the few terms that matter most, what to push on and why, and what — if anything — would stop signature. Use the stakeholder-communication language patterns in `skills/contracts/references/negotiability-ratings.md`. Avoid legal jargon.
17. **Assemble the output** and label it as a draft for attorney review.

## Output Format

Deliver:

1. **Triage Rating** — GREEN / YELLOW / RED, with a one-line rationale.
2. **Summary** — 3-5 sentences: document type, client role, overall risk posture.
3. **Red Flags Quick Scan** — each red-flag pattern from `skills/contracts/references/red-flags.md` found in the NDA, or a note that none surfaced in the scan.
4. **Key Terms Table** — plain-language summary with section references.
5. **Scope Check** — whether the document contains obligations beyond confidentiality, and which.
6. **Risk Table** — from `templates/nda-risk-table.md`.
7. **Negotiability Table** — a table covering each material issue, with columns: Issue | Negotiability Rating | Basis | Recommended Lawyer Action. The Negotiability Rating is one of the six ratings defined in `skills/contracts/references/negotiability-ratings.md` (Must Push, Strong Push, Business Call, Acceptable if Balanced, Low Priority, Do Not Spend Leverage); the Basis is a one-line rationale.
8. **Market Practice Notes** — any market comparison, recorded using `skills/contracts/references/market-benchmark-framework.md`. Characterize each relevant term with the controlled vocabulary (Common, Aggressive, Unusual, Depends on Leverage, Needs Attorney Confirmation), state the basis and supporting source, and flag every characterization not backed by a playbook, comparable, counterparty prior form, or attorney-supplied norm for attorney verification. AgentCounsel does not supply market data.
9. **Prioritized Redline Points** — High / Medium / Low. Each point states the issue and why it matters, a **Preferred Position**, a **Fallback Position**, and a **Suggested Redline Direction** (direction of change, not final language), following `skills/contracts/references/redline-output-guidance.md`. Use `skills/contracts/references/fallback-language-bank.md` to help articulate preferred and fallback positions.
10. **Business-Friendly Summary** — a short, plain-language summary for non-lawyer stakeholders: the overall posture, the few terms that matter most, what to push on and why, and what — if anything — would stop signature. Avoid legal jargon.
11. **Internal Consistency Check** — whether defined terms, party names, cross-references, and section numbers are used consistently, with any inconsistency flagged.
12. **Attorney Verification Items** — open questions and items requiring legal judgment.
13. **Assumptions** — every assumption made, listed explicitly.

Use placeholders like `[CONFIRM: governing law]` wherever information is missing. Do not fill gaps with invented content.

### Optional: Business Stakeholder Summary

When the output will be used to brief a non-lawyer business stakeholder — a product owner, deal lead, people manager, founder, or executive — add a **Business Stakeholder Summary** as a clearly separated, plainly labeled section, following `core/business-stakeholder-communication.md`. Produce it only when the user requests it or when the audience is plainly a business decision-maker. It is an addition to the deliverable above — never a replacement for it, and never a substitute for attorney review. It contains:

- **Business Summary** — the bottom line in plain language, with unnecessary legal jargon removed and legal risk stated separately from business and commercial risk.
- **Decision Needed** — the specific business decision(s) now on the table, stated as concrete choices, each with its owner.
- **Recommended Ask** — the legal team's recommended position or course of action, framed as a recommendation for the business to weigh, not a decision made on its behalf.
- **Fallback Position** — the minimum acceptable alternative if the Recommended Ask cannot be achieved.
- **Escalation Needed?** — whether the matter should be escalated, to whom (senior management, the board, or outside counsel), and why — or a plain statement that no escalation is needed.

## Attorney Verification Checklist

- [ ] The NDA text reviewed is complete and final.
- [ ] The client's role (disclosing / receiving / mutual) is correctly identified.
- [ ] The transaction context is confirmed; if the NDA arises in an M&A, employment, or investment deal, specialist counsel has been involved.
- [ ] The scope check is complete; if the document contains obligations beyond confidentiality, it has been reviewed as more than an NDA.
- [ ] All section references and quotations match the source document.
- [ ] No legal authority, statute, or case law has been asserted without verification.
- [ ] Enforceability of remedies and any restrictive covenants has been assessed under the governing law.
- [ ] Governing law and jurisdiction are appropriate for the client.
- [ ] Term and survival periods are acceptable for the type of information being shared.
- [ ] The triage rating and risk ratings reflect the client's standard positions, role, and leverage.
- [ ] The red-flag quick scan and the negotiability table have been reviewed; each of the six-scale negotiability ratings reflects the client's actual leverage and standard positions.
- [ ] Every market-practice characterization has a stated basis and supporting source; no market benchmark has been relied on without independent verification.
- [ ] Preferred and fallback positions reflect the client's actual leverage and standard positions.
- [ ] The business-friendly summary accurately reflects the review and neither overstates nor understates any risk.
- [ ] The internal consistency check is complete; defined terms and cross-references are sound.
- [ ] A GREEN rating has attorney sign-off before the NDA is signed.
- [ ] All assumptions and open items are resolved before the review is relied upon.
- [ ] If a practice profile was loaded: every Standard Position and Escalation Threshold that applies to the matter facts has been surfaced; deviations are flagged; profile-silent items are flagged as not-yet-addressed by the playbook.
- [ ] If no practice profile was loaded: any benchmarking or "standard position" framing in the output is grounded in user-supplied inline data, not assumed.

AgentCounsel selective execution package for NDA Review.

The core skill always applies. Choose one declared execution mode and evaluate each module's machine-readable activation object exactly. Missing activation inputs fail closed: do not load every conditional module. A module without activation is not selected unless it is required or explicitly requested. Use only the selected resources, preserve why each resource was selected, and keep every parent safety rule active.

This portable package contains every possible resource. For true prompt-size reduction, use the MCP get_skill_context tool or another client that sends only the selected bundle.

=== BEGIN AGENTCOUNSEL CORE SKILL ===
---
name: NDA Review
description: "Use when reviewing a non-disclosure or confidentiality agreement to produce a triage rating (route, flag, or stop), a structured risk summary, and prioritized redline points for attorney review."
practice_area: contracts
task_type: review
jurisdictions: []
risk_level: medium
requires_attorney_review: true
inputs:
  - "The full NDA or confidentiality agreement text"
  - "The client's role: disclosing, receiving, or mutual"
  - "The business and transaction context"
  - "Optional: the client's standard NDA positions or playbook"
outputs:
  - "Triage rating (route, flag, or stop)"
  - "Structured risk summary"
  - "Prioritized redline points for attorney review"
related_skills:
  - skills/contracts/contract-risk-review/SKILL.md
  - skills/contracts/redline-summary/SKILL.md
tags:
  - contracts
  - nda
  - confidentiality
  - contract-review
  - risk-triage
---

# NDA Review

## Purpose

Produce a structured, attorney-ready review of a non-disclosure agreement (NDA) or confidentiality agreement. The skill identifies key terms, flags risk-allocation issues, assigns an overall triage rating, and proposes prioritized redline points. It produces draft legal work product for attorney review — not legal advice and not a final negotiating position.

## Use When

- A user asks to "review this NDA," "check this confidentiality agreement," or "tell me what's risky here."
- A counterparty has sent an NDA and the user needs a first-pass risk read.
- The user wants a route / flag / stop call on whether an NDA can move toward signature.
- The user wants a redline priority list before negotiation.
- The user wants a plain-language summary of an NDA's obligations.

## Required Inputs

- The full NDA text (uploaded or pasted). Do not review from a description alone.
- The client's role: disclosing party, receiving party, or mutual.
- The business context: what is being shared and why.
- The transaction context: whether this is a stand-alone commercial NDA, or part of an M&A, employment, or investment deal.
- Optional but recommended: the client's standard NDA positions or playbook — acceptable terms, "never accept" terms, mutuality default, required carve-outs, term and survival caps, and governing-law preferences. The review benchmarks against these where they are provided.
- Optional: the practice group's `practice-profiles/contracts.md` if it has been populated and is loaded alongside this skill. If present, the skill uses its Standard Positions and Escalation Thresholds tables to benchmark the output and to gate escalation. If absent, the skill proceeds without practice-profile benchmarking and asks the user to supply standing positions inline if needed.

If the NDA text is not provided, stop and request it. Do not reconstruct or assume contract language.

## Do Not Use When

- The document is not an NDA (use `contract-risk-review` for general commercial agreements).
- The user needs a summary of tracked edits between drafts (use `redline-summary`).
- The confidentiality terms are one section of a larger commercial agreement (use `contract-risk-review`).
- The NDA is part of an M&A, employment, or investment transaction — confidentiality terms in those contexts carry deal-specific risk and should be reviewed with specialist counsel rather than triaged as a stand-alone commercial NDA.
- The request is for a statement of legal advice or a final negotiating position — those require an attorney.

## Legal Safety Rules

- **Source and citation discipline.** Follow `core/source-and-citation-discipline.md`. Never invent legal authority, citations, quotations, statutes, cases, regulations, filing deadlines, or procedural rules. Label what is a provided source, a user-provided fact, an assumption, a legal inference, or an item requiring attorney verification, and use a citation placeholder such as `[Attorney to insert authority]` when no source is available.
- Produce draft legal work product for attorney review. This is not legal advice.
- Review only the language actually present in the provided document. Quote it accurately.
- Do not invent contract terms, defined terms, section numbers, or quotations.
- Do not invent statutes, regulations, or case law. If legal authority is relevant, mark it as an attorney verification item.
- Do not invent or assume deadlines. Treat any signing or negotiation deadline as user-supplied or unverified.
- A triage rating of GREEN ("clear to route for signature") is a workflow signal, not authorization to sign. Attorney review and sign-off remain required before any NDA is signed.
- Do not draft new clause language or restructure provisions. Propose the direction of a change and route substantive drafting to an attorney.
- Distinguish what the contract says from what you assume and from what the attorney must confirm.
- Preserve confidentiality and privilege: the review is attorney work product. Do not place client-sensitive facts into reusable templates.
- Flag every point of uncertainty rather than resolving it silently.
- **Severity floor.** Once an issue has been rated High priority in the prioritized redline points or risk table, that rating must not be silently downgraded. Any reduction in priority is an explicit attorney decision and must be recorded as such (e.g., "Downgraded from High to Medium by [attorney], [date], reason: [brief rationale]"). This applies regardless of the counterparty's explanation or commercial commonness of the provision.
- **Profile reference is optional, not authoritative.** Where `practice-profiles/contracts.md` is loaded, its Standard Positions and Escalation Thresholds inform the draft but never substitute for attorney judgment. The profile is a configuration record approved by the practice group; it is not legal advice and does not override the skill's normal attorney-verification gates. If the profile's standing positions conflict with the matter facts or with what the supervising attorney concludes, the attorney prevails.

## Workflow

This skill draws on shared contract-review reference material in `skills/contracts/references/`: `red-flags.md` (red-flag catalogue), `negotiability-ratings.md` (six-rating negotiability rubric), `market-benchmark-framework.md` (benchmarking discipline and market-practice vocabulary), `fallback-language-bank.md` (sample preferred and fallback positions by clause type), `document-type-checklists.md` (per-document-type checklists), `clause-category-checklist.md` (cross-document clause-category completeness sweep), `market-standard-baselines.md` (open-standard baseline comparisons), and `redline-output-guidance.md` (how to frame redline direction). Consult them at the steps noted below.

1. **Confirm inputs.** Verify you have the full NDA text, the client's role, and the transaction context. If anything is missing, request it before proceeding.
2. **Transaction-context check.** If the NDA is part of an M&A, employment, or investment transaction, stop and route the matter to specialist counsel (see Do Not Use When). Continue only for stand-alone commercial NDAs.
3. **Identify the structure.** Locate and label the core provisions: parties, definition of Confidential Information, permitted use, standard exclusions, term and survival, return/destruction, remedies, and governing law. Use the NDA checklist in `skills/contracts/references/document-type-checklists.md` to confirm nothing is overlooked, and run the formation/term and restrictive-covenant groups of `skills/contracts/references/clause-category-checklist.md` as a fast completeness pass across clause categories before the deeper review.
4. **Red flags quick scan.** Run a fast first pass against the red-flag catalogue in `skills/contracts/references/red-flags.md`. Record each red-flag pattern present, or note that none surfaced in the scan. This scan orients the deeper review; it does not replace it.
5. **Scope check.** Scan for obligations that go beyond confidentiality — for example a standstill, exclusivity, non-solicitation, non-competition, IP assignment, a licensing grant, a right of first refusal, a most-favored-nation clause, broad arbitration, or a governing-law clause reaching beyond confidentiality disputes. Any such term means the document is more than an NDA: flag it prominently and raise the triage rating accordingly.
6. **Summarize each key term** in plain language, citing the section number as written.
7. **Assess risk allocation from the client's role.** A receiving party and a disclosing party care about opposite asymmetries; analyze from the client's actual position.
8. **Benchmark against the client's standard positions.** If a playbook was provided — either inline by the user or via the loaded `practice-profiles/contracts.md` Standard Positions section — note where the NDA matches it, where it deviates, and where any term hits a "never accept" position. Where the profile is loaded but a specific term is silent in its Standard Positions, treat that term as not addressed by the playbook and flag for attorney review. Record any market comparison using the discipline in `skills/contracts/references/market-benchmark-framework.md`: characterize each relevant term with the controlled vocabulary (Common, Aggressive, Unusual, Depends on Leverage, Needs Attorney Confirmation), state the basis and supporting source, and flag every characterization not backed by a playbook, comparable, counterparty prior form, or attorney-supplied norm as an attorney-verification item. AgentCounsel does not supply market data. For a stand-alone mutual or unilateral NDA, also consider a baseline comparison against the oneNDA open standard using `skills/contracts/references/market-standard-baselines.md`.
9. **Flag missing or one-sided terms** — for example, no standard exclusions, a perpetual term on all information, broad injunctive-relief language, or unilateral obligations in a document labeled "mutual."
10. **Build the risk table** using `templates/nda-risk-table.md`.
11. **Rate negotiability.** For each material issue, assign one of the six negotiability ratings from `skills/contracts/references/negotiability-ratings.md` — Must Push, Strong Push, Business Call, Acceptable if Balanced, Low Priority, or Do Not Spend Leverage — with a one-line rationale drawn from leverage, who drafted the form, the deal value, and any regulatory floor.
12. **Draft prioritized redline points.** Rank issues High / Medium / Low. For each, following `skills/contracts/references/redline-output-guidance.md`, state: the issue, why it matters, a **Preferred Position**, a **Fallback Position**, and a **Suggested Redline Direction** — the direction of the change, not final clause language unless the user asks for it. Use `skills/contracts/references/fallback-language-bank.md` to help articulate preferred and fallback positions. Route substantive drafting to an attorney.
13. **Internal consistency check.** Confirm that defined terms, party names, cross-references, and section numbers are used consistently throughout the NDA. Flag any defined-but-unused term, used-but-undefined term, broken cross-reference, mismatched party label, or numbering gap.
14. **Assign an overall triage rating:**
    - **GREEN — clear to route for signature.** Terms are consistent with the client's role and standard positions; no obligations beyond confidentiality; no missing protection that matters for the client's role. Attorney sign-off is still required.
    - **YELLOW — flag for negotiation or approver review.** One or more terms deviate from the client's standard positions or are one-sided but not dealbreakers; or a playbook is silent on a material term; or the scope check found a non-confidentiality term that needs review.
    - **RED — stop and escalate.** A term hits a "never accept" position; there is a structural mismatch (such as unilateral obligations in a "mutual" NDA, or a perpetual term on all information); or the document carries significant non-confidentiality obligations or arises in an M&A, employment, or investment context.
15. **List attorney verification items** — governing-law implications, enforceability questions, every unverified benchmark, and anything requiring legal judgment.
16. **Draft a business-friendly summary.** Produce a short, plain-language summary for non-lawyer stakeholders: the overall posture, the few terms that matter most, what to push on and why, and what — if anything — would stop signature. Use the stakeholder-communication language patterns in `skills/contracts/references/negotiability-ratings.md`. Avoid legal jargon.
17. **Assemble the output** and label it as a draft for attorney review.

## Output Format

Deliver:

1. **Triage Rating** — GREEN / YELLOW / RED, with a one-line rationale.
2. **Summary** — 3-5 sentences: document type, client role, overall risk posture.
3. **Red Flags Quick Scan** — each red-flag pattern from `skills/contracts/references/red-flags.md` found in the NDA, or a note that none surfaced in the scan.
4. **Key Terms Table** — plain-language summary with section references.
5. **Scope Check** — whether the document contains obligations beyond confidentiality, and which.
6. **Risk Table** — from `templates/nda-risk-table.md`.
7. **Negotiability Table** — a table covering each material issue, with columns: Issue | Negotiability Rating | Basis | Recommended Lawyer Action. The Negotiability Rating is one of the six ratings defined in `skills/contracts/references/negotiability-ratings.md` (Must Push, Strong Push, Business Call, Acceptable if Balanced, Low Priority, Do Not Spend Leverage); the Basis is a one-line rationale.
8. **Market Practice Notes** — any market comparison, recorded using `skills/contracts/references/market-benchmark-framework.md`. Characterize each relevant term with the controlled vocabulary (Common, Aggressive, Unusual, Depends on Leverage, Needs Attorney Confirmation), state the basis and supporting source, and flag every characterization not backed by a playbook, comparable, counterparty prior form, or attorney-supplied norm for attorney verification. AgentCounsel does not supply market data.
9. **Prioritized Redline Points** — High / Medium / Low. Each point states the issue and why it matters, a **Preferred Position**, a **Fallback Position**, and a **Suggested Redline Direction** (direction of change, not final language), following `skills/contracts/references/redline-output-guidance.md`. Use `skills/contracts/references/fallback-language-bank.md` to help articulate preferred and fallback positions.
10. **Business-Friendly Summary** — a short, plain-language summary for non-lawyer stakeholders: the overall posture, the few terms that matter most, what to push on and why, and what — if anything — would stop signature. Avoid legal jargon.
11. **Internal Consistency Check** — whether defined terms, party names, cross-references, and section numbers are used consistently, with any inconsistency flagged.
12. **Attorney Verification Items** — open questions and items requiring legal judgment.
13. **Assumptions** — every assumption made, listed explicitly.

Use placeholders like `[CONFIRM: governing law]` wherever information is missing. Do not fill gaps with invented content.

### Optional: Business Stakeholder Summary

When the output will be used to brief a non-lawyer business stakeholder — a product owner, deal lead, people manager, founder, or executive — add a **Business Stakeholder Summary** as a clearly separated, plainly labeled section, following `core/business-stakeholder-communication.md`. Produce it only when the user requests it or when the audience is plainly a business decision-maker. It is an addition to the deliverable above — never a replacement for it, and never a substitute for attorney review. It contains:

- **Business Summary** — the bottom line in plain language, with unnecessary legal jargon removed and legal risk stated separately from business and commercial risk.
- **Decision Needed** — the specific business decision(s) now on the table, stated as concrete choices, each with its owner.
- **Recommended Ask** — the legal team's recommended position or course of action, framed as a recommendation for the business to weigh, not a decision made on its behalf.
- **Fallback Position** — the minimum acceptable alternative if the Recommended Ask cannot be achieved.
- **Escalation Needed?** — whether the matter should be escalated, to whom (senior management, the board, or outside counsel), and why — or a plain statement that no escalation is needed.

## Attorney Verification Checklist

- [ ] The NDA text reviewed is complete and final.
- [ ] The client's role (disclosing / receiving / mutual) is correctly identified.
- [ ] The transaction context is confirmed; if the NDA arises in an M&A, employment, or investment deal, specialist counsel has been involved.
- [ ] The scope check is complete; if the document contains obligations beyond confidentiality, it has been reviewed as more than an NDA.
- [ ] All section references and quotations match the source document.
- [ ] No legal authority, statute, or case law has been asserted without verification.
- [ ] Enforceability of remedies and any restrictive covenants has been assessed under the governing law.
- [ ] Governing law and jurisdiction are appropriate for the client.
- [ ] Term and survival periods are acceptable for the type of information being shared.
- [ ] The triage rating and risk ratings reflect the client's standard positions, role, and leverage.
- [ ] The red-flag quick scan and the negotiability table have been reviewed; each of the six-scale negotiability ratings reflects the client's actual leverage and standard positions.
- [ ] Every market-practice characterization has a stated basis and supporting source; no market benchmark has been relied on without independent verification.
- [ ] Preferred and fallback positions reflect the client's actual leverage and standard positions.
- [ ] The business-friendly summary accurately reflects the review and neither overstates nor understates any risk.
- [ ] The internal consistency check is complete; defined terms and cross-references are sound.
- [ ] A GREEN rating has attorney sign-off before the NDA is signed.
- [ ] All assumptions and open items are resolved before the review is relied upon.
- [ ] If a practice profile was loaded: every Standard Position and Escalation Threshold that applies to the matter facts has been surfaced; deviations are flagged; profile-silent items are flagged as not-yet-addressed by the playbook.
- [ ] If no practice profile was loaded: any benchmarking or "standard position" framing in the output is grounded in user-supplied inline data, not assumed.

=== END AGENTCOUNSEL CORE SKILL ===

=== BEGIN AGENTCOUNSEL SPEC ===
Canonical path: skills/contracts/nda-review/SPEC.json
{
  "schema_version": "2.0",
  "skill_id": "contracts/nda-review",
  "inherits": [
    "core/business-stakeholder-communication.md"
  ],
  "gates": {
    "custom": [
      {
        "id": "specialist-transaction-context",
        "condition": "The NDA is part of an M&A, employment, or investment transaction.",
        "action": "stop-and-escalate",
        "reason": "The confidentiality terms require transaction-specific specialist review rather than stand-alone commercial NDA triage."
      },
      {
        "id": "non-confidentiality-obligations",
        "condition": "The document contains standstill, exclusivity, non-solicitation, non-competition, IP assignment, license, right-of-first-refusal, most-favored-nation, or similarly broader obligations.",
        "action": "require-attorney-confirmation",
        "reason": "The document may be more than an NDA and cannot be routed for signature on confidentiality review alone."
      }
    ]
  },
  "execution_modes": [
    {
      "id": "quick-triage",
      "enabled": true,
      "purpose": "Confirm the document is a stand-alone commercial NDA, identify missing inputs, scan for obligations beyond confidentiality, and return only the preliminary escalation posture.",
      "output_detail": "minimal",
      "quality_checks": [
        "attorney-review-gate",
        "source-validation-check"
      ]
    },
    {
      "id": "standard",
      "enabled": true,
      "purpose": "Produce the standard NDA triage rating, key-term summary, risk table, negotiation priorities, and attorney-verification items.",
      "output_detail": "standard",
      "quality_checks": [
        "attorney-review-gate",
        "source-validation-check",
        "assumption-audit",
        "legal-prose-polish"
      ]
    },
    {
      "id": "deep-review",
      "enabled": true,
      "purpose": "Run the complete clause-category, red-flag, market-benchmark, negotiability, internal-consistency, and stakeholder-summary workflow with all applicable reference modules.",
      "output_detail": "expanded",
      "quality_checks": [
        "attorney-review-gate",
        "source-validation-check",
        "assumption-audit",
        "hallucination-red-team",
        "output-format-compliance-check",
        "privilege-confidentiality-check",
        "legal-prose-polish"
      ]
    }
  ],
  "input_schema": [
    {
      "id": "clients-role-disclosing-receiving-or-mutual",
      "label": "Client role",
      "type": "enum",
      "required": true,
      "description": "The client's role under the NDA.",
      "source_requirement": "user-provided",
      "may_infer": false,
      "sensitive": false,
      "enum": [
        "disclosing",
        "receiving",
        "mutual"
      ]
    },
    {
      "id": "transaction-context",
      "label": "Transaction context",
      "type": "enum",
      "required": true,
      "description": "The transaction setting used to determine whether stand-alone NDA triage is appropriate.",
      "source_requirement": "user-provided",
      "may_infer": false,
      "sensitive": false,
      "enum": [
        "standalone-commercial",
        "m-and-a",
        "employment",
        "investment",
        "other"
      ]
    }
  ],
  "output_schema": [
    {
      "id": "structured-risk-summary",
      "label": "Structured risk summary",
      "type": "table",
      "required": true,
      "description": "Material NDA provisions, exact section evidence, client risk, severity, preferred position, fallback position, and attorney action.",
      "attorney_review_required": true
    },
    {
      "id": "prioritized-redline-points-for-attorney-review",
      "label": "Prioritized redline points for attorney review",
      "type": "checklist",
      "required": true,
      "description": "High, medium, and low negotiation points with preferred and fallback positions and no final clause language unless attorney-directed.",
      "attorney_review_required": true
    }
  ],
  "evidence_schema": {
    "required_fields": [
      "support_text"
    ],
    "fields": [
      {
        "id": "provision_name",
        "type": "text",
        "description": "The provision or clause category supporting the issue."
      },
      {
        "id": "client_position",
        "type": "text",
        "description": "The client role and playbook position used in the analysis."
      }
    ]
  },
  "modules": [
    {
      "id": "nda-risk-table-template",
      "kind": "template",
      "path": "skills/contracts/nda-review/templates/nda-risk-table.md",
      "required": true,
      "load_when": "standard or deep-review mode"
    },
    {
      "id": "contract-red-flags",
      "kind": "reference",
      "path": "skills/contracts/references/red-flags.md",
      "required": true,
      "load_when": "all enabled modes"
    },
    {
      "id": "negotiability-ratings",
      "kind": "reference",
      "path": "skills/contracts/references/negotiability-ratings.md",
      "required": false,
      "load_when": "standard or deep-review mode when negotiation prioritization is requested"
    },
    {
      "id": "market-benchmark-framework",
      "kind": "reference",
      "path": "skills/contracts/references/market-benchmark-framework.md",
      "required": false,
      "load_when": "deep-review mode or when market practice is requested"
    },
    {
      "id": "contracts-practice-profile",
      "kind": "profile",
      "path": "practice-profiles/contracts.md",
      "required": false,
      "load_when": "a populated and attorney-approved contracts profile is available"
    }
  ]
}

=== END AGENTCOUNSEL SPEC ===

=== BEGIN AGENTCOUNSEL MODULE: nda-risk-table-template ===
Kind: template
Canonical path: skills/contracts/nda-review/templates/nda-risk-table.md
Load when: standard or deep-review mode

# NDA Risk Table

> Draft legal work product for attorney review. Not legal advice.
> Do not paste client-sensitive facts into a reusable copy of this template.

**Matter:** [matter name / number]
**Document reviewed:** [NDA title and date]
**Client role:** [Disclosing party / Receiving party / Mutual]
**Overall triage:** [GREEN — route for signature / YELLOW — flag for review / RED — stop and escalate]
**Reviewer:** [name]   **Review date:** [date]
**Governing law (as drafted):** [CONFIRM]

| # | Provision | Section | What it says (plain language) | Risk to client | Severity | Suggested change | Attorney note |
|---|-----------|---------|-------------------------------|----------------|----------|------------------|---------------|
| 1 | Definition of Confidential Information | [§] | | | | | |
| 2 | Permitted use | [§] | | | | | |
| 3 | Standard exclusions | [§] | | | | | |
| 4 | Term and survival | [§] | | | | | |
| 5 | Return / destruction | [§] | | | | | |
| 6 | Remedies / injunctive relief | [§] | | | | | |
| 7 | Governing law / jurisdiction | [§] | | | | | |
| 8 | Other restrictive covenants | [§] | | | | | |

## Severity key

- **High** — material exposure or one-sided allocation; address before signing.
- **Medium** — meaningful issue; negotiate where leverage allows.
- **Low** — minor or stylistic; note, but unlikely to block signing.

## Open items for attorney verification

- [ ] Enforceability of remedies and any restrictive covenants under the governing law.
- [ ] Whether the term and survival periods fit the sensitivity of the information.
- [ ] Whether the definition of Confidential Information is appropriately scoped for the client's role.
- [ ] Any item marked `[CONFIRM]` above.

=== END AGENTCOUNSEL MODULE: nda-risk-table-template ===

=== BEGIN AGENTCOUNSEL MODULE: contract-red-flags ===
Kind: reference
Canonical path: skills/contracts/references/red-flags.md
Load when: all enabled modes

> Shared reference material supporting the AgentCounsel contracts skills, used to help produce draft legal work product for attorney review — not legal advice.

# Contract Red-Flag Catalog

This catalog lists clause patterns and structural features that a reviewer should actively scan for during a contract review. Each entry describes the pattern, why it matters, what to check, and which client roles are most exposed. The catalog is organized by clause category to support a Red Flags Quick Scan output within the contracts skills.

This catalog is a review aid. It identifies what to look for and why. Whether a flagged pattern is actually problematic depends on the specific contract language, the client's role, the business context, and attorney judgment. Every flagged item is a candidate for attorney verification — not a legal conclusion.

---

## How to Use This Catalog

For each clause category below:

1. Locate the relevant provision in the document under review (or note its absence — a missing provision is itself a red flag in many contexts).
2. Check the pattern description against the actual language.
3. If the pattern is present, add the item to the risk matrix and the issue list.
4. Note which client roles are most exposed and whether the client's role matches the exposure profile.
5. Flag every finding for attorney review; do not resolve ambiguity silently.

---

## 1. Limitation of Liability

### 1.1 Cap tied to a very short period or very low base

**Pattern:** The liability cap is calculated as fees paid in the prior one or two months, or a nominal fixed amount that is small relative to the realistic loss scenario.

**Why it matters:** If the client's realistic harm from a breach (data loss, business interruption, IP misappropriation) greatly exceeds the cap, the clause transfers nearly all downside risk to the client.

**What to check:**
- Quote the cap formula verbatim.
- Compare the cap amount to the client's estimated worst-case exposure and the total contract value.
- Identify whether the cap applies to all claims or only certain types.

**Most exposed:** Customer / buyer / licensee receiving services or data access; any party whose loss would be consequential in nature.

---

### 1.2 Consequential-damages waiver covering the client's primary loss type

**Pattern:** The waiver of indirect, consequential, incidental, or special damages is mutual in form but asymmetric in effect — because the client's realistic losses are almost entirely consequential (lost profits, business interruption, data loss) while the vendor's realistic losses are direct (unpaid fees).

**Why it matters:** A nominally mutual clause can be functionally one-sided if one party's harm is categorically different from the other's.

**What to check:**
- Quote the exclusion language exactly.
- Identify whether lost profits, lost data, or business interruption are expressly included or excluded.
- Check whether any carve-outs restore consequential-damages recovery for specific breach types (data breach, fraud, willful misconduct, IP infringement).

**Most exposed:** Customer / buyer relying on services for business operations; parties with high data or IP exposure.

---

### 1.3 No carve-outs for fraud, willful misconduct, or death/personal injury

**Pattern:** The cap and consequential-damages waiver apply to all claims with no exceptions for egregious conduct.

**Why it matters:** Absence of carve-outs for fraud, willful misconduct, gross negligence, or death/personal injury is non-standard and may be unenforceable in some jurisdictions `[verify jurisdiction]`.

**What to check:**
- List every carve-out that is present.
- Note any carve-out that is one-sided (e.g., data breach carved out for vendor but not for client).

**Most exposed:** Any party relying on the counterparty to handle sensitive data, physical property, or activities with personal-injury risk.

---

### 1.4 IP indemnity subject to liability cap

**Pattern:** The intellectual property indemnity is not carved out from the liability cap, meaning the indemnifying party's maximum exposure for an IP infringement claim is limited to the cap amount.

**Why it matters:** IP infringement claims can generate liability far exceeding typical fee-based caps. If the IP indemnity is capped, the party receiving the indemnity bears the excess risk.

**What to check:**
- Confirm whether the IP indemnity is expressly carved out from the cap.
- Check whether the indemnity is mutual or one-sided.

**Most exposed:** Licensee or customer accepting IP representations from the vendor.

---

## 2. Indemnification

### 2.1 Broad, one-sided indemnification

**Pattern:** The client is required to indemnify the vendor broadly (e.g., for any claim arising from client's "use" of the product or service) without a reciprocal indemnity running from vendor to client.

**Why it matters:** A unilateral indemnity can transfer risk for claims the client did not cause, including claims arising from the vendor's own defects or conduct.

**What to check:**
- Is the indemnity mutual or one-sided?
- What triggers the client's indemnity obligation — is "use" or "breach" defined narrowly?
- Is there a carve-out for claims caused by the vendor's own negligence or misconduct?

**Most exposed:** Customer / buyer who does not have leverage to insist on mutuality.

---

### 2.2 No procedural controls on indemnity claims

**Pattern:** The indemnification provision does not require prompt notice of a claim, does not give the indemnifying party control over the defense, and does not require the indemnified party's cooperation.

**Why it matters:** Without procedural controls, the indemnified party can settle a claim at the indemnifying party's expense or prejudice the defense by giving late notice.

**What to check:**
- Is there a notice requirement with a time frame?
- Is there a defense-control right for the indemnifying party?
- Is there a restriction on the indemnified party settling without consent?
- Is there a cooperation obligation?

**Most exposed:** Any party in the indemnifying role.

---

### 2.3 Indemnity triggered by IP claims arising from client modifications

**Pattern:** The client's IP indemnity obligation is triggered by any infringement claim related to the vendor's product, including where the infringement arises from the vendor's base product rather than the client's modifications.

**Why it matters:** The client should bear indemnity risk only for infringement resulting from its own modifications or misuse, not for the vendor's baseline IP risk.

**What to check:**
- Is the IP indemnity limited to claims caused by client modifications or client-provided materials?
- Is the vendor's own IP indemnity obligation clearly stated?

**Most exposed:** Customer / licensee who deploys or integrates vendor technology.

---

## 3. Intellectual Property

### 3.1 Future-tense assignment language

**Pattern:** Work-for-hire or assignment provisions use future-tense language ("will assign," "agrees to assign," "shall vest in") rather than a present-tense grant ("hereby assigns," "is hereby assigned," "vests in").

**Why it matters:** A future promise to assign may require a further act (a subsequent written assignment instrument) to perfect the transfer of ownership `[verify jurisdiction]`. Without that further act, ownership may remain with the assignor.

**What to check:**
- Quote the assignment language verbatim.
- Is it present-tense or future-tense?
- Is there a further-assurances or cooperation clause requiring the assignor to execute additional instruments?
- Is there a power of attorney as backup?

**Most exposed:** Client receiving a work product assignment, acquirer in an M&A diligence context.

---

### 3.2 No further-assurances obligation

**Pattern:** An IP assignment clause contains no obligation on the assignor to execute additional documents or take further steps to perfect the assignment.

**Why it matters:** Without a further-assurances clause, the assignee may be unable to register the IP, record the assignment, or enforce the assignment against third parties if the assignor later becomes uncooperative.

**What to check:**
- Is a further-assurances or cooperation obligation present?
- Is there a provision addressing what happens if the assignor cannot be located or refuses to cooperate?

**Most exposed:** Assignee / buyer / commissioning party.

---

### 3.3 Broad vendor background IP carve-out

**Pattern:** The vendor retains broad rights to background IP, pre-existing tools, platforms, and methodologies used to create the deliverables, with no license back to the client to use those elements embedded in the deliverables.

**Why it matters:** If vendor-retained background IP is embedded in the deliverables, the client owns a deliverable it cannot independently use or modify without an ongoing vendor license.

**What to check:**
- What is included in the definition of background IP?
- Is there a license back to the client for use of background IP embedded in deliverables?
- Can the client's use survive termination of the contract?

**Most exposed:** Client commissioning custom work product (software, creative content, technology).

---

### 3.4 No moral rights treatment

**Pattern:** An assignment of creative works makes no mention of moral rights — no waiver, no confirmation that the jurisdiction does not recognize moral rights, and no express inclusion in the assignment.

**Why it matters:** In jurisdictions that recognize moral rights, an assignment of copyright does not automatically transfer or extinguish moral rights `[verify jurisdiction]`. An unaddressed moral rights position can complicate the assignee's ability to modify or commercialize the work.

**What to check:**
- Does the clause include a waiver of moral rights?
- Is a waiver effective in the governing jurisdiction? `[verify jurisdiction]`

**Most exposed:** Assignee of creative or software works intended for modification or commercialization.

---

### 3.5 Residual rights / residual knowledge clause

**Pattern:** The contract includes a residual rights or residual knowledge clause allowing the vendor to retain and use unaided human memory of confidential information, ideas, concepts, or methods encountered during performance.

**Why it matters:** A residual-knowledge clause can be a significant erosion of confidentiality and IP protection — the vendor's personnel can, in theory, use retained knowledge to benefit competitors.

**What to check:**
- Is the residual clause limited in scope (e.g., to genuinely unaided memory only, excluding written notes or deliberate memorization)?
- Does the residual clause carve out trade secrets or specifically identified confidential categories?
- Does the clause interact with the IP assignment — could retained knowledge be used to recreate assigned work?

**Most exposed:** Disclosing party; client commissioning proprietary development.

---

## 4. Termination

### 4.1 Asymmetric termination for convenience

**Pattern:** One party (typically the vendor) has a termination-for-convenience right with a short notice period, but the other party (typically the client) does not, or must pay a substantial termination fee.

**Why it matters:** The party without a convenience termination right is locked in, while the counterparty retains flexibility.

**What to check:**
- Are termination-for-convenience rights mutual?
- What is the required notice period?
- Are there fees payable on termination (wind-down fees, accelerated payments, break fees)?

**Most exposed:** Client locked into a long-term services or subscription relationship.

---

### 4.2 Short cure period or no cure period for material breach

**Pattern:** Termination for cause is triggered on breach with a very short cure period (or no cure period), meaning a minor operational failure can give rise to immediate termination.

**Why it matters:** A short or absent cure period can be used opportunistically to terminate a relationship that the other party wants to exit for other reasons.

**What to check:**
- Is the cure period reasonable given the nature of the obligations?
- Is the right to terminate limited to material breach, or does it extend to any breach?
- Is the "material breach" standard defined, or is it left open?

**Most exposed:** Party performing services or delivering technology who bears the risk of inadvertent breach.

---

### 4.3 Broad termination triggers beyond breach

**Pattern:** Termination rights are triggered by events beyond breach: insolvency, change of control, regulatory action, or subjective standards ("if [party] determines in its sole discretion that performance is unsatisfactory").

**Why it matters:** Broad termination triggers can be exercised to exit a deal that the counterparty simply no longer wants, regardless of fault.

**What to check:**
- List every termination trigger in the agreement.
- Flag any trigger based on subjective determination without an objective standard.
- Check whether insolvency termination may be unenforceable in the relevant jurisdiction `[verify jurisdiction]`.

**Most exposed:** Party who has invested significantly in relationship setup (data migration, integration, customization).

---

### 4.4 Inadequate wind-down and data return provisions

**Pattern:** The termination section says nothing about transition assistance, data export, data deletion timelines, return of confidential information, or continuity of access during a wind-down period.

**Why it matters:** Without wind-down provisions, a party can be cut off from data, systems, or services immediately on termination with no ability to transition.

**What to check:**
- Is there a transition assistance obligation (and for how long)?
- Is there a data export right before deletion?
- Is there a data deletion obligation and timeline?
- Are there post-termination access rights for retrieval?

**Most exposed:** Customer or client whose operations depend on access to vendor-held data or systems.

---

## 5. Fees, Payment, and Price Escalation

### 5.1 Unilateral price escalation right

**Pattern:** The vendor has the right to increase fees unilaterally on notice (or at renewal), with no cap on the increase percentage and no right for the client to terminate without penalty if the increase is unacceptable.

**Why it matters:** An uncapped unilateral escalation right gives the vendor leverage to impose significant price increases that the client cannot easily exit.

**What to check:**
- Is the escalation right unilateral or subject to mutual agreement?
- Is there a cap on annual increases (e.g., tied to a published index)?
- Does the client have a termination right if it rejects the increase?

**Most exposed:** Client in a multi-year or auto-renewing subscription or services contract.

---

### 5.2 Fees payable on termination or early exit

**Pattern:** The contract requires the client to pay all remaining fees for the unexpired term if the contract is terminated for any reason (including vendor breach), or imposes a substantial early-termination fee.

**Why it matters:** An obligation to pay all remaining fees on termination, even for vendor breach, shifts the financial risk of the relationship to the client.

**What to check:**
- Does the termination-fee obligation apply even on termination for vendor cause?
- Are there any offsets or credits for the vendor's cost savings on early exit?
- Are there acceleration provisions in other parts of the contract (e.g., payment on insolvency)?

**Most exposed:** Client in a long-term, high-value contract.

---

### 5.3 Short payment window with automatic late fees or suspension right

**Pattern:** Payment is due within a very short window (e.g., 5 or 10 days of invoice), with automatic late fees, interest, or the right to suspend services immediately on non-payment.

**Why it matters:** Short payment windows and suspension rights can be used to create leverage, particularly if the client's accounts-payable cycle is longer than the payment window.

**What to check:**
- What is the payment window?
- Is a dispute or good-faith objection sufficient to pause the payment obligation?
- What is the suspension notice period?
- Are late fees or interest rates specified, and are they commercially reasonable?

**Most exposed:** Customer with standard payment cycles; client who relies on continuous service access.

---

### 5.4 Fees due on disputed invoices

**Pattern:** The contract requires payment of all invoiced amounts — including amounts under good-faith dispute — within the payment window, with no mechanism for withholding disputed amounts pending resolution.

**Why it matters:** Requiring payment of disputed amounts removes the client's leverage to dispute invoices without facing late fees, suspension, or default.

**What to check:**
- Is there an invoice dispute mechanism?
- Can the client withhold disputed amounts without triggering late fees or default?
- What is the resolution process for invoice disputes?

**Most exposed:** Client with complex or variable invoicing arrangements.

---

## 6. Confidentiality

### 6.1 Overly broad definition of Confidential Information

**Pattern:** "Confidential Information" is defined to include essentially everything the disclosing party has ever communicated — oral, written, or observed — with no requirement of marking or identification.

**Why it matters:** An over-broad definition creates compliance difficulties and potentially exposes the receiving party to liability for normal business activities (e.g., using generally available information or independently developed knowledge).

**What to check:**
- What are the standard exclusions (publicly available information, independently developed, received from third parties without restriction)?
- Is oral information included? If so, what confirmation steps are required?
- Is there a residual knowledge carve-out (see Section 3.5)?

**Most exposed:** Receiving party who must manage and segregate a very broad confidentiality obligation.

---

### 6.2 Perpetual confidentiality obligation

**Pattern:** Confidentiality obligations survive termination indefinitely, with no sunset period.

**Why it matters:** Perpetual obligations can be overly burdensome, difficult to manage operationally over time, and may be unenforceable in some jurisdictions `[verify jurisdiction]`.

**What to check:**
- Is the confidentiality term defined?
- Are trade secrets carved out for longer or indefinite protection (which may be appropriate)?
- Does the duration align with the sensitivity of the information and market norms for the transaction type?

**Most exposed:** Receiving party with long-term operational compliance obligations.

---

### 6.3 No return-or-destroy obligation

**Pattern:** The confidentiality section contains no obligation to return or destroy confidential information on termination or at the disclosing party's request.

**Why it matters:** Without a return-or-destroy obligation, confidential information may remain with the receiving party indefinitely after the relationship ends.

**What to check:**
- Is there a return-or-destroy obligation?
- Is there a certification requirement?
- Are backup copies and legal hold exceptions addressed?

**Most exposed:** Disclosing party sharing sensitive business, technical, or personal information.

---

## 7. Data, Privacy, and Security

### 7.1 No data processing agreement or data processing terms

**Pattern:** The contract involves the vendor processing personal data on behalf of the client, but contains no data processing agreement, data processing addendum, or data-specific terms addressing processing purposes, data subject rights, security requirements, sub-processing, data return, and deletion.

**Why it matters:** Regulatory frameworks applicable to personal data processing may require a data processing agreement and may impose liability for its absence `[verify jurisdiction]`.

**What to check:**
- Does the contract involve vendor processing of personal data?
- Is there a data processing agreement or addendum?
- If a DPA is referenced but not attached, confirm it exists and is incorporated by reference.

**Most exposed:** Client acting as data controller whose regulatory obligations flow to its processors.

---

### 7.2 No breach notification obligation, or notification period is very long

**Pattern:** The vendor has no obligation to notify the client of a security breach or data incident, or the notification period is so long that it would prevent timely regulatory or customer notification.

**Why it matters:** Failure to receive timely breach notification can cause the client to miss mandatory reporting deadlines under applicable regulatory frameworks `[verify jurisdiction]`.

**What to check:**
- Is there a breach notification obligation?
- What is the notification trigger (confirmed breach vs. suspected incident)?
- Is the notification period consistent with applicable legal requirements? `[verify jurisdiction]`
- Is the notification obligation to the client, or does the vendor notify regulators directly?

**Most exposed:** Client acting as data controller or subject to sector-specific security obligations.

---

### 7.3 Broad data use rights granted to vendor

**Pattern:** The vendor is permitted to use client data for its own purposes — product improvement, analytics, benchmarking, training AI or machine learning models — with broad or unlimited scope.

**Why it matters:** Broad data use rights can expose the client's confidential business data, personal data it controls, or proprietary datasets to use for the vendor's competitive benefit.

**What to check:**
- What are the permitted uses of client data by the vendor?
- Is the scope limited to providing the contracted services?
- Can the vendor use client data to train models or develop competing services?
- If the contract involves AI or machine learning services, route to or also apply the `ai-vendor-terms-review` skill.

**Most exposed:** Client with proprietary data, personal data obligations, or competitive sensitivity about usage patterns.

---

### 7.4 No data deletion or portability right on termination

**Pattern:** The contract does not require the vendor to delete client data on termination, does not specify a deletion timeline, and does not provide a right for the client to export its data in a usable format before deletion.

**Why it matters:** Without a deletion and portability right, client data may persist indefinitely on vendor systems, the client may be unable to migrate to a replacement vendor, and residual data may create ongoing compliance or competitive risk.

**What to check:**
- Is there a data deletion obligation? When does it trigger?
- Is there a data export or portability right? In what format?
- Is there a post-termination access window for retrieval?

**Most exposed:** Client with significant data stored on or processed by vendor systems.

---

## 8. Dispute Resolution

### 8.1 Mandatory arbitration in a forum inconvenient for the client

**Pattern:** The contract requires all disputes to be resolved by arbitration in a specific city or jurisdiction that is the vendor's home forum and is inconvenient or expensive for the client.

**Why it matters:** Inconvenient forum requirements raise the cost and burden of dispute resolution, which can deter a client from pursuing legitimate claims.

**What to check:**
- Is arbitration mandatory or permissive?
- What is the venue?
- Which arbitration rules govern?
- Is there a fee allocation provision?
- Does the clause include a waiver of jury trial? `[verify jurisdiction]`

**Most exposed:** Client who is geographically distant from the vendor, or a smaller party with limited litigation resources.

---

### 8.2 Class action or collective claim waiver

**Pattern:** The dispute resolution clause waives the right to bring or participate in class action or collective proceedings.

**Why it matters:** Class action waivers may limit the client's ability to participate in or benefit from group relief `[verify jurisdiction]`.

**What to check:**
- Is a class action waiver present?
- Is it enforceable in the applicable jurisdiction? `[verify jurisdiction]`
- Does the waiver cover all types of claims or only certain categories?

**Most exposed:** Client exposed to systemic vendor conduct affecting many customers.

---

### 8.3 No carve-out for injunctive relief in court

**Pattern:** A mandatory arbitration clause does not carve out the right to seek emergency or preliminary injunctive relief in a court of competent jurisdiction.

**Why it matters:** Arbitration proceedings typically move more slowly than emergency court applications. Without a court carve-out, a party facing imminent harm (e.g., ongoing misappropriation of trade secrets) may be unable to obtain timely interim relief.

**What to check:**
- Is there a carve-out permitting either party to seek injunctive or other equitable relief in court?
- Is the carve-out mutual?

**Most exposed:** Any party whose potential harm could be irreparable and time-sensitive (IP holder, data owner).

---

## 9. Auto-Renewal

### 9.1 Auto-renewal with short or unclear non-renewal window

**Pattern:** The contract automatically renews for the same term unless a party gives notice within a window that is short, poorly defined, or measured from an unclear trigger date.

**Why it matters:** A client who misses the non-renewal window is committed to another full term, potentially with updated pricing or revised terms.

**What to check:**
- What is the auto-renewal notice window?
- When does the window open and close relative to the renewal date?
- Is the renewal for the same term length and pricing, or does pricing change?
- Does any price-escalation right apply automatically at renewal?

**Most exposed:** Client in a multi-year subscription or services contract who may not actively track renewal dates.

---

### 9.2 Renewal at modified terms

**Pattern:** On auto-renewal, the contract incorporates the vendor's then-current standard terms or pricing rather than the terms in effect at signing.

**Why it matters:** The client may be bound on renewal to materially different terms without receiving notice of specific changes.

**What to check:**
- Does the renewal lock in existing terms or incorporate updated terms?
- Is there a requirement for the vendor to notify the client of material changes before renewal?
- Is there a right to reject updated terms and terminate on shorter notice?

**Most exposed:** Client in a long-term, auto-renewing relationship with a vendor who regularly updates its standard terms.

---

## 10. Assignment and Change of Control

### 10.1 No consent right on vendor assignment or change of control

**Pattern:** The vendor may assign the contract, or undergo a change of control (acquisition, merger), without the client's consent, automatically binding the client to the acquirer or assignee.

**Why it matters:** The client may be bound to a counterparty it would not have chosen — including a competitor — with no ability to exit.

**What to check:**
- Does change of control trigger any client rights (consent right, termination right, step-in right)?
- Is assignment limited to affiliates, or is it fully unrestricted?
- Does the client have a right to terminate if change-of-control consent is not obtained?

**Most exposed:** Client in a relationship where the vendor's identity matters (key-person services, sensitive data sharing, competitive sensitivity).

---

### 10.2 Client's anti-assignment rights inconsistent with its own transaction plans

**Pattern:** The contract restricts the client's ability to assign (e.g., requires vendor consent, prohibits assignment to affiliates) in a way that would require consent for the client's own anticipated corporate transactions.

**Why it matters:** Anti-assignment restrictions can require consent from the counterparty for the client's own M&A, restructuring, or affiliate transfers, potentially complicating or blocking internal transactions.

**What to check:**
- What are the client's assignment rights?
- Is assignment to affiliates permitted?
- Is there a change-of-control trigger for the client as well as the vendor?
- Does the client have any anticipated corporate transactions that would trigger the assignment provision?

**Most exposed:** Client undergoing or anticipating M&A activity, spin-off, or internal restructuring.

---

## 11. One-Sided or Unusual Clauses

### 11.1 Vendor's unilateral right to modify the agreement

**Pattern:** The vendor reserves the right to modify the contract, its terms of service, or incorporated policies unilaterally on notice (or by posting to a website), with continued use constituting acceptance.

**Why it matters:** Unilateral modification rights can change material terms — pricing, functionality, data rights, liability allocation — without requiring the client's affirmative consent.

**What to check:**
- Is the unilateral modification right subject to any limits?
- What notice is required?
- Does the client have a right to reject modifications and terminate without penalty?
- Are any terms expressly locked (e.g., pricing for a fixed term)?

**Most exposed:** Client in a subscription or platform-services relationship governed in part by online terms.

---

### 11.2 "Sole discretion" or subjective standards

**Pattern:** Key rights or obligations are conditioned on a party's "sole discretion," "satisfaction," or "good faith" determination, with no objective standard and no right of appeal or review.

**Why it matters:** Sole-discretion standards can be used to exit obligations, withhold approvals, or exercise rights in ways that are commercially unreasonable with limited recourse for the counterparty.

**What to check:**
- What decisions or determinations are left to sole discretion?
- Is the sole-discretion standard mutual or one-sided?
- Is there a deemed-approval mechanism if a decision is not made within a specified period?

**Most exposed:** Party whose performance, approval rights, or payment depends on a subjective determination by the counterparty.

---

### 11.3 Most-favored-nation or most-favored-customer clause

**Pattern:** One party is guaranteed pricing or terms at least as favorable as those the other party offers to any other customer (or a defined set of customers), without a clear definition of what is being compared or a mechanism to verify compliance.

**Why it matters:** MFN clauses create ongoing obligations that are difficult to monitor, can restrict pricing flexibility, and may interact poorly with regulatory requirements `[verify jurisdiction]`.

**What to check:**
- Is the MFN clause clearly defined as to scope, comparator class, and verification mechanism?
- Are there exceptions for promotional pricing, volume discounts, or bundled offerings?
- Does the clause require proactive disclosure of better pricing?

**Most exposed:** Party obligated to maintain MFN compliance over a long agreement term.

---

### 11.4 Unusual representations or warranties

**Pattern:** A party is required to represent or warrant matters that are inherently forward-looking, beyond its knowledge, or outside its control — for example, that third-party technology will perform in a particular way, or that a regulatory outcome will occur.

**Why it matters:** Representations beyond a party's knowledge or control create strict-liability exposure for breach regardless of the party's reasonable efforts.

**What to check:**
- Are any representations or warranties qualified by knowledge (`"to the best of its knowledge"`) when that qualifier is appropriate?
- Are any representations inherently forward-looking or speculative?
- What is the remedy for breach of a warranty — does it go beyond the limitation-of-liability cap?

**Most exposed:** Party making representations about third-party products, regulatory approvals, or future performance.

---

### 11.5 Standstill, non-solicitation, or non-compete embedded in a commercial agreement

**Pattern:** What appears to be a routine commercial agreement contains a standstill clause, a non-solicitation of employees or customers, or a non-compete restriction buried in the confidentiality, term, or general covenants section rather than labeled as such.

**Why it matters:** Restrictive covenants may have enforceability requirements, geographic or duration limits, and regulatory implications that vary by jurisdiction `[verify jurisdiction]`. Finding them embedded in routine commercial agreements is itself a red flag.

**What to check:**
- Perform a scope check across the entire document for non-compete, non-solicit, and standstill language (see also: `nda-review` scope check).
- Flag any such provision prominently regardless of where it appears in the agreement.
- Note that enforceability of restrictive covenants is jurisdiction-dependent `[verify jurisdiction]`.

**Most exposed:** Client whose operational flexibility could be constrained post-signing or post-termination.

---

## 12. Warranties and Disclaimers

See also Section 11.4 on representations or warranties that are forward-looking or extend beyond a party's knowledge.

### 12.1 Blanket "as is" disclaimer leaving no performance recourse

**Pattern:** The counterparty disclaims all warranties — express and implied, including merchantability, fitness for a particular purpose, and non-infringement — and provides the product or service strictly "as is," with no affirmative warranty that it will perform as described or conform to its documentation.

**Why it matters:** If the counterparty makes no enforceable performance promise, the client may have no contractual remedy when the product or service fails to do what the client is paying for — even if the failure is total.

**What to check:**
- Is there any affirmative warranty (conformance to documentation, conformance to specifications, or performance for a defined period)?
- Quote the disclaimer verbatim and identify exactly which warranties are disclaimed.
- Does the disclaimer's breadth conflict with the order form, statement of work, or materials the client relied on?

**Most exposed:** Customer / buyer / licensee relying on the product or service for a business-critical function.

---

### 12.2 Warranty remedy limited to repair-or-replace as the sole remedy

**Pattern:** The only remedy for breach of warranty is the counterparty's election to repair, replace, or re-perform, with no right to a refund, no right to terminate, and no damages if repair or replacement fails.

**Why it matters:** A sole-and-exclusive repair-or-replace remedy can leave the client with no exit and no compensation if the counterparty cannot actually cure the defect.

**What to check:**
- Is the remedy expressed as "sole and exclusive"?
- Is there a fallback (refund or termination right) if repair or replacement fails or cannot be completed within a reasonable time?
- How does the remedy limitation interact with the liability cap (see Section 1)?

**Most exposed:** Customer / buyer of goods, software, or services with defined performance expectations.

---

### 12.3 Warranty period or survival too short to surface real defects

**Pattern:** The warranty period is very short relative to how long defects would realistically take to appear, or warranties expire on delivery or acceptance with no post-acceptance survival.

**Why it matters:** A warranty that expires before latent defects can reasonably be discovered provides little practical protection.

**What to check:**
- What is the warranty period, and when does it start (delivery, acceptance, go-live)?
- Is the period appropriate for the nature of the goods or services and the way defects would surface?
- Is the survival of warranties on termination addressed?

**Most exposed:** Buyer of goods or deliverables where defects may be latent.

---

## 13. Service Levels and Performance Commitments

### 13.1 No service levels for a service the client depends on

**Pattern:** The agreement is for an ongoing service (hosting, SaaS, managed services, support) but contains no uptime commitment, no response or resolution targets, and no defined performance standard.

**Why it matters:** Without a defined service level, the client has no objective standard to measure performance against and no contractual trigger for a remedy when the service degrades.

**What to check:**
- Is there any uptime, availability, or response-time commitment?
- If service levels appear in a separate SLA or exhibit, confirm it is attached and incorporated.
- Is service availability stated as a warranty, a service-level commitment, or merely aspirational language?

**Most exposed:** Customer relying on continuous service availability for operations.

---

### 13.2 Service credits framed as the sole and exclusive remedy

**Pattern:** When the counterparty misses a service level, the client's only remedy is a service credit — typically a small percentage of fees — and the contract states this is the sole and exclusive remedy for any performance failure.

**Why it matters:** Service credits are often far smaller than the client's actual loss from an outage. As a sole-and-exclusive remedy, they can foreclose any other claim for chronic or severe underperformance.

**What to check:**
- Are service credits expressed as the sole and exclusive remedy?
- Is there a right to terminate for chronic or material SLA failure, separate from the credit mechanism?
- Must the client claim credits within a short window or forfeit them?

**Most exposed:** Customer whose realistic outage losses far exceed a fee-percentage credit.

---

### 13.3 Exclusions that swallow the service-level commitment

**Pattern:** The uptime or availability commitment is subject to broad exclusions — scheduled maintenance, emergency maintenance, third-party failures, "force majeure," anything outside the counterparty's "direct control" — wide enough to exclude most realistic downtime.

**Why it matters:** A high headline availability figure can be meaningless if the definition of measured downtime excludes the events that actually cause outages.

**What to check:**
- List every exclusion from the availability calculation.
- Is scheduled maintenance capped as to frequency, duration, notice, and off-peak windows?
- Does the exclusion for third-party or "outside our control" events swallow the commitment?

**Most exposed:** Customer relying on the headline availability figure without reading the measurement definition.

---

## 14. Insurance

### 14.1 No insurance requirement on the counterparty

**Pattern:** The agreement imposes no obligation on the counterparty to carry insurance, even though the counterparty's performance creates risks (property damage, bodily injury, professional error, data breach) that insurance would ordinarily backstop.

**Why it matters:** Without an insurance requirement, the client's ability to actually recover on an indemnity or damages claim depends entirely on the counterparty's balance sheet. An uninsured or judgment-proof counterparty makes a strong indemnity worth little.

**What to check:**
- Is any insurance required?
- Do the required coverage types match the risks the counterparty's performance creates (commercial general liability, professional liability / errors and omissions, cyber / data-breach, workers' compensation, auto)?
- Are coverage limits specified, and are they meaningful relative to the realistic exposure?

**Most exposed:** Client relying on the counterparty's indemnity or damages obligations as a real source of recovery.

---

### 14.2 Insurance mechanics missing (additional insured, certificates, notice)

**Pattern:** The contract requires coverage but omits the operational mechanics: no additional-insured status for the client, no certificate-of-insurance delivery requirement, no advance notice of cancellation or material reduction, no primary-and-noncontributory language.

**Why it matters:** A bare requirement to "carry insurance" without these mechanics gives the client no visibility into whether coverage exists and no direct rights against the policy.

**What to check:**
- Is the client named (or required to be named) as an additional insured where appropriate?
- Must the counterparty deliver certificates of insurance, including on renewal?
- Is there a notice obligation if coverage lapses, is cancelled, or is materially reduced?

**Most exposed:** Client that would need to claim against the counterparty's policy.

---

### 14.3 Insurance offered as a substitute for liability allocation

**Pattern:** The counterparty points to its insurance to justify a low liability cap or broad limitation, but the insurance requirement and the liability cap are not aligned — the cap is below the coverage limit, or the policies exclude the very risks the indemnity covers.

**Why it matters:** Insurance and contractual liability allocation are separate. A policy the client cannot reach, or that excludes the relevant risk, does not cure a deficient liability clause.

**What to check:**
- Does the liability cap align with the insurance limits, or is the cap far lower?
- Do the required policies actually cover the indemnified risks?
- Is the insurance a real backstop, or a negotiating talking point?

**Most exposed:** Client persuaded to accept a low cap on the strength of insurance that may not respond.

---

## 15. Audit and Inspection Rights

### 15.1 No audit right where verification matters

**Pattern:** The client has obligations it needs to confirm the counterparty is meeting — security controls, data handling, regulatory compliance, royalty or usage-based fee calculations — but the contract gives the client no right to audit, inspect, or obtain compliance evidence.

**Why it matters:** Without an audit or reporting right, the client must take the counterparty's compliance on trust and may be unable to detect a breach until it causes harm.

**What to check:**
- Does the client have any audit, inspection, or reporting right?
- For security and data obligations, is there a right to obtain third-party audit reports or certifications in place of, or alongside, a direct audit?
- Are there obligations whose breach the client could not otherwise detect?

**Most exposed:** Client with regulatory exposure, usage-based pricing, or sensitive-data obligations flowing to the counterparty.

---

### 15.2 One-sided audit right running against the client

**Pattern:** The counterparty has a broad right to audit the client's use of a product or service (a license "true-up" audit), often including entry to premises, inspection of systems, and back-charges for any underpayment — with no reciprocal right and few limits.

**Why it matters:** A broad vendor audit right can be used to generate surprise back-charges, disrupt operations, and create leverage at renewal.

**What to check:**
- What triggers the audit right, and how often can it be exercised?
- Is there advance-notice, business-hours, scope, and confidentiality protection?
- Who bears audit costs, and what are the consequences of an adverse finding?

**Most exposed:** Licensee or customer subject to usage-based or seat-based licensing.

---

### 15.3 Audit right with no procedural limits

**Pattern:** An audit right (in either direction) is granted with no limits on notice, frequency, scope, duration, location, who conducts it, the confidentiality of what is reviewed, or who pays.

**Why it matters:** An unbounded audit right is disruptive and can expose the audited party's sensitive information. Procedural limits are what make an audit right workable.

**What to check:**
- Notice period, frequency cap, scope limitation, and business-hours restriction.
- Confidentiality protection for information reviewed during the audit.
- Cost allocation, including any shifting rule if the audit finds a material discrepancy.

**Most exposed:** Whichever party is subject to the audit.

---

## 16. Publicity, Marketing, and Use of Name

### 16.1 Counterparty may use the client's name, marks, or a case study without consent

**Pattern:** The counterparty is permitted to use the client's name, logo, or trademarks, to identify the client as a customer, or to publish a case study or testimonial — without the client's prior written consent for each use.

**Why it matters:** Unconsented use of the client's name and marks can create unwanted public association, implied endorsement, brand-control problems, and trademark-licensing issues.

**What to check:**
- Does the counterparty need the client's prior written consent for each public use?
- Is any permitted use narrowly limited (e.g., to a customer list) and revocable?
- Is the right mutual, and does it survive termination?

**Most exposed:** Client sensitive about brand, public association, or confidentiality of the relationship.

---

### 16.2 No mutual control over public statements about the relationship

**Pattern:** The contract is silent on press releases and public announcements, or allows one party to announce the deal unilaterally.

**Why it matters:** A unilateral announcement can disclose a relationship the client wanted kept confidential, or mischaracterize it.

**What to check:**
- Is there a mutual prior-approval requirement for press releases and public statements?
- Are disclosures required by law or stock-exchange rule carved out?

**Most exposed:** Client with confidentiality, competitive, or regulatory sensitivity about the relationship.

---

## 17. Non-Solicitation and Non-Competition

This section expands on Section 11.5, which flags restrictive covenants embedded in routine commercial agreements. Enforceability of restrictive covenants is highly jurisdiction-dependent and, in some jurisdictions, restricted or prohibited `[verify jurisdiction]`.

### 17.1 Non-compete restricting the client's ordinary business

**Pattern:** The client is restricted from competing with the counterparty, from working with the counterparty's competitors, or from offering certain products or services — in a way that reaches the client's ordinary business activity.

**Why it matters:** A non-compete can constrain the client's core operations, future deals, and strategic flexibility, often far beyond the value of the contract.

**What to check:**
- What activity is restricted, for how long, and in what geography or market?
- Does the restriction reach beyond the subject matter of this contract?
- Is the restriction mutual, and is it enforceable in the governing jurisdiction `[verify jurisdiction]`?

**Most exposed:** Client whose business overlaps with the counterparty's market.

---

### 17.2 Overbroad non-solicitation of employees

**Pattern:** A non-solicit of employees has no carve-out for general advertising, job postings, or unsolicited inbound applications, and/or covers all employees rather than those connected to the engagement.

**Why it matters:** An overbroad non-solicit can be triggered by ordinary recruiting and restrict the client's hiring well beyond the people connected to the deal.

**What to check:**
- Is there a carve-out for general solicitations not targeted at the counterparty's staff, and for unsolicited applicants?
- Is the covered population limited to employees connected to the engagement?
- What is the duration, and does it run from termination?

**Most exposed:** Client that recruits in the same talent market as the counterparty.

---

### 17.3 Customer non-solicitation or exclusivity embedded in the deal

**Pattern:** The agreement restricts the client from soliciting, serving, or contracting with certain customers or categories of customers, or grants the counterparty exclusivity.

**Why it matters:** Customer non-solicits and exclusivity provisions can foreclose revenue opportunities and lock the client out of markets.

**What to check:**
- What customers or segments are covered, and for how long?
- Is exclusivity reciprocal, and is it tied to minimum commitments?
- Flag the provision prominently regardless of where it appears.

**Most exposed:** Client whose growth depends on access to the restricted customers or markets.

---

## 18. Governing Law and Choice of Forum

See also Section 8 (Dispute Resolution) for arbitration-specific patterns.

### 18.1 Governing law or forum with no connection to the parties or transaction

**Pattern:** The agreement selects a governing law or an exclusive forum that has no relationship to either party, the place of performance, or the subject matter.

**Why it matters:** An unrelated governing law can introduce unfamiliar legal rules; an unrelated or distant forum raises the cost and burden of any dispute and can deter the client from enforcing its rights. A choice with no reasonable connection may also face enforceability questions `[verify jurisdiction]`.

**What to check:**
- What law governs, and what is the exclusive forum or venue?
- Is there a reasonable connection between the chosen law or forum and the deal?
- Is the forum the counterparty's home turf and inconvenient for the client?

**Most exposed:** Client distant from the chosen forum, or a smaller party with limited litigation resources.

---

### 18.2 Inconsistent or split governing-law, forum, and arbitration provisions

**Pattern:** Different provisions point in different directions — a governing-law clause naming one jurisdiction, a forum-selection clause naming another, an arbitration clause naming a third seat — or incorporated documents (online terms, exhibits) carry their own conflicting clauses.

**Why it matters:** Inconsistent dispute provisions create uncertainty about where and under what law a dispute would proceed, and can trigger expensive threshold litigation about the dispute clause itself.

**What to check:**
- Do the governing-law, forum-selection, and arbitration clauses align?
- Do incorporated or online terms contain their own, conflicting clauses?
- Is there a clear order-of-precedence rule?

**Most exposed:** Either party, if a dispute arises.

---

### 18.3 Jury-trial waiver

**Pattern:** The agreement waives the right to a jury trial for any dispute.

**Why it matters:** A jury-trial waiver changes who decides the facts in any litigation. Its enforceability and effect vary by jurisdiction `[verify jurisdiction]`.

**What to check:**
- Is a jury-trial waiver present, and is it mutual?
- Is it enforceable under the governing law `[verify jurisdiction]`?

**Most exposed:** Either party; the effect depends on the dispute and the jurisdiction.

---

## Reviewer Notes

- A red flag is a prompt to look closely and flag for attorney attention — not a conclusion that a clause is unenforceable or unacceptable.
- Whether a flagged clause is a problem depends on the client's role, leverage, business context, and risk tolerance — all of which are for the attorney to assess.
- This catalog is not exhaustive. Unusual or deal-specific provisions not listed here may still warrant a flag in the "Unusual or One-Sided Clauses" category of the risk matrix.
- See `skills/contracts/contract-risk-review/SKILL.md` for the full clause-by-clause review workflow.
- See `skills/contracts/nda-review/SKILL.md` for the NDA-specific scope check and risk table workflow.

=== END AGENTCOUNSEL MODULE: contract-red-flags ===

=== BEGIN AGENTCOUNSEL MODULE: negotiability-ratings ===
Kind: reference
Canonical path: skills/contracts/references/negotiability-ratings.md
Load when: standard or deep-review mode when negotiation prioritization is requested

> Shared reference material supporting the AgentCounsel contracts skills, used to help produce draft legal work product for attorney review — not legal advice.

# Negotiability Ratings Framework

This framework gives a reviewer a structured way to rate, for each material issue in a contract, how hard the client should push and what that posture means in practice. It is a reasoning tool — not a fixed list of which clauses are always negotiable and which are not. How negotiable a term is depends on factors that vary by deal, and the supervising attorney determines the final negotiating strategy.

All negotiability ratings are draft assessments for attorney review. The attorney confirms whether a rating is appropriate given the client's actual leverage, the counterparty's behavior, the client's risk tolerance, and strategic priorities.

---

## The Rating Scale

The framework uses six ratings. Each rating combines two judgments: how serious the issue is for the client, and how the lawyer should handle it in the negotiation. The ratings are recommendations to the attorney and the business — not conclusions.

The six ratings, in order:

1. **Must Push** — change it or escalate; do not sign over it.
2. **Strong Push** — negotiate hard; real exposure, movement likely.
3. **Business Call** — a commercial tradeoff for the business to decide.
4. **Acceptable if Balanced** — fine if made mutual or balanced.
5. **Low Priority** — minor; flag it, don't spend capital on it.
6. **Do Not Spend Leverage** — do not raise it.

Must Push, Strong Push, and Low Priority describe descending intensity. Business Call and Acceptable if Balanced describe a *type* of handling rather than a point on that intensity line — they tell the lawyer *how* to treat the issue, not just how hard to press. Do Not Spend Leverage is the floor: a deliberate decision not to raise the issue at all.

---

### Must Push

**Definition:** The term, as written, creates risk the client should not accept. It must change before signature — or the decision to proceed anyway must be made consciously by a senior decision-maker, not reached by default.

**When to use it:**
- The term hits a defined "never accept" line in the client's playbook or practice profile.
- The risk it creates is disproportionate to the value of the deal.
- The term may be unenforceable or may create regulatory exposure `[verify jurisdiction]`.
- The supervising attorney has confirmed the term cannot stand as drafted.

**What it implies for the lawyer:**
- Raise the issue as a requirement, not a preference.
- Do not let the contract move to signature with the term unresolved.
- If the counterparty will not move, escalate to a senior business decision-maker for a conscious accept-or-reject decision.
- Record the item in the Open Items section and the Attorney Verification Checklist.

**Communicating it to business stakeholders (sample language):**
> "This term has to change before we can sign. This is not a preference — as written, it exposes us to [describe the risk in concrete terms]. We will tell the counterparty it is a requirement. If they will not move, this needs a leadership decision about whether the deal is still worth doing on these terms."

---

### Strong Push

**Definition:** A material, one-sided term that creates real exposure. It is not a standalone deal-breaker, but the client should negotiate it hard and can realistically expect to improve it.

**When to use it:**
- The term allocates meaningful financial, operational, or legal risk against the client.
- Movement is realistically possible given the deal context and the client's leverage.
- The issue is material enough to justify spending negotiating capital.
- A clear preferred position and a defined fallback both exist.

**What it implies for the lawyer:**
- Raise it as a priority redline; lead with the preferred position.
- Press for the preferred position; accept the fallback only if the counterparty genuinely resists.
- Be prepared to trade for it against lower-rated items.
- Document the preferred and fallback positions in the issue list.

**Communicating it to business stakeholders (sample language):**
> "We should push hard on this one. It is a real imbalance and we have a good chance of improving it. Our opening ask is [preferred position]; if they push back, the least we should accept is [fallback]. Expect some back-and-forth — this is worth the effort."

---

### Business Call

**Definition:** The legal risk is real and has been explained, but whether to accept it is a commercial judgment that depends on business priorities — price, timing, the relationship, the available alternatives — not a pure legal question.

**When to use it:**
- The issue is a genuine tradeoff between legal risk and a business benefit.
- Legal can frame the risk and the options but does not own the decision.
- Reasonable decision-makers could go either way depending on the client's risk appetite.

**What it implies for the lawyer:**
- Present the risk and the realistic options neutrally — do not hide the recommendation, but make clear the decision belongs to the business.
- Give the business what it needs to decide: what the term means, what could go wrong, how likely it is, and what accepting or rejecting it costs.
- Record the business's decision and its rationale, so the basis for the call is documented.

**Communicating it to business stakeholders (sample language):**
> "Here is a tradeoff for you to decide. Legally, this term means [plain-language consequence]. The risk is [likelihood and impact]. Pushing back may cost us [time / goodwill / leverage elsewhere]. Whether it is worth accepting depends on how much you value [speed / price / this relationship]. We need you to make the call — and we will document it."

---

### Acceptable if Balanced

**Definition:** The concept of the term is fine; the problem is that it runs only one way. The term would be acceptable if it were made mutual, or paired with a corresponding protection.

**When to use it:**
- A one-sided clause whose substance is reasonable if it is reciprocal — for example, a one-way indemnity, audit right, termination right, or limitation that should cut both ways.
- The fix is symmetry or a balancing carve-out, not deletion or a fight over the substance of the clause.

**What it implies for the lawyer:**
- Ask for mutuality, or for the balancing protection, rather than challenging the clause itself — usually a low-friction request.
- If the counterparty makes the term balanced, treat the issue as resolved.
- If the counterparty refuses to balance it, re-rate the issue — often upward to Strong Push — and reassess.

**Communicating it to business stakeholders (sample language):**
> "We can live with this as long as it cuts both ways. Right now it only protects them. We will ask them to make it mutual — that is usually an easy fix. If they agree, no further concern. If they will not, we will come back to you, because a one-way version is a bigger problem."

---

### Low Priority

**Definition:** A minor imbalance or a suboptimal drafting point. Worth recording so the attorney and the client are aware of it, but not worth significant negotiating capital.

**When to use it:**
- The issue has limited practical or financial impact.
- The cost of raising it — time, goodwill, capital — is out of proportion to the gain.
- It may be worth raising only if it can be bundled cheaply, or in a high-value or high-stakes deal.

**What it implies for the lawyer:**
- Note it in the issue list at Low priority.
- Raise it only opportunistically — bundled with larger items, or if the counterparty is moving freely.
- Do not let it slow the deal or consume capital reserved for higher-rated items.

**Communicating it to business stakeholders (sample language):**
> "Minor point — we have flagged it for the record. It is not worth holding up the deal or spending leverage on. We may mention it if it is easy to fold into the larger discussion, but we will not fight for it."

---

### Do Not Spend Leverage

**Definition:** The term should not be raised. It is either genuinely balanced, or it reflects an entrenched counterparty position where the cost of asking — in capital or in signaling — outweighs any realistic gain.

**When to use it:**
- The term is balanced or unremarkable as a general drafting matter (characterize it, do not assert market data — see `skills/contracts/references/market-benchmark-framework.md`).
- The term sits in the counterparty's standard form and is one they consistently hold.
- Raising it would consume capital better spent on higher-rated issues, or would signal inexperience.

**What it implies for the lawyer:**
- Do not raise the issue in the negotiation.
- Preserve negotiating capital for Must Push and Strong Push items.
- Still record the term and the rating, so the decision not to raise it is deliberate and visible — "not raised" should be a choice, not an oversight.

**Communicating it to business stakeholders (sample language):**
> "We looked at this and recommend leaving it alone. It is either standard or something they will not move on, and raising it would burn goodwill we need for the issues that matter. We are flagging it so you know it was a deliberate call, not an oversight."

---

## Factors That Drive the Rating

A rating is not assigned mechanically. The reviewer considers each of the following factors and how they interact.

### 1. Relative Leverage

Which party needs this deal more? Which party has viable alternatives? The party with more alternatives has more leverage to push on hard terms. A client who is one of many customers of a large platform vendor has less leverage than a client representing a significant share of the counterparty's revenue. Leverage is deal-specific — the reviewer notes the apparent leverage position and flags it for attorney confirmation.

### 2. Who Drafted the Form

A term appearing in the reviewing party's own form can often be adjusted without counterparty resistance. A term appearing in the counterparty's standard form signals an entrenched position and raises the cost of negotiation. The form's origin pushes the rating toward Do Not Spend Leverage (entrenched form term) or away from it (the client's own form).

### 3. Deal Value and Strategic Importance

High-value or strategically important deals warrant spending more negotiating capital. A term that would be rated Low Priority on a routine small transaction may warrant a Strong Push on a large or strategic deal, where the client's leverage and incentive to spend effort are both higher.

### 4. Market Norms and Standard Practice

Whether a term deviates from what is typical for this contract type, transaction size, and industry affects whether the counterparty will engage. A genuine deviation from market norms is a more credible basis for a push than a request to improve an already-balanced term. Market-norm assessments must be verified — see `skills/contracts/references/market-benchmark-framework.md`.

### 5. Regulatory Floor

Some terms cannot be negotiated below a regulatory minimum: required data-processing provisions, mandatory breach-notification timelines, required disclosures. A term that hits a regulatory floor is not negotiable below that floor regardless of leverage or deal value `[verify jurisdiction]`. The reviewer notes when a floor may apply and flags it for attorney verification.

### 6. Insurance and Underwriting Constraints

Liability caps, indemnification limits, and some insurance-requirement terms may be constrained by the counterparty's insurance underwriting. If the counterparty's insurer requires a particular liability allocation, the counterparty may have limited ability to move even if it is willing. The reviewer notes this factor when it is apparent from the contract structure.

### 7. The Client's Own Position

If the client has a playbook or practice profile with defined preferred, acceptable, and unacceptable positions, the rating is calibrated against those positions. A term that falls within the client's acceptable range affects priority. A term that hits a "never accept" threshold is Must Push regardless of other factors.

### 8. Pattern and History

If the client has prior contracts with the same counterparty, or the attorney has experience with this counterparty's negotiation posture, that history informs the rating. A counterparty that has moved on a term before is more likely to move again.

---

## How to Apply the Framework

1. **Identify the issue** being rated and note its current posture in the draft (client-favorable, neutral, counterparty-favorable, or missing).

2. **Work through the factors** above. Not all factors are relevant to every issue. Note which factors are present and how they push the rating.

3. **Assign one of the six ratings.** Where factors point in different directions, flag the tension and note which factors are driving the rating.

4. **Record the basis.** The rating is only as useful as its explanation. A bare rating without reasoning is not actionable.

5. **Note confidence level.** If key factors are unknown — for example, the client's leverage has not been confirmed — note the uncertainty. A rating based on incomplete information should be flagged: `[CONFIRM: leverage position before finalizing rating]`.

6. **Flag for attorney review.** All negotiability ratings are draft assessments. The attorney confirms strategy, adjusts for factors the reviewer cannot observe, and decides which issues to raise and in what order.

---

## Recording a Rating

When recording a negotiability rating in an issue list, a negotiability table, or a risk matrix, use the following pattern:

```
Issue:               [clause name or topic]
Current posture:     [counterparty-favorable / neutral / missing]
Negotiability:       [Must Push / Strong Push / Business Call /
                      Acceptable if Balanced / Low Priority /
                      Do Not Spend Leverage]
Basis:               [one to two sentences identifying the key factors]
Preferred position:  [what the client wants]
Fallback position:   [what the client would accept]
Attorney note:       [CONFIRM: ...] or [ATTORNEY TO CONFIRM: ...]
```

See `skills/contracts/references/redline-output-guidance.md` for guidance on expressing preferred and fallback positions, and `skills/contracts/references/fallback-language-bank.md` for sample fallback positions by clause type.

---

## Negotiability Rating and Issue Priority

The negotiability rating answers a different question from the issue's **priority** rating (High / Medium / Low), which the contract skills use in the risk matrix and issue list to reflect the *materiality* of the risk.

- **Priority** measures how much the issue matters — the size of the risk to the client.
- **Negotiability** measures how the lawyer should handle the issue — how hard to push, and in what manner.

The two interact, and the negotiability rating already absorbs much of the priority judgment:

- A **Must Push** issue is, by definition, High priority — and the negotiability rating tells the attorney that movement is required, not merely desirable.
- A **Strong Push** issue is typically High or Medium priority, with realistic prospects of movement.
- A **Business Call** can sit at any priority level; the rating signals that the *decision*, not the priority, is the open question.
- **Low Priority** and **Do Not Spend Leverage** both signal the issue is not worth significant capital — Low Priority leaves the door open to raise it opportunistically, while Do Not Spend Leverage recommends not raising it at all.

Record both the priority rating and the negotiability rating for each material issue. Together they tell the attorney what matters and what to do about it. See `skills/contracts/contract-risk-review/SKILL.md` for the priority rating definitions used in the issue list.

=== END AGENTCOUNSEL MODULE: negotiability-ratings ===

=== BEGIN AGENTCOUNSEL MODULE: market-benchmark-framework ===
Kind: reference
Canonical path: skills/contracts/references/market-benchmark-framework.md
Load when: deep-review mode or when market practice is requested

> Shared reference material supporting the AgentCounsel contracts skills, used to help produce draft legal work product for attorney review — not legal advice.

# Market Benchmark Framework

This framework gives a reviewer a disciplined method for recording how a contract term compares to market norms, citing the basis for any benchmark observation, and flagging every unverified benchmark for attorney confirmation.

**AgentCounsel does not supply market data.** This library contains no percentages, no assertions of what terms are "typically" offered, and no claims about what the market "standard" is for any clause. Every benchmark observation in a deliverable must come from a source the attorney can verify — and every such observation is an attorney-verification item until confirmed.

An unverified benchmark is more dangerous than no benchmark. A fabricated or unconfirmed market-data assertion can lead an attorney or client to make a negotiating decision on a false premise. This framework exists to ensure that any benchmark used in a review is clearly sourced, clearly qualified, and clearly flagged for confirmation.

---

## Why Market Benchmarks Are Attorney-Verification Items

Market norms for contract terms vary by:

- **Industry and sector** — what is typical in technology services differs from what is typical in construction, financial services, or life sciences.
- **Transaction type** — MSA terms differ from SaaS subscription terms, which differ from one-time professional services engagements.
- **Transaction size and deal value** — large-enterprise terms differ from mid-market or SMB terms.
- **Geography and governing law** — norms differ across jurisdictions `[verify jurisdiction]`.
- **Time** — what was standard practice several years ago may not reflect current market expectations.
- **Counterparty type** — terms offered by a large platform vendor differ from those offered by a boutique professional services firm.
- **Relative leverage** — "market standard" often means "what the party with more leverage typically gets."

An agent cannot verify any of these variables from a contract document alone. Only the attorney, drawing on active practice experience and current knowledge of the relevant market segment, can assess whether a benchmark observation is accurate for the specific deal.

---

## Permitted Sources for Benchmark Observations

A benchmark observation may only be recorded if it can be attributed to one of the following:

### Source 1: The Client's Practice Profile or Playbook

The client's own standard positions, as provided by the attorney or reflected in the client's supplied template, playbook, or prior agreements. Observations from this source describe what the client's standard is — not what "the market" is. Record as: _"Client's playbook [specify source] provides for [term]. The reviewed contract departs from client's standard in the following way: [description]."_

### Source 2: Attorney-Provided Comparables

Comparable contract terms specifically identified by the supervising attorney or the client as representative of market practice for this type of deal. Record as: _"Attorney-provided comparable [specify, e.g., 'prior agreement with similar vendor supplied by client'] contains [term]. The reviewed contract [matches / departs from] this comparable in the following way: [description]."_

### Source 3: The Counterparty's Own Prior Forms

Where the client has a prior contract with the same counterparty, or has obtained a prior version of the counterparty's standard form, terms from that prior form are a benchmark for what the counterparty has historically offered. Record as: _"Counterparty's prior form [specify source] contained [term]. The reviewed contract [matches / departs from / is more restrictive than] the counterparty's prior form in the following way: [description]."_

### Source 4: Industry Norms Supplied by the Attorney

The attorney identifies specific industry norms applicable to this deal, drawing on active practice knowledge for this sector, transaction type, and deal size. The attorney must supply the norm — the agent records and flags it. Record as: _"Attorney-supplied industry norm for [sector / transaction type]: [description of norm]. Flagged for attorney confirmation."_

---

## Prohibited Assertions

The following assertions must never appear in a deliverable produced using this framework:

- "Market standard is [X]."
- "It is typical for [clause] to be [Y]."
- "[X]% of contracts in this sector include [term]."
- "Most vendors accept [Y] on [term]."
- "Industry practice requires [Z]."
- Any percentage, frequency, or statistical claim about market practice.
- Any assertion about what a counterparty "usually" offers or "would normally" accept.

If a benchmark observation cannot be sourced to one of the four permitted sources above, it must not appear in the deliverable. Record an open item instead: `[ATTORNEY TO CONFIRM: market norm for [clause/term] in [transaction type] — no verified benchmark available]`.

---

## A Controlled Vocabulary for Characterizing Terms

A reviewer often needs to give the attorney a sense of *how a term reads* without asserting market data the reviewer cannot supply. The five characterizations below are the permitted way to do that. They replace prohibited statements like "market standard is X" with a qualitative, clearly-labeled impression.

**These five labels are general drafting heuristics.** They reflect a reviewer's qualitative impression of how a clause is constructed — not a measured or verified market position. They become reliable benchmarks **only** when supported by one of the four permitted sources above: a provided client playbook, attorney-provided comparables, the counterparty's prior form, or an attorney-supplied industry norm. Used on their own, every one of these characterizations is an attorney-verification item.

Use exactly one of these labels for any term the reviewer characterizes:

### Common

The clause follows a familiar, frequently-seen drafting pattern for this contract type. "Common" is **not** a claim that the term is "market standard," nor that any particular share of contracts use it. It means only this: the construction is unremarkable, and a reviewer would not be surprised to encounter it. A Common term may still carry real risk for the client — see "Benchmark Observations vs. Risk Ratings" below.

### Aggressive

The clause follows a recognizable pattern but is drafted notably toward one party — typically the drafting party. It is a familiar construction sitting at the one-sided end of the range. Always state which party it favors.

### Unusual

The clause departs from familiar drafting patterns. The reviewer has not commonly seen this construction, or it combines terms in an unexpected way. "Unusual" is a prompt for close attention and explanation — it does not by itself mean the term is unacceptable, but it warrants attorney scrutiny.

### Depends on Leverage

Whether the term reads as ordinary or as one-sided genuinely turns on the parties' relative bargaining power and cannot be characterized without knowing it. Many liability, indemnity, exclusivity, and pricing terms fall here. Record what is known about leverage and flag the gap.

### Needs Attorney Confirmation

The reviewer cannot characterize the term against any reference point — there is no playbook position, no comparable, no counterparty prior form, and the reviewer has no basis to call the term Common, Aggressive, or Unusual. The attorney must supply the market read. This is the correct default whenever the reviewer is uncertain; do not guess at one of the other four labels to avoid using this one.

### Recording a characterization

```
Clause / Term:        [name of the clause or issue]
Characterization:     [Common / Aggressive / Unusual /
                       Depends on Leverage / Needs Attorney Confirmation]
Basis:                [why the reviewer chose this label]
Supporting source:    [client playbook / attorney comparable /
                       counterparty prior form / attorney-supplied norm /
                       NONE — drafting heuristic only]
Verification status:  [UNVERIFIED — attorney confirmation required]
                      OR [CONFIRMED by: (attorney / playbook / comparables)]
```

When the supporting source is NONE, the characterization is a drafting heuristic only and must be flagged: `[ATTORNEY TO CONFIRM: characterization of [term] as "[label]" is a drafting heuristic, not verified market data — confirm against current market practice for [transaction type / sector / deal size]]`.

These characterizations are the vocabulary used in the **Market Practice Notes** output section of the contracts skills.

---

## How to Record a Benchmark Observation

Every benchmark observation in a deliverable must follow this structure:

```
Benchmark Observation
Clause / Term:        [name of the clause or issue]
Observed term:        [what the reviewed contract says, quoted or precisely described]
Benchmark source:     [one of the four permitted sources; identify the specific source]
Benchmark position:   [what the benchmark source says about this term]
Deviation:            [how the reviewed contract departs from the benchmark, if at all]
Verification status:  [UNVERIFIED — attorney confirmation required]
                      OR [CONFIRMED by: (attorney / playbook / comparables)]
```

All benchmark observations are marked UNVERIFIED until the supervising attorney confirms them.

---

## Flagging Unverified Benchmarks

Every unverified benchmark in a deliverable must be flagged as an open item. Use the following placeholder form:

`[ATTORNEY TO CONFIRM: benchmark for [clause] — basis is [source]; confirm whether this reflects current market practice for [transaction type / sector / deal size]]`

Do not omit the source basis in the placeholder. A bare `[verify]` tag is not sufficient; the attorney needs to know what assertion is being flagged and what the claimed source is.

---

## Benchmark Observations vs. Risk Ratings

A benchmark observation describes how a term compares to a reference point. A risk rating (High / Medium / Low in the risk matrix) describes the risk to the client. These are distinct assessments:

- A term can depart significantly from a benchmark but pose low risk to the client (e.g., a client-favorable deviation).
- A term can be consistent with a benchmark but still pose meaningful risk to the client (e.g., a term that is "typical" but still creates genuine exposure).

Do not conflate "consistent with market" with "acceptable risk." The risk assessment belongs to the attorney. The benchmark observation is one input to that assessment.

---

## Benchmark Observations in the Risk Matrix

When recording a benchmark observation in the risk matrix (see `skills/contracts/contract-risk-review/templates/contract-risk-matrix.md`), the Attorney Note column is the appropriate place to record the observation and its verification status. Example:

> Attorney Note: _Liability cap formula departs from client playbook standard (12-month fees; playbook calls for 24-month minimum). No external market benchmark available. `[ATTORNEY TO CONFIRM: whether 12-month cap is acceptable for this transaction type and deal value]`_

---

## A Note on "Market Standard" Claims in the Contract Itself

Counterparties sometimes include language in their agreements asserting that a term is "market standard," "industry standard," or "customary." These assertions are counterparty representations — they are not independently verified benchmarks. When such language appears in a reviewed contract, note it as a counterparty claim and flag it for attorney verification: `[ATTORNEY TO CONFIRM: counterparty's "market standard" assertion for [term] — independent verification required]`.

=== END AGENTCOUNSEL MODULE: market-benchmark-framework ===

=== BEGIN AGENTCOUNSEL MODULE: contracts-practice-profile ===
Kind: profile
Canonical path: practice-profiles/contracts.md
Load when: a populated and attorney-approved contracts profile is available

> **Internal practice-group configuration reference. This is not legal work product and is not legal advice.** This profile configures AI agent behavior for this practice group. It must be maintained and approved by a supervising attorney before use. This file must NOT contain privileged or client-sensitive facts. Source-of-truth documents are referenced by name and location only — never pasted in.

# Practice Profile: Contracts

## Profile Information

| Field | Value |
|---|---|
| Practice Group | Contracts |
| Profile Owner | `[CONFIRM: name and title of profile owner]` |
| Approving Attorney | `[CONFIRM: name and bar number of approving attorney]` |
| Last Reviewed Date | `[CONFIRM: date of last attorney review]` |
| Version | `[CONFIRM: version number, e.g., 1.0]` |

---

## Jurisdictions

Identify every jurisdiction, governing-law regime, and forum in which this group regularly works. Agents will gate jurisdiction-specific analysis on this list and flag anything outside it for attorney escalation.

| Field | Value |
|---|---|
| Primary Jurisdictions | `[CONFIRM: e.g., state/province, country]` |
| Secondary / Occasional Jurisdictions | `[CONFIRM: list or "none at this time"]` |
| Default Governing Law | `[CONFIRM: preferred governing-law clause, or "counterparty-dependent"]` |
| Preferred Dispute-Resolution Forum | `[CONFIRM: e.g., courts of a specified jurisdiction, arbitration body]` |
| International / Cross-Border Work | `[CONFIRM: yes/no; if yes, list regimes and any export-control considerations]` |

**Guiding prompts for this section:**
- What governing-law clause does the group prefer to propose as a starting position?
- In which jurisdictions does the group regularly enforce or defend contractual claims?
- Are there forum-selection clauses the group treats as standard or as automatic deal points?
- Does the group work on agreements subject to cross-border transfer restrictions or international arbitration rules?

---

## Client / Team Context

Describe who this group serves and how it is organized. Agents use this section to understand escalation paths and supervision structure.

| Field | Value |
|---|---|
| Internal Clients Served | `[CONFIRM: e.g., business units, product teams, procurement]` |
| External Client Types | `[CONFIRM: e.g., enterprise SaaS vendors, Fortune 500 buyers, startups]` |
| Team Composition | `[CONFIRM: partners, senior associates, associates, paralegals, contract managers]` |
| Supervising Attorney(s) | `[CONFIRM: name(s) with oversight responsibility for AI-assisted work]` |
| Matter-Intake Process | `[CONFIRM: how matters reach the group — ticketing system, direct request, etc.]` |

**Guiding prompts for this section:**
- Who is the primary internal or external client this group supports?
- Who is the designated supervising attorney for AI-assisted contract review or drafting?
- Does the group use a contract management system, intake form, or matter-management platform?

---

## Escalation Thresholds

Define the conditions under which an agent must stop autonomous work and route to a human reviewer. Agents treat these thresholds as hard stops.

| Trigger | Threshold / Description | Route To |
|---|---|---|
| Contract value | `[CONFIRM: e.g., above $[X], escalate to partner]` | `[CONFIRM: role or name]` |
| Liability cap below floor | `[CONFIRM: e.g., cap less than [X] months' fees or $[X] total]` | `[CONFIRM: role or name]` |
| Uncapped liability clause | `[CONFIRM: escalate any agreement with no liability cap]` | `[CONFIRM: role or name]` |
| Auto-renewal clause present | `[CONFIRM: flag for attorney review or client instruction]` | `[CONFIRM: role or name]` |
| IP assignment affecting core assets | `[CONFIRM: any assignment of patents, trademarks, or platform IP]` | `[CONFIRM: role or name]` |
| Indemnification — one-sided or uncapped | `[CONFIRM: escalation criteria]` | `[CONFIRM: role or name]` |
| Counterparty is a government entity | `[CONFIRM: always escalate / apply special review]` | `[CONFIRM: role or name]` |
| Non-standard dispute resolution | `[CONFIRM: e.g., mandatory arbitration in unfamiliar forum]` | `[CONFIRM: role or name]` |
| Any clause outside known playbook | `[CONFIRM: agent flags and pauses rather than improvising]` | `[CONFIRM: role or name]` |

**Guiding prompts for this section:**
- At what dollar value does a contract require partner or senior-attorney sign-off?
- Does the group have a minimum acceptable liability cap expressed as a dollar figure or a multiple of fees?
- Are auto-renewal clauses a standing concern requiring client notification before they trigger?
- What indemnification structures are outside the group's standard playbook and require escalation?

---

## Preferred Output Style

Specify the format, tone, and length conventions agents must follow when producing deliverables for this group.

| Preference | Setting |
|---|---|
| Deliverable format | `[CONFIRM: e.g., tabular risk matrix, memo, redline markup, clause-by-clause summary]` |
| Tone | `[CONFIRM: e.g., plain business language, formal legal prose]` |
| Length convention | `[CONFIRM: e.g., executive summary ≤ 1 page + full matrix; no single-section limit]` |
| Heading style | `[CONFIRM: e.g., numbered sections, H2/H3 Markdown]` |
| Risk-rating scheme | `[CONFIRM: e.g., High / Medium / Low aligned with contract-risk-matrix template]` |
| Redline conventions | `[CONFIRM: e.g., track-changes Word, Markdown strikethrough/insertion, inline annotations]` |
| Privilege designation line | `[CONFIRM: e.g., "Privileged and Confidential — Attorney Work Product"]` |

**Guiding prompts for this section:**
- Do clients expect a one-page executive summary or a full clause-by-clause walkthrough?
- Does the group use a standard risk-rating scheme that agents should align with?
- How should agents present redline suggestions — narrative, table, or markup?

---

## Source-of-Truth Documents

List the authoritative playbooks, templates, clause libraries, and reference materials this group uses. Reference by name and location only. Do not paste content here.

| Document | Location / Path | Notes |
|---|---|---|
| Standard contract-review playbook | `[CONFIRM: file name and location, e.g., internal drive path or system name]` | `[CONFIRM: version or last-updated date]` |
| Approved clause library | `[CONFIRM: file name and location]` | `[CONFIRM: version or last-updated date]` |
| NDA template (inbound) | `[CONFIRM: file name and location]` | |
| NDA template (outbound) | `[CONFIRM: file name and location]` | |
| MSA template | `[CONFIRM: file name and location]` | |
| SaaS / subscription agreement template | `[CONFIRM: file name and location]` | |
| Signature authority / approval matrix | `[CONFIRM: file name and location]` | |
| Contract risk matrix template | `skills/contracts/contract-risk-review/templates/contract-risk-matrix.md` | Canonical AgentCounsel template |

**Guiding prompts for this section:**
- Where does the group store its approved templates and clause fallbacks?
- Is there a playbook document that defines the group's standard positions for common clauses?
- What contract management system holds executed agreements?

---

## Standard Positions / Playbooks

Record the group's default negotiating positions for key contract terms. These are starting positions — an agent uses them to flag deviations but always defers final judgment to an attorney.

| Clause | Group's Default Position | Notes / Conditions |
|---|---|---|
| Governing law | `[CONFIRM: preferred jurisdiction]` | `[CONFIRM: when to accept counterparty's law]` |
| Limitation of liability — cap amount | `[CONFIRM: e.g., greater of total fees paid or $[X]]` | `[CONFIRM: when a lower cap is acceptable]` |
| Limitation of liability — consequential damages | `[CONFIRM: e.g., mutual exclusion with named carve-outs]` | `[CONFIRM: required carve-outs, e.g., IP indemnity, fraud, data breach]` |
| Indemnification — IP infringement | `[CONFIRM: e.g., mutual; each party indemnifies for its own IP]` | |
| Indemnification — data breach | `[CONFIRM: group's standard position]` | |
| Auto-renewal | `[CONFIRM: e.g., oppose; require affirmative renewal or minimum notice window]` | `[CONFIRM: minimum acceptable notice period]` |
| Term / initial contract duration | `[CONFIRM: preferred initial term length]` | |
| Termination for convenience | `[CONFIRM: e.g., require mutual right; minimum notice period]` | |
| Assignment / change of control | `[CONFIRM: e.g., require consent for assignment; termination right on change of control]` | |
| Confidentiality duration | `[CONFIRM: minimum post-termination confidentiality period]` | |
| Dispute resolution | `[CONFIRM: preferred mechanism — litigation, arbitration, mediation first]` | |

**Guiding prompts for this section:**
- What is the group's floor for a liability cap as a multiple of fees or an absolute dollar amount?
- Which carve-outs from the consequential-damages exclusion does the group always seek?
- Does the group have a standing position on auto-renewal notice windows?
- What governing-law clauses does the group accept from counterparties without escalation?

---

## Attorney Review Requirements

Specify what must be reviewed by a qualified attorney before any deliverable produced with this profile is used, sent, or relied upon.

| Deliverable Type | Required Reviewer | Conditions |
|---|---|---|
| Contract risk matrix or review memo | `[CONFIRM: e.g., supervising associate or partner]` | All; no exceptions |
| Redline or draft contract | `[CONFIRM: role]` | All; no exceptions |
| Clause library addition or update | `[CONFIRM: role]` | Requires written approval |
| Playbook update | `[CONFIRM: role]` | Requires written approval and version increment |
| Executed-agreement summary | `[CONFIRM: role]` | `[CONFIRM: before distribution to business?]` |
| Any output touching an uncapped liability or IP assignment | Partner-level review | Always |

**Guiding prompts for this section:**
- Is there a tiered review structure (associate drafts, partner approves) for different contract values?
- Which deliverables can be reviewed by a senior associate without partner sign-off?
- Does the group require countersignature by a second attorney for agreements above a certain value?

---

## Prohibited Assumptions

List what an agent must never assume and must always confirm with a human before proceeding.

| Item | Why It Cannot Be Assumed |
|---|---|
| Governing law is the group's preferred jurisdiction | Counterparty's form may specify a different law; must be confirmed |
| Liability cap meets the group's floor | Cap amount and basis must be read from the actual agreement |
| Auto-renewal clause is absent | Must be confirmed by reading every agreement; do not assume it is absent |
| Indemnification is mutual | One-sided indemnification is common; must be confirmed |
| Prior version of an agreement reflects current terms | Only the version provided for review controls |
| A standard-form agreement is unchanged from the template | Counterparties modify forms; read the actual document |
| Client entity name and authorized signatory are correct | Must be confirmed against authoritative records |
| Signature authority has been obtained | Approval matrix must be consulted for each agreement |
| `[CONFIRM: any additional group-specific prohibited assumption]` | `[CONFIRM: reason]` |

---

## How to Populate This Profile

Complete every bracketed placeholder with information specific to this practice group. Have a supervising attorney review and approve the completed profile before it is loaded alongside any skill.

For a guided, question-by-question setup process, use the cold-start interview skill at `skills/setup/contracts-cold-start-interview/SKILL.md`. That skill walks through each section of this profile and produces a draft-completed version for attorney review.

Do not include client names, matter numbers, confidential facts, or privileged analysis in this profile. This is a configuration document, not a work-product file.

=== END AGENTCOUNSEL MODULE: contracts-practice-profile ===

You are assisting with a legal task using AgentCounsel, a platform-agnostic legal skills library. Use the skill package provided below and follow it exactly.

Operating rules (these always apply):
- Produce draft legal work product for review by a licensed attorney. This is not legal advice and not a final answer.
- Never invent legal authority, citations, quotations, facts, or deadlines. Mark every gap with a visible placeholder such as [CONFIRM: ...] or [VERIFY: ...].
- Identify jurisdiction, governing law, posture, and the relevant date — or flag them as unknown. Never compute a deadline.
- Keep facts, assumptions, analysis, strategy, and verification items visibly separate.
- Follow the skill's Workflow and Output Format. Complete its Attorney Verification Checklist.
- If a Required Input is missing, stop and ask for it. Do not guess.
- This skill has a typed execution contract. Choose a declared mode, evaluate every module activation exactly, and treat missing activation inputs as unresolved rather than loading all modules.

=== BEGIN AGENTCOUNSEL EXECUTION PACKAGE: NDA Review ===
AgentCounsel selective execution package for NDA Review.

The core skill always applies. Choose one declared execution mode and evaluate each module's machine-readable activation object exactly. Missing activation inputs fail closed: do not load every conditional module. A module without activation is not selected unless it is required or explicitly requested. Use only the selected resources, preserve why each resource was selected, and keep every parent safety rule active.

This portable package contains every possible resource. For true prompt-size reduction, use the MCP get_skill_context tool or another client that sends only the selected bundle.

=== BEGIN AGENTCOUNSEL CORE SKILL ===
---
name: NDA Review
description: "Use when reviewing a non-disclosure or confidentiality agreement to produce a triage rating (route, flag, or stop), a structured risk summary, and prioritized redline points for attorney review."
practice_area: contracts
task_type: review
jurisdictions: []
risk_level: medium
requires_attorney_review: true
inputs:
  - "The full NDA or confidentiality agreement text"
  - "The client's role: disclosing, receiving, or mutual"
  - "The business and transaction context"
  - "Optional: the client's standard NDA positions or playbook"
outputs:
  - "Triage rating (route, flag, or stop)"
  - "Structured risk summary"
  - "Prioritized redline points for attorney review"
related_skills:
  - skills/contracts/contract-risk-review/SKILL.md
  - skills/contracts/redline-summary/SKILL.md
tags:
  - contracts
  - nda
  - confidentiality
  - contract-review
  - risk-triage
---

# NDA Review

## Purpose

Produce a structured, attorney-ready review of a non-disclosure agreement (NDA) or confidentiality agreement. The skill identifies key terms, flags risk-allocation issues, assigns an overall triage rating, and proposes prioritized redline points. It produces draft legal work product for attorney review — not legal advice and not a final negotiating position.

## Use When

- A user asks to "review this NDA," "check this confidentiality agreement," or "tell me what's risky here."
- A counterparty has sent an NDA and the user needs a first-pass risk read.
- The user wants a route / flag / stop call on whether an NDA can move toward signature.
- The user wants a redline priority list before negotiation.
- The user wants a plain-language summary of an NDA's obligations.

## Required Inputs

- The full NDA text (uploaded or pasted). Do not review from a description alone.
- The client's role: disclosing party, receiving party, or mutual.
- The business context: what is being shared and why.
- The transaction context: whether this is a stand-alone commercial NDA, or part of an M&A, employment, or investment deal.
- Optional but recommended: the client's standard NDA positions or playbook — acceptable terms, "never accept" terms, mutuality default, required carve-outs, term and survival caps, and governing-law preferences. The review benchmarks against these where they are provided.
- Optional: the practice group's `practice-profiles/contracts.md` if it has been populated and is loaded alongside this skill. If present, the skill uses its Standard Positions and Escalation Thresholds tables to benchmark the output and to gate escalation. If absent, the skill proceeds without practice-profile benchmarking and asks the user to supply standing positions inline if needed.

If the NDA text is not provided, stop and request it. Do not reconstruct or assume contract language.

## Do Not Use When

- The document is not an NDA (use `contract-risk-review` for general commercial agreements).
- The user needs a summary of tracked edits between drafts (use `redline-summary`).
- The confidentiality terms are one section of a larger commercial agreement (use `contract-risk-review`).
- The NDA is part of an M&A, employment, or investment transaction — confidentiality terms in those contexts carry deal-specific risk and should be reviewed with specialist counsel rather than triaged as a stand-alone commercial NDA.
- The request is for a statement of legal advice or a final negotiating position — those require an attorney.

## Legal Safety Rules

- **Source and citation discipline.** Follow `core/source-and-citation-discipline.md`. Never invent legal authority, citations, quotations, statutes, cases, regulations, filing deadlines, or procedural rules. Label what is a provided source, a user-provided fact, an assumption, a legal inference, or an item requiring attorney verification, and use a citation placeholder such as `[Attorney to insert authority]` when no source is available.
- Produce draft legal work product for attorney review. This is not legal advice.
- Review only the language actually present in the provided document. Quote it accurately.
- Do not invent contract terms, defined terms, section numbers, or quotations.
- Do not invent statutes, regulations, or case law. If legal authority is relevant, mark it as an attorney verification item.
- Do not invent or assume deadlines. Treat any signing or negotiation deadline as user-supplied or unverified.
- A triage rating of GREEN ("clear to route for signature") is a workflow signal, not authorization to sign. Attorney review and sign-off remain required before any NDA is signed.
- Do not draft new clause language or restructure provisions. Propose the direction of a change and route substantive drafting to an attorney.
- Distinguish what the contract says from what you assume and from what the attorney must confirm.
- Preserve confidentiality and privilege: the review is attorney work product. Do not place client-sensitive facts into reusable templates.
- Flag every point of uncertainty rather than resolving it silently.
- **Severity floor.** Once an issue has been rated High priority in the prioritized redline points or risk table, that rating must not be silently downgraded. Any reduction in priority is an explicit attorney decision and must be recorded as such (e.g., "Downgraded from High to Medium by [attorney], [date], reason: [brief rationale]"). This applies regardless of the counterparty's explanation or commercial commonness of the provision.
- **Profile reference is optional, not authoritative.** Where `practice-profiles/contracts.md` is loaded, its Standard Positions and Escalation Thresholds inform the draft but never substitute for attorney judgment. The profile is a configuration record approved by the practice group; it is not legal advice and does not override the skill's normal attorney-verification gates. If the profile's standing positions conflict with the matter facts or with what the supervising attorney concludes, the attorney prevails.

## Workflow

This skill draws on shared contract-review reference material in `skills/contracts/references/`: `red-flags.md` (red-flag catalogue), `negotiability-ratings.md` (six-rating negotiability rubric), `market-benchmark-framework.md` (benchmarking discipline and market-practice vocabulary), `fallback-language-bank.md` (sample preferred and fallback positions by clause type), `document-type-checklists.md` (per-document-type checklists), `clause-category-checklist.md` (cross-document clause-category completeness sweep), `market-standard-baselines.md` (open-standard baseline comparisons), and `redline-output-guidance.md` (how to frame redline direction). Consult them at the steps noted below.

1. **Confirm inputs.** Verify you have the full NDA text, the client's role, and the transaction context. If anything is missing, request it before proceeding.
2. **Transaction-context check.** If the NDA is part of an M&A, employment, or investment transaction, stop and route the matter to specialist counsel (see Do Not Use When). Continue only for stand-alone commercial NDAs.
3. **Identify the structure.** Locate and label the core provisions: parties, definition of Confidential Information, permitted use, standard exclusions, term and survival, return/destruction, remedies, and governing law. Use the NDA checklist in `skills/contracts/references/document-type-checklists.md` to confirm nothing is overlooked, and run the formation/term and restrictive-covenant groups of `skills/contracts/references/clause-category-checklist.md` as a fast completeness pass across clause categories before the deeper review.
4. **Red flags quick scan.** Run a fast first pass against the red-flag catalogue in `skills/contracts/references/red-flags.md`. Record each red-flag pattern present, or note that none surfaced in the scan. This scan orients the deeper review; it does not replace it.
5. **Scope check.** Scan for obligations that go beyond confidentiality — for example a standstill, exclusivity, non-solicitation, non-competition, IP assignment, a licensing grant, a right of first refusal, a most-favored-nation clause, broad arbitration, or a governing-law clause reaching beyond confidentiality disputes. Any such term means the document is more than an NDA: flag it prominently and raise the triage rating accordingly.
6. **Summarize each key term** in plain language, citing the section number as written.
7. **Assess risk allocation from the client's role.** A receiving party and a disclosing party care about opposite asymmetries; analyze from the client's actual position.
8. **Benchmark against the client's standard positions.** If a playbook was provided — either inline by the user or via the loaded `practice-profiles/contracts.md` Standard Positions section — note where the NDA matches it, where it deviates, and where any term hits a "never accept" position. Where the profile is loaded but a specific term is silent in its Standard Positions, treat that term as not addressed by the playbook and flag for attorney review. Record any market comparison using the discipline in `skills/contracts/references/market-benchmark-framework.md`: characterize each relevant term with the controlled vocabulary (Common, Aggressive, Unusual, Depends on Leverage, Needs Attorney Confirmation), state the basis and supporting source, and flag every characterization not backed by a playbook, comparable, counterparty prior form, or attorney-supplied norm as an attorney-verification item. AgentCounsel does not supply market data. For a stand-alone mutual or unilateral NDA, also consider a baseline comparison against the oneNDA open standard using `skills/contracts/references/market-standard-baselines.md`.
9. **Flag missing or one-sided terms** — for example, no standard exclusions, a perpetual term on all information, broad injunctive-relief language, or unilateral obligations in a document labeled "mutual."
10. **Build the risk table** using `templates/nda-risk-table.md`.
11. **Rate negotiability.** For each material issue, assign one of the six negotiability ratings from `skills/contracts/references/negotiability-ratings.md` — Must Push, Strong Push, Business Call, Acceptable if Balanced, Low Priority, or Do Not Spend Leverage — with a one-line rationale drawn from leverage, who drafted the form, the deal value, and any regulatory floor.
12. **Draft prioritized redline points.** Rank issues High / Medium / Low. For each, following `skills/contracts/references/redline-output-guidance.md`, state: the issue, why it matters, a **Preferred Position**, a **Fallback Position**, and a **Suggested Redline Direction** — the direction of the change, not final clause language unless the user asks for it. Use `skills/contracts/references/fallback-language-bank.md` to help articulate preferred and fallback positions. Route substantive drafting to an attorney.
13. **Internal consistency check.** Confirm that defined terms, party names, cross-references, and section numbers are used consistently throughout the NDA. Flag any defined-but-unused term, used-but-undefined term, broken cross-reference, mismatched party label, or numbering gap.
14. **Assign an overall triage rating:**
    - **GREEN — clear to route for signature.** Terms are consistent with the client's role and standard positions; no obligations beyond confidentiality; no missing protection that matters for the client's role. Attorney sign-off is still required.
    - **YELLOW — flag for negotiation or approver review.** One or more terms deviate from the client's standard positions or are one-sided but not dealbreakers; or a playbook is silent on a material term; or the scope check found a non-confidentiality term that needs review.
    - **RED — stop and escalate.** A term hits a "never accept" position; there is a structural mismatch (such as unilateral obligations in a "mutual" NDA, or a perpetual term on all information); or the document carries significant non-confidentiality obligations or arises in an M&A, employment, or investment context.
15. **List attorney verification items** — governing-law implications, enforceability questions, every unverified benchmark, and anything requiring legal judgment.
16. **Draft a business-friendly summary.** Produce a short, plain-language summary for non-lawyer stakeholders: the overall posture, the few terms that matter most, what to push on and why, and what — if anything — would stop signature. Use the stakeholder-communication language patterns in `skills/contracts/references/negotiability-ratings.md`. Avoid legal jargon.
17. **Assemble the output** and label it as a draft for attorney review.

## Output Format

Deliver:

1. **Triage Rating** — GREEN / YELLOW / RED, with a one-line rationale.
2. **Summary** — 3-5 sentences: document type, client role, overall risk posture.
3. **Red Flags Quick Scan** — each red-flag pattern from `skills/contracts/references/red-flags.md` found in the NDA, or a note that none surfaced in the scan.
4. **Key Terms Table** — plain-language summary with section references.
5. **Scope Check** — whether the document contains obligations beyond confidentiality, and which.
6. **Risk Table** — from `templates/nda-risk-table.md`.
7. **Negotiability Table** — a table covering each material issue, with columns: Issue | Negotiability Rating | Basis | Recommended Lawyer Action. The Negotiability Rating is one of the six ratings defined in `skills/contracts/references/negotiability-ratings.md` (Must Push, Strong Push, Business Call, Acceptable if Balanced, Low Priority, Do Not Spend Leverage); the Basis is a one-line rationale.
8. **Market Practice Notes** — any market comparison, recorded using `skills/contracts/references/market-benchmark-framework.md`. Characterize each relevant term with the controlled vocabulary (Common, Aggressive, Unusual, Depends on Leverage, Needs Attorney Confirmation), state the basis and supporting source, and flag every characterization not backed by a playbook, comparable, counterparty prior form, or attorney-supplied norm for attorney verification. AgentCounsel does not supply market data.
9. **Prioritized Redline Points** — High / Medium / Low. Each point states the issue and why it matters, a **Preferred Position**, a **Fallback Position**, and a **Suggested Redline Direction** (direction of change, not final language), following `skills/contracts/references/redline-output-guidance.md`. Use `skills/contracts/references/fallback-language-bank.md` to help articulate preferred and fallback positions.
10. **Business-Friendly Summary** — a short, plain-language summary for non-lawyer stakeholders: the overall posture, the few terms that matter most, what to push on and why, and what — if anything — would stop signature. Avoid legal jargon.
11. **Internal Consistency Check** — whether defined terms, party names, cross-references, and section numbers are used consistently, with any inconsistency flagged.
12. **Attorney Verification Items** — open questions and items requiring legal judgment.
13. **Assumptions** — every assumption made, listed explicitly.

Use placeholders like `[CONFIRM: governing law]` wherever information is missing. Do not fill gaps with invented content.

### Optional: Business Stakeholder Summary

When the output will be used to brief a non-lawyer business stakeholder — a product owner, deal lead, people manager, founder, or executive — add a **Business Stakeholder Summary** as a clearly separated, plainly labeled section, following `core/business-stakeholder-communication.md`. Produce it only when the user requests it or when the audience is plainly a business decision-maker. It is an addition to the deliverable above — never a replacement for it, and never a substitute for attorney review. It contains:

- **Business Summary** — the bottom line in plain language, with unnecessary legal jargon removed and legal risk stated separately from business and commercial risk.
- **Decision Needed** — the specific business decision(s) now on the table, stated as concrete choices, each with its owner.
- **Recommended Ask** — the legal team's recommended position or course of action, framed as a recommendation for the business to weigh, not a decision made on its behalf.
- **Fallback Position** — the minimum acceptable alternative if the Recommended Ask cannot be achieved.
- **Escalation Needed?** — whether the matter should be escalated, to whom (senior management, the board, or outside counsel), and why — or a plain statement that no escalation is needed.

## Attorney Verification Checklist

- [ ] The NDA text reviewed is complete and final.
- [ ] The client's role (disclosing / receiving / mutual) is correctly identified.
- [ ] The transaction context is confirmed; if the NDA arises in an M&A, employment, or investment deal, specialist counsel has been involved.
- [ ] The scope check is complete; if the document contains obligations beyond confidentiality, it has been reviewed as more than an NDA.
- [ ] All section references and quotations match the source document.
- [ ] No legal authority, statute, or case law has been asserted without verification.
- [ ] Enforceability of remedies and any restrictive covenants has been assessed under the governing law.
- [ ] Governing law and jurisdiction are appropriate for the client.
- [ ] Term and survival periods are acceptable for the type of information being shared.
- [ ] The triage rating and risk ratings reflect the client's standard positions, role, and leverage.
- [ ] The red-flag quick scan and the negotiability table have been reviewed; each of the six-scale negotiability ratings reflects the client's actual leverage and standard positions.
- [ ] Every market-practice characterization has a stated basis and supporting source; no market benchmark has been relied on without independent verification.
- [ ] Preferred and fallback positions reflect the client's actual leverage and standard positions.
- [ ] The business-friendly summary accurately reflects the review and neither overstates nor understates any risk.
- [ ] The internal consistency check is complete; defined terms and cross-references are sound.
- [ ] A GREEN rating has attorney sign-off before the NDA is signed.
- [ ] All assumptions and open items are resolved before the review is relied upon.
- [ ] If a practice profile was loaded: every Standard Position and Escalation Threshold that applies to the matter facts has been surfaced; deviations are flagged; profile-silent items are flagged as not-yet-addressed by the playbook.
- [ ] If no practice profile was loaded: any benchmarking or "standard position" framing in the output is grounded in user-supplied inline data, not assumed.

=== END AGENTCOUNSEL CORE SKILL ===

=== BEGIN AGENTCOUNSEL SPEC ===
Canonical path: skills/contracts/nda-review/SPEC.json
{
  "schema_version": "2.0",
  "skill_id": "contracts/nda-review",
  "inherits": [
    "core/business-stakeholder-communication.md"
  ],
  "gates": {
    "custom": [
      {
        "id": "specialist-transaction-context",
        "condition": "The NDA is part of an M&A, employment, or investment transaction.",
        "action": "stop-and-escalate",
        "reason": "The confidentiality terms require transaction-specific specialist review rather than stand-alone commercial NDA triage."
      },
      {
        "id": "non-confidentiality-obligations",
        "condition": "The document contains standstill, exclusivity, non-solicitation, non-competition, IP assignment, license, right-of-first-refusal, most-favored-nation, or similarly broader obligations.",
        "action": "require-attorney-confirmation",
        "reason": "The document may be more than an NDA and cannot be routed for signature on confidentiality review alone."
      }
    ]
  },
  "execution_modes": [
    {
      "id": "quick-triage",
      "enabled": true,
      "purpose": "Confirm the document is a stand-alone commercial NDA, identify missing inputs, scan for obligations beyond confidentiality, and return only the preliminary escalation posture.",
      "output_detail": "minimal",
      "quality_checks": [
        "attorney-review-gate",
        "source-validation-check"
      ]
    },
    {
      "id": "standard",
      "enabled": true,
      "purpose": "Produce the standard NDA triage rating, key-term summary, risk table, negotiation priorities, and attorney-verification items.",
      "output_detail": "standard",
      "quality_checks": [
        "attorney-review-gate",
        "source-validation-check",
        "assumption-audit",
        "legal-prose-polish"
      ]
    },
    {
      "id": "deep-review",
      "enabled": true,
      "purpose": "Run the complete clause-category, red-flag, market-benchmark, negotiability, internal-consistency, and stakeholder-summary workflow with all applicable reference modules.",
      "output_detail": "expanded",
      "quality_checks": [
        "attorney-review-gate",
        "source-validation-check",
        "assumption-audit",
        "hallucination-red-team",
        "output-format-compliance-check",
        "privilege-confidentiality-check",
        "legal-prose-polish"
      ]
    }
  ],
  "input_schema": [
    {
      "id": "clients-role-disclosing-receiving-or-mutual",
      "label": "Client role",
      "type": "enum",
      "required": true,
      "description": "The client's role under the NDA.",
      "source_requirement": "user-provided",
      "may_infer": false,
      "sensitive": false,
      "enum": [
        "disclosing",
        "receiving",
        "mutual"
      ]
    },
    {
      "id": "transaction-context",
      "label": "Transaction context",
      "type": "enum",
      "required": true,
      "description": "The transaction setting used to determine whether stand-alone NDA triage is appropriate.",
      "source_requirement": "user-provided",
      "may_infer": false,
      "sensitive": false,
      "enum": [
        "standalone-commercial",
        "m-and-a",
        "employment",
        "investment",
        "other"
      ]
    }
  ],
  "output_schema": [
    {
      "id": "structured-risk-summary",
      "label": "Structured risk summary",
      "type": "table",
      "required": true,
      "description": "Material NDA provisions, exact section evidence, client risk, severity, preferred position, fallback position, and attorney action.",
      "attorney_review_required": true
    },
    {
      "id": "prioritized-redline-points-for-attorney-review",
      "label": "Prioritized redline points for attorney review",
      "type": "checklist",
      "required": true,
      "description": "High, medium, and low negotiation points with preferred and fallback positions and no final clause language unless attorney-directed.",
      "attorney_review_required": true
    }
  ],
  "evidence_schema": {
    "required_fields": [
      "support_text"
    ],
    "fields": [
      {
        "id": "provision_name",
        "type": "text",
        "description": "The provision or clause category supporting the issue."
      },
      {
        "id": "client_position",
        "type": "text",
        "description": "The client role and playbook position used in the analysis."
      }
    ]
  },
  "modules": [
    {
      "id": "nda-risk-table-template",
      "kind": "template",
      "path": "skills/contracts/nda-review/templates/nda-risk-table.md",
      "required": true,
      "load_when": "standard or deep-review mode"
    },
    {
      "id": "contract-red-flags",
      "kind": "reference",
      "path": "skills/contracts/references/red-flags.md",
      "required": true,
      "load_when": "all enabled modes"
    },
    {
      "id": "negotiability-ratings",
      "kind": "reference",
      "path": "skills/contracts/references/negotiability-ratings.md",
      "required": false,
      "load_when": "standard or deep-review mode when negotiation prioritization is requested"
    },
    {
      "id": "market-benchmark-framework",
      "kind": "reference",
      "path": "skills/contracts/references/market-benchmark-framework.md",
      "required": false,
      "load_when": "deep-review mode or when market practice is requested"
    },
    {
      "id": "contracts-practice-profile",
      "kind": "profile",
      "path": "practice-profiles/contracts.md",
      "required": false,
      "load_when": "a populated and attorney-approved contracts profile is available"
    }
  ]
}

=== END AGENTCOUNSEL SPEC ===

=== BEGIN AGENTCOUNSEL MODULE: nda-risk-table-template ===
Kind: template
Canonical path: skills/contracts/nda-review/templates/nda-risk-table.md
Load when: standard or deep-review mode

# NDA Risk Table

> Draft legal work product for attorney review. Not legal advice.
> Do not paste client-sensitive facts into a reusable copy of this template.

**Matter:** [matter name / number]
**Document reviewed:** [NDA title and date]
**Client role:** [Disclosing party / Receiving party / Mutual]
**Overall triage:** [GREEN — route for signature / YELLOW — flag for review / RED — stop and escalate]
**Reviewer:** [name]   **Review date:** [date]
**Governing law (as drafted):** [CONFIRM]

| # | Provision | Section | What it says (plain language) | Risk to client | Severity | Suggested change | Attorney note |
|---|-----------|---------|-------------------------------|----------------|----------|------------------|---------------|
| 1 | Definition of Confidential Information | [§] | | | | | |
| 2 | Permitted use | [§] | | | | | |
| 3 | Standard exclusions | [§] | | | | | |
| 4 | Term and survival | [§] | | | | | |
| 5 | Return / destruction | [§] | | | | | |
| 6 | Remedies / injunctive relief | [§] | | | | | |
| 7 | Governing law / jurisdiction | [§] | | | | | |
| 8 | Other restrictive covenants | [§] | | | | | |

## Severity key

- **High** — material exposure or one-sided allocation; address before signing.
- **Medium** — meaningful issue; negotiate where leverage allows.
- **Low** — minor or stylistic; note, but unlikely to block signing.

## Open items for attorney verification

- [ ] Enforceability of remedies and any restrictive covenants under the governing law.
- [ ] Whether the term and survival periods fit the sensitivity of the information.
- [ ] Whether the definition of Confidential Information is appropriately scoped for the client's role.
- [ ] Any item marked `[CONFIRM]` above.

=== END AGENTCOUNSEL MODULE: nda-risk-table-template ===

=== BEGIN AGENTCOUNSEL MODULE: contract-red-flags ===
Kind: reference
Canonical path: skills/contracts/references/red-flags.md
Load when: all enabled modes

> Shared reference material supporting the AgentCounsel contracts skills, used to help produce draft legal work product for attorney review — not legal advice.

# Contract Red-Flag Catalog

This catalog lists clause patterns and structural features that a reviewer should actively scan for during a contract review. Each entry describes the pattern, why it matters, what to check, and which client roles are most exposed. The catalog is organized by clause category to support a Red Flags Quick Scan output within the contracts skills.

This catalog is a review aid. It identifies what to look for and why. Whether a flagged pattern is actually problematic depends on the specific contract language, the client's role, the business context, and attorney judgment. Every flagged item is a candidate for attorney verification — not a legal conclusion.

---

## How to Use This Catalog

For each clause category below:

1. Locate the relevant provision in the document under review (or note its absence — a missing provision is itself a red flag in many contexts).
2. Check the pattern description against the actual language.
3. If the pattern is present, add the item to the risk matrix and the issue list.
4. Note which client roles are most exposed and whether the client's role matches the exposure profile.
5. Flag every finding for attorney review; do not resolve ambiguity silently.

---

## 1. Limitation of Liability

### 1.1 Cap tied to a very short period or very low base

**Pattern:** The liability cap is calculated as fees paid in the prior one or two months, or a nominal fixed amount that is small relative to the realistic loss scenario.

**Why it matters:** If the client's realistic harm from a breach (data loss, business interruption, IP misappropriation) greatly exceeds the cap, the clause transfers nearly all downside risk to the client.

**What to check:**
- Quote the cap formula verbatim.
- Compare the cap amount to the client's estimated worst-case exposure and the total contract value.
- Identify whether the cap applies to all claims or only certain types.

**Most exposed:** Customer / buyer / licensee receiving services or data access; any party whose loss would be consequential in nature.

---

### 1.2 Consequential-damages waiver covering the client's primary loss type

**Pattern:** The waiver of indirect, consequential, incidental, or special damages is mutual in form but asymmetric in effect — because the client's realistic losses are almost entirely consequential (lost profits, business interruption, data loss) while the vendor's realistic losses are direct (unpaid fees).

**Why it matters:** A nominally mutual clause can be functionally one-sided if one party's harm is categorically different from the other's.

**What to check:**
- Quote the exclusion language exactly.
- Identify whether lost profits, lost data, or business interruption are expressly included or excluded.
- Check whether any carve-outs restore consequential-damages recovery for specific breach types (data breach, fraud, willful misconduct, IP infringement).

**Most exposed:** Customer / buyer relying on services for business operations; parties with high data or IP exposure.

---

### 1.3 No carve-outs for fraud, willful misconduct, or death/personal injury

**Pattern:** The cap and consequential-damages waiver apply to all claims with no exceptions for egregious conduct.

**Why it matters:** Absence of carve-outs for fraud, willful misconduct, gross negligence, or death/personal injury is non-standard and may be unenforceable in some jurisdictions `[verify jurisdiction]`.

**What to check:**
- List every carve-out that is present.
- Note any carve-out that is one-sided (e.g., data breach carved out for vendor but not for client).

**Most exposed:** Any party relying on the counterparty to handle sensitive data, physical property, or activities with personal-injury risk.

---

### 1.4 IP indemnity subject to liability cap

**Pattern:** The intellectual property indemnity is not carved out from the liability cap, meaning the indemnifying party's maximum exposure for an IP infringement claim is limited to the cap amount.

**Why it matters:** IP infringement claims can generate liability far exceeding typical fee-based caps. If the IP indemnity is capped, the party receiving the indemnity bears the excess risk.

**What to check:**
- Confirm whether the IP indemnity is expressly carved out from the cap.
- Check whether the indemnity is mutual or one-sided.

**Most exposed:** Licensee or customer accepting IP representations from the vendor.

---

## 2. Indemnification

### 2.1 Broad, one-sided indemnification

**Pattern:** The client is required to indemnify the vendor broadly (e.g., for any claim arising from client's "use" of the product or service) without a reciprocal indemnity running from vendor to client.

**Why it matters:** A unilateral indemnity can transfer risk for claims the client did not cause, including claims arising from the vendor's own defects or conduct.

**What to check:**
- Is the indemnity mutual or one-sided?
- What triggers the client's indemnity obligation — is "use" or "breach" defined narrowly?
- Is there a carve-out for claims caused by the vendor's own negligence or misconduct?

**Most exposed:** Customer / buyer who does not have leverage to insist on mutuality.

---

### 2.2 No procedural controls on indemnity claims

**Pattern:** The indemnification provision does not require prompt notice of a claim, does not give the indemnifying party control over the defense, and does not require the indemnified party's cooperation.

**Why it matters:** Without procedural controls, the indemnified party can settle a claim at the indemnifying party's expense or prejudice the defense by giving late notice.

**What to check:**
- Is there a notice requirement with a time frame?
- Is there a defense-control right for the indemnifying party?
- Is there a restriction on the indemnified party settling without consent?
- Is there a cooperation obligation?

**Most exposed:** Any party in the indemnifying role.

---

### 2.3 Indemnity triggered by IP claims arising from client modifications

**Pattern:** The client's IP indemnity obligation is triggered by any infringement claim related to the vendor's product, including where the infringement arises from the vendor's base product rather than the client's modifications.

**Why it matters:** The client should bear indemnity risk only for infringement resulting from its own modifications or misuse, not for the vendor's baseline IP risk.

**What to check:**
- Is the IP indemnity limited to claims caused by client modifications or client-provided materials?
- Is the vendor's own IP indemnity obligation clearly stated?

**Most exposed:** Customer / licensee who deploys or integrates vendor technology.

---

## 3. Intellectual Property

### 3.1 Future-tense assignment language

**Pattern:** Work-for-hire or assignment provisions use future-tense language ("will assign," "agrees to assign," "shall vest in") rather than a present-tense grant ("hereby assigns," "is hereby assigned," "vests in").

**Why it matters:** A future promise to assign may require a further act (a subsequent written assignment instrument) to perfect the transfer of ownership `[verify jurisdiction]`. Without that further act, ownership may remain with the assignor.

**What to check:**
- Quote the assignment language verbatim.
- Is it present-tense or future-tense?
- Is there a further-assurances or cooperation clause requiring the assignor to execute additional instruments?
- Is there a power of attorney as backup?

**Most exposed:** Client receiving a work product assignment, acquirer in an M&A diligence context.

---

### 3.2 No further-assurances obligation

**Pattern:** An IP assignment clause contains no obligation on the assignor to execute additional documents or take further steps to perfect the assignment.

**Why it matters:** Without a further-assurances clause, the assignee may be unable to register the IP, record the assignment, or enforce the assignment against third parties if the assignor later becomes uncooperative.

**What to check:**
- Is a further-assurances or cooperation obligation present?
- Is there a provision addressing what happens if the assignor cannot be located or refuses to cooperate?

**Most exposed:** Assignee / buyer / commissioning party.

---

### 3.3 Broad vendor background IP carve-out

**Pattern:** The vendor retains broad rights to background IP, pre-existing tools, platforms, and methodologies used to create the deliverables, with no license back to the client to use those elements embedded in the deliverables.

**Why it matters:** If vendor-retained background IP is embedded in the deliverables, the client owns a deliverable it cannot independently use or modify without an ongoing vendor license.

**What to check:**
- What is included in the definition of background IP?
- Is there a license back to the client for use of background IP embedded in deliverables?
- Can the client's use survive termination of the contract?

**Most exposed:** Client commissioning custom work product (software, creative content, technology).

---

### 3.4 No moral rights treatment

**Pattern:** An assignment of creative works makes no mention of moral rights — no waiver, no confirmation that the jurisdiction does not recognize moral rights, and no express inclusion in the assignment.

**Why it matters:** In jurisdictions that recognize moral rights, an assignment of copyright does not automatically transfer or extinguish moral rights `[verify jurisdiction]`. An unaddressed moral rights position can complicate the assignee's ability to modify or commercialize the work.

**What to check:**
- Does the clause include a waiver of moral rights?
- Is a waiver effective in the governing jurisdiction? `[verify jurisdiction]`

**Most exposed:** Assignee of creative or software works intended for modification or commercialization.

---

### 3.5 Residual rights / residual knowledge clause

**Pattern:** The contract includes a residual rights or residual knowledge clause allowing the vendor to retain and use unaided human memory of confidential information, ideas, concepts, or methods encountered during performance.

**Why it matters:** A residual-knowledge clause can be a significant erosion of confidentiality and IP protection — the vendor's personnel can, in theory, use retained knowledge to benefit competitors.

**What to check:**
- Is the residual clause limited in scope (e.g., to genuinely unaided memory only, excluding written notes or deliberate memorization)?
- Does the residual clause carve out trade secrets or specifically identified confidential categories?
- Does the clause interact with the IP assignment — could retained knowledge be used to recreate assigned work?

**Most exposed:** Disclosing party; client commissioning proprietary development.

---

## 4. Termination

### 4.1 Asymmetric termination for convenience

**Pattern:** One party (typically the vendor) has a termination-for-convenience right with a short notice period, but the other party (typically the client) does not, or must pay a substantial termination fee.

**Why it matters:** The party without a convenience termination right is locked in, while the counterparty retains flexibility.

**What to check:**
- Are termination-for-convenience rights mutual?
- What is the required notice period?
- Are there fees payable on termination (wind-down fees, accelerated payments, break fees)?

**Most exposed:** Client locked into a long-term services or subscription relationship.

---

### 4.2 Short cure period or no cure period for material breach

**Pattern:** Termination for cause is triggered on breach with a very short cure period (or no cure period), meaning a minor operational failure can give rise to immediate termination.

**Why it matters:** A short or absent cure period can be used opportunistically to terminate a relationship that the other party wants to exit for other reasons.

**What to check:**
- Is the cure period reasonable given the nature of the obligations?
- Is the right to terminate limited to material breach, or does it extend to any breach?
- Is the "material breach" standard defined, or is it left open?

**Most exposed:** Party performing services or delivering technology who bears the risk of inadvertent breach.

---

### 4.3 Broad termination triggers beyond breach

**Pattern:** Termination rights are triggered by events beyond breach: insolvency, change of control, regulatory action, or subjective standards ("if [party] determines in its sole discretion that performance is unsatisfactory").

**Why it matters:** Broad termination triggers can be exercised to exit a deal that the counterparty simply no longer wants, regardless of fault.

**What to check:**
- List every termination trigger in the agreement.
- Flag any trigger based on subjective determination without an objective standard.
- Check whether insolvency termination may be unenforceable in the relevant jurisdiction `[verify jurisdiction]`.

**Most exposed:** Party who has invested significantly in relationship setup (data migration, integration, customization).

---

### 4.4 Inadequate wind-down and data return provisions

**Pattern:** The termination section says nothing about transition assistance, data export, data deletion timelines, return of confidential information, or continuity of access during a wind-down period.

**Why it matters:** Without wind-down provisions, a party can be cut off from data, systems, or services immediately on termination with no ability to transition.

**What to check:**
- Is there a transition assistance obligation (and for how long)?
- Is there a data export right before deletion?
- Is there a data deletion obligation and timeline?
- Are there post-termination access rights for retrieval?

**Most exposed:** Customer or client whose operations depend on access to vendor-held data or systems.

---

## 5. Fees, Payment, and Price Escalation

### 5.1 Unilateral price escalation right

**Pattern:** The vendor has the right to increase fees unilaterally on notice (or at renewal), with no cap on the increase percentage and no right for the client to terminate without penalty if the increase is unacceptable.

**Why it matters:** An uncapped unilateral escalation right gives the vendor leverage to impose significant price increases that the client cannot easily exit.

**What to check:**
- Is the escalation right unilateral or subject to mutual agreement?
- Is there a cap on annual increases (e.g., tied to a published index)?
- Does the client have a termination right if it rejects the increase?

**Most exposed:** Client in a multi-year or auto-renewing subscription or services contract.

---

### 5.2 Fees payable on termination or early exit

**Pattern:** The contract requires the client to pay all remaining fees for the unexpired term if the contract is terminated for any reason (including vendor breach), or imposes a substantial early-termination fee.

**Why it matters:** An obligation to pay all remaining fees on termination, even for vendor breach, shifts the financial risk of the relationship to the client.

**What to check:**
- Does the termination-fee obligation apply even on termination for vendor cause?
- Are there any offsets or credits for the vendor's cost savings on early exit?
- Are there acceleration provisions in other parts of the contract (e.g., payment on insolvency)?

**Most exposed:** Client in a long-term, high-value contract.

---

### 5.3 Short payment window with automatic late fees or suspension right

**Pattern:** Payment is due within a very short window (e.g., 5 or 10 days of invoice), with automatic late fees, interest, or the right to suspend services immediately on non-payment.

**Why it matters:** Short payment windows and suspension rights can be used to create leverage, particularly if the client's accounts-payable cycle is longer than the payment window.

**What to check:**
- What is the payment window?
- Is a dispute or good-faith objection sufficient to pause the payment obligation?
- What is the suspension notice period?
- Are late fees or interest rates specified, and are they commercially reasonable?

**Most exposed:** Customer with standard payment cycles; client who relies on continuous service access.

---

### 5.4 Fees due on disputed invoices

**Pattern:** The contract requires payment of all invoiced amounts — including amounts under good-faith dispute — within the payment window, with no mechanism for withholding disputed amounts pending resolution.

**Why it matters:** Requiring payment of disputed amounts removes the client's leverage to dispute invoices without facing late fees, suspension, or default.

**What to check:**
- Is there an invoice dispute mechanism?
- Can the client withhold disputed amounts without triggering late fees or default?
- What is the resolution process for invoice disputes?

**Most exposed:** Client with complex or variable invoicing arrangements.

---

## 6. Confidentiality

### 6.1 Overly broad definition of Confidential Information

**Pattern:** "Confidential Information" is defined to include essentially everything the disclosing party has ever communicated — oral, written, or observed — with no requirement of marking or identification.

**Why it matters:** An over-broad definition creates compliance difficulties and potentially exposes the receiving party to liability for normal business activities (e.g., using generally available information or independently developed knowledge).

**What to check:**
- What are the standard exclusions (publicly available information, independently developed, received from third parties without restriction)?
- Is oral information included? If so, what confirmation steps are required?
- Is there a residual knowledge carve-out (see Section 3.5)?

**Most exposed:** Receiving party who must manage and segregate a very broad confidentiality obligation.

---

### 6.2 Perpetual confidentiality obligation

**Pattern:** Confidentiality obligations survive termination indefinitely, with no sunset period.

**Why it matters:** Perpetual obligations can be overly burdensome, difficult to manage operationally over time, and may be unenforceable in some jurisdictions `[verify jurisdiction]`.

**What to check:**
- Is the confidentiality term defined?
- Are trade secrets carved out for longer or indefinite protection (which may be appropriate)?
- Does the duration align with the sensitivity of the information and market norms for the transaction type?

**Most exposed:** Receiving party with long-term operational compliance obligations.

---

### 6.3 No return-or-destroy obligation

**Pattern:** The confidentiality section contains no obligation to return or destroy confidential information on termination or at the disclosing party's request.

**Why it matters:** Without a return-or-destroy obligation, confidential information may remain with the receiving party indefinitely after the relationship ends.

**What to check:**
- Is there a return-or-destroy obligation?
- Is there a certification requirement?
- Are backup copies and legal hold exceptions addressed?

**Most exposed:** Disclosing party sharing sensitive business, technical, or personal information.

---

## 7. Data, Privacy, and Security

### 7.1 No data processing agreement or data processing terms

**Pattern:** The contract involves the vendor processing personal data on behalf of the client, but contains no data processing agreement, data processing addendum, or data-specific terms addressing processing purposes, data subject rights, security requirements, sub-processing, data return, and deletion.

**Why it matters:** Regulatory frameworks applicable to personal data processing may require a data processing agreement and may impose liability for its absence `[verify jurisdiction]`.

**What to check:**
- Does the contract involve vendor processing of personal data?
- Is there a data processing agreement or addendum?
- If a DPA is referenced but not attached, confirm it exists and is incorporated by reference.

**Most exposed:** Client acting as data controller whose regulatory obligations flow to its processors.

---

### 7.2 No breach notification obligation, or notification period is very long

**Pattern:** The vendor has no obligation to notify the client of a security breach or data incident, or the notification period is so long that it would prevent timely regulatory or customer notification.

**Why it matters:** Failure to receive timely breach notification can cause the client to miss mandatory reporting deadlines under applicable regulatory frameworks `[verify jurisdiction]`.

**What to check:**
- Is there a breach notification obligation?
- What is the notification trigger (confirmed breach vs. suspected incident)?
- Is the notification period consistent with applicable legal requirements? `[verify jurisdiction]`
- Is the notification obligation to the client, or does the vendor notify regulators directly?

**Most exposed:** Client acting as data controller or subject to sector-specific security obligations.

---

### 7.3 Broad data use rights granted to vendor

**Pattern:** The vendor is permitted to use client data for its own purposes — product improvement, analytics, benchmarking, training AI or machine learning models — with broad or unlimited scope.

**Why it matters:** Broad data use rights can expose the client's confidential business data, personal data it controls, or proprietary datasets to use for the vendor's competitive benefit.

**What to check:**
- What are the permitted uses of client data by the vendor?
- Is the scope limited to providing the contracted services?
- Can the vendor use client data to train models or develop competing services?
- If the contract involves AI or machine learning services, route to or also apply the `ai-vendor-terms-review` skill.

**Most exposed:** Client with proprietary data, personal data obligations, or competitive sensitivity about usage patterns.

---

### 7.4 No data deletion or portability right on termination

**Pattern:** The contract does not require the vendor to delete client data on termination, does not specify a deletion timeline, and does not provide a right for the client to export its data in a usable format before deletion.

**Why it matters:** Without a deletion and portability right, client data may persist indefinitely on vendor systems, the client may be unable to migrate to a replacement vendor, and residual data may create ongoing compliance or competitive risk.

**What to check:**
- Is there a data deletion obligation? When does it trigger?
- Is there a data export or portability right? In what format?
- Is there a post-termination access window for retrieval?

**Most exposed:** Client with significant data stored on or processed by vendor systems.

---

## 8. Dispute Resolution

### 8.1 Mandatory arbitration in a forum inconvenient for the client

**Pattern:** The contract requires all disputes to be resolved by arbitration in a specific city or jurisdiction that is the vendor's home forum and is inconvenient or expensive for the client.

**Why it matters:** Inconvenient forum requirements raise the cost and burden of dispute resolution, which can deter a client from pursuing legitimate claims.

**What to check:**
- Is arbitration mandatory or permissive?
- What is the venue?
- Which arbitration rules govern?
- Is there a fee allocation provision?
- Does the clause include a waiver of jury trial? `[verify jurisdiction]`

**Most exposed:** Client who is geographically distant from the vendor, or a smaller party with limited litigation resources.

---

### 8.2 Class action or collective claim waiver

**Pattern:** The dispute resolution clause waives the right to bring or participate in class action or collective proceedings.

**Why it matters:** Class action waivers may limit the client's ability to participate in or benefit from group relief `[verify jurisdiction]`.

**What to check:**
- Is a class action waiver present?
- Is it enforceable in the applicable jurisdiction? `[verify jurisdiction]`
- Does the waiver cover all types of claims or only certain categories?

**Most exposed:** Client exposed to systemic vendor conduct affecting many customers.

---

### 8.3 No carve-out for injunctive relief in court

**Pattern:** A mandatory arbitration clause does not carve out the right to seek emergency or preliminary injunctive relief in a court of competent jurisdiction.

**Why it matters:** Arbitration proceedings typically move more slowly than emergency court applications. Without a court carve-out, a party facing imminent harm (e.g., ongoing misappropriation of trade secrets) may be unable to obtain timely interim relief.

**What to check:**
- Is there a carve-out permitting either party to seek injunctive or other equitable relief in court?
- Is the carve-out mutual?

**Most exposed:** Any party whose potential harm could be irreparable and time-sensitive (IP holder, data owner).

---

## 9. Auto-Renewal

### 9.1 Auto-renewal with short or unclear non-renewal window

**Pattern:** The contract automatically renews for the same term unless a party gives notice within a window that is short, poorly defined, or measured from an unclear trigger date.

**Why it matters:** A client who misses the non-renewal window is committed to another full term, potentially with updated pricing or revised terms.

**What to check:**
- What is the auto-renewal notice window?
- When does the window open and close relative to the renewal date?
- Is the renewal for the same term length and pricing, or does pricing change?
- Does any price-escalation right apply automatically at renewal?

**Most exposed:** Client in a multi-year subscription or services contract who may not actively track renewal dates.

---

### 9.2 Renewal at modified terms

**Pattern:** On auto-renewal, the contract incorporates the vendor's then-current standard terms or pricing rather than the terms in effect at signing.

**Why it matters:** The client may be bound on renewal to materially different terms without receiving notice of specific changes.

**What to check:**
- Does the renewal lock in existing terms or incorporate updated terms?
- Is there a requirement for the vendor to notify the client of material changes before renewal?
- Is there a right to reject updated terms and terminate on shorter notice?

**Most exposed:** Client in a long-term, auto-renewing relationship with a vendor who regularly updates its standard terms.

---

## 10. Assignment and Change of Control

### 10.1 No consent right on vendor assignment or change of control

**Pattern:** The vendor may assign the contract, or undergo a change of control (acquisition, merger), without the client's consent, automatically binding the client to the acquirer or assignee.

**Why it matters:** The client may be bound to a counterparty it would not have chosen — including a competitor — with no ability to exit.

**What to check:**
- Does change of control trigger any client rights (consent right, termination right, step-in right)?
- Is assignment limited to affiliates, or is it fully unrestricted?
- Does the client have a right to terminate if change-of-control consent is not obtained?

**Most exposed:** Client in a relationship where the vendor's identity matters (key-person services, sensitive data sharing, competitive sensitivity).

---

### 10.2 Client's anti-assignment rights inconsistent with its own transaction plans

**Pattern:** The contract restricts the client's ability to assign (e.g., requires vendor consent, prohibits assignment to affiliates) in a way that would require consent for the client's own anticipated corporate transactions.

**Why it matters:** Anti-assignment restrictions can require consent from the counterparty for the client's own M&A, restructuring, or affiliate transfers, potentially complicating or blocking internal transactions.

**What to check:**
- What are the client's assignment rights?
- Is assignment to affiliates permitted?
- Is there a change-of-control trigger for the client as well as the vendor?
- Does the client have any anticipated corporate transactions that would trigger the assignment provision?

**Most exposed:** Client undergoing or anticipating M&A activity, spin-off, or internal restructuring.

---

## 11. One-Sided or Unusual Clauses

### 11.1 Vendor's unilateral right to modify the agreement

**Pattern:** The vendor reserves the right to modify the contract, its terms of service, or incorporated policies unilaterally on notice (or by posting to a website), with continued use constituting acceptance.

**Why it matters:** Unilateral modification rights can change material terms — pricing, functionality, data rights, liability allocation — without requiring the client's affirmative consent.

**What to check:**
- Is the unilateral modification right subject to any limits?
- What notice is required?
- Does the client have a right to reject modifications and terminate without penalty?
- Are any terms expressly locked (e.g., pricing for a fixed term)?

**Most exposed:** Client in a subscription or platform-services relationship governed in part by online terms.

---

### 11.2 "Sole discretion" or subjective standards

**Pattern:** Key rights or obligations are conditioned on a party's "sole discretion," "satisfaction," or "good faith" determination, with no objective standard and no right of appeal or review.

**Why it matters:** Sole-discretion standards can be used to exit obligations, withhold approvals, or exercise rights in ways that are commercially unreasonable with limited recourse for the counterparty.

**What to check:**
- What decisions or determinations are left to sole discretion?
- Is the sole-discretion standard mutual or one-sided?
- Is there a deemed-approval mechanism if a decision is not made within a specified period?

**Most exposed:** Party whose performance, approval rights, or payment depends on a subjective determination by the counterparty.

---

### 11.3 Most-favored-nation or most-favored-customer clause

**Pattern:** One party is guaranteed pricing or terms at least as favorable as those the other party offers to any other customer (or a defined set of customers), without a clear definition of what is being compared or a mechanism to verify compliance.

**Why it matters:** MFN clauses create ongoing obligations that are difficult to monitor, can restrict pricing flexibility, and may interact poorly with regulatory requirements `[verify jurisdiction]`.

**What to check:**
- Is the MFN clause clearly defined as to scope, comparator class, and verification mechanism?
- Are there exceptions for promotional pricing, volume discounts, or bundled offerings?
- Does the clause require proactive disclosure of better pricing?

**Most exposed:** Party obligated to maintain MFN compliance over a long agreement term.

---

### 11.4 Unusual representations or warranties

**Pattern:** A party is required to represent or warrant matters that are inherently forward-looking, beyond its knowledge, or outside its control — for example, that third-party technology will perform in a particular way, or that a regulatory outcome will occur.

**Why it matters:** Representations beyond a party's knowledge or control create strict-liability exposure for breach regardless of the party's reasonable efforts.

**What to check:**
- Are any representations or warranties qualified by knowledge (`"to the best of its knowledge"`) when that qualifier is appropriate?
- Are any representations inherently forward-looking or speculative?
- What is the remedy for breach of a warranty — does it go beyond the limitation-of-liability cap?

**Most exposed:** Party making representations about third-party products, regulatory approvals, or future performance.

---

### 11.5 Standstill, non-solicitation, or non-compete embedded in a commercial agreement

**Pattern:** What appears to be a routine commercial agreement contains a standstill clause, a non-solicitation of employees or customers, or a non-compete restriction buried in the confidentiality, term, or general covenants section rather than labeled as such.

**Why it matters:** Restrictive covenants may have enforceability requirements, geographic or duration limits, and regulatory implications that vary by jurisdiction `[verify jurisdiction]`. Finding them embedded in routine commercial agreements is itself a red flag.

**What to check:**
- Perform a scope check across the entire document for non-compete, non-solicit, and standstill language (see also: `nda-review` scope check).
- Flag any such provision prominently regardless of where it appears in the agreement.
- Note that enforceability of restrictive covenants is jurisdiction-dependent `[verify jurisdiction]`.

**Most exposed:** Client whose operational flexibility could be constrained post-signing or post-termination.

---

## 12. Warranties and Disclaimers

See also Section 11.4 on representations or warranties that are forward-looking or extend beyond a party's knowledge.

### 12.1 Blanket "as is" disclaimer leaving no performance recourse

**Pattern:** The counterparty disclaims all warranties — express and implied, including merchantability, fitness for a particular purpose, and non-infringement — and provides the product or service strictly "as is," with no affirmative warranty that it will perform as described or conform to its documentation.

**Why it matters:** If the counterparty makes no enforceable performance promise, the client may have no contractual remedy when the product or service fails to do what the client is paying for — even if the failure is total.

**What to check:**
- Is there any affirmative warranty (conformance to documentation, conformance to specifications, or performance for a defined period)?
- Quote the disclaimer verbatim and identify exactly which warranties are disclaimed.
- Does the disclaimer's breadth conflict with the order form, statement of work, or materials the client relied on?

**Most exposed:** Customer / buyer / licensee relying on the product or service for a business-critical function.

---

### 12.2 Warranty remedy limited to repair-or-replace as the sole remedy

**Pattern:** The only remedy for breach of warranty is the counterparty's election to repair, replace, or re-perform, with no right to a refund, no right to terminate, and no damages if repair or replacement fails.

**Why it matters:** A sole-and-exclusive repair-or-replace remedy can leave the client with no exit and no compensation if the counterparty cannot actually cure the defect.

**What to check:**
- Is the remedy expressed as "sole and exclusive"?
- Is there a fallback (refund or termination right) if repair or replacement fails or cannot be completed within a reasonable time?
- How does the remedy limitation interact with the liability cap (see Section 1)?

**Most exposed:** Customer / buyer of goods, software, or services with defined performance expectations.

---

### 12.3 Warranty period or survival too short to surface real defects

**Pattern:** The warranty period is very short relative to how long defects would realistically take to appear, or warranties expire on delivery or acceptance with no post-acceptance survival.

**Why it matters:** A warranty that expires before latent defects can reasonably be discovered provides little practical protection.

**What to check:**
- What is the warranty period, and when does it start (delivery, acceptance, go-live)?
- Is the period appropriate for the nature of the goods or services and the way defects would surface?
- Is the survival of warranties on termination addressed?

**Most exposed:** Buyer of goods or deliverables where defects may be latent.

---

## 13. Service Levels and Performance Commitments

### 13.1 No service levels for a service the client depends on

**Pattern:** The agreement is for an ongoing service (hosting, SaaS, managed services, support) but contains no uptime commitment, no response or resolution targets, and no defined performance standard.

**Why it matters:** Without a defined service level, the client has no objective standard to measure performance against and no contractual trigger for a remedy when the service degrades.

**What to check:**
- Is there any uptime, availability, or response-time commitment?
- If service levels appear in a separate SLA or exhibit, confirm it is attached and incorporated.
- Is service availability stated as a warranty, a service-level commitment, or merely aspirational language?

**Most exposed:** Customer relying on continuous service availability for operations.

---

### 13.2 Service credits framed as the sole and exclusive remedy

**Pattern:** When the counterparty misses a service level, the client's only remedy is a service credit — typically a small percentage of fees — and the contract states this is the sole and exclusive remedy for any performance failure.

**Why it matters:** Service credits are often far smaller than the client's actual loss from an outage. As a sole-and-exclusive remedy, they can foreclose any other claim for chronic or severe underperformance.

**What to check:**
- Are service credits expressed as the sole and exclusive remedy?
- Is there a right to terminate for chronic or material SLA failure, separate from the credit mechanism?
- Must the client claim credits within a short window or forfeit them?

**Most exposed:** Customer whose realistic outage losses far exceed a fee-percentage credit.

---

### 13.3 Exclusions that swallow the service-level commitment

**Pattern:** The uptime or availability commitment is subject to broad exclusions — scheduled maintenance, emergency maintenance, third-party failures, "force majeure," anything outside the counterparty's "direct control" — wide enough to exclude most realistic downtime.

**Why it matters:** A high headline availability figure can be meaningless if the definition of measured downtime excludes the events that actually cause outages.

**What to check:**
- List every exclusion from the availability calculation.
- Is scheduled maintenance capped as to frequency, duration, notice, and off-peak windows?
- Does the exclusion for third-party or "outside our control" events swallow the commitment?

**Most exposed:** Customer relying on the headline availability figure without reading the measurement definition.

---

## 14. Insurance

### 14.1 No insurance requirement on the counterparty

**Pattern:** The agreement imposes no obligation on the counterparty to carry insurance, even though the counterparty's performance creates risks (property damage, bodily injury, professional error, data breach) that insurance would ordinarily backstop.

**Why it matters:** Without an insurance requirement, the client's ability to actually recover on an indemnity or damages claim depends entirely on the counterparty's balance sheet. An uninsured or judgment-proof counterparty makes a strong indemnity worth little.

**What to check:**
- Is any insurance required?
- Do the required coverage types match the risks the counterparty's performance creates (commercial general liability, professional liability / errors and omissions, cyber / data-breach, workers' compensation, auto)?
- Are coverage limits specified, and are they meaningful relative to the realistic exposure?

**Most exposed:** Client relying on the counterparty's indemnity or damages obligations as a real source of recovery.

---

### 14.2 Insurance mechanics missing (additional insured, certificates, notice)

**Pattern:** The contract requires coverage but omits the operational mechanics: no additional-insured status for the client, no certificate-of-insurance delivery requirement, no advance notice of cancellation or material reduction, no primary-and-noncontributory language.

**Why it matters:** A bare requirement to "carry insurance" without these mechanics gives the client no visibility into whether coverage exists and no direct rights against the policy.

**What to check:**
- Is the client named (or required to be named) as an additional insured where appropriate?
- Must the counterparty deliver certificates of insurance, including on renewal?
- Is there a notice obligation if coverage lapses, is cancelled, or is materially reduced?

**Most exposed:** Client that would need to claim against the counterparty's policy.

---

### 14.3 Insurance offered as a substitute for liability allocation

**Pattern:** The counterparty points to its insurance to justify a low liability cap or broad limitation, but the insurance requirement and the liability cap are not aligned — the cap is below the coverage limit, or the policies exclude the very risks the indemnity covers.

**Why it matters:** Insurance and contractual liability allocation are separate. A policy the client cannot reach, or that excludes the relevant risk, does not cure a deficient liability clause.

**What to check:**
- Does the liability cap align with the insurance limits, or is the cap far lower?
- Do the required policies actually cover the indemnified risks?
- Is the insurance a real backstop, or a negotiating talking point?

**Most exposed:** Client persuaded to accept a low cap on the strength of insurance that may not respond.

---

## 15. Audit and Inspection Rights

### 15.1 No audit right where verification matters

**Pattern:** The client has obligations it needs to confirm the counterparty is meeting — security controls, data handling, regulatory compliance, royalty or usage-based fee calculations — but the contract gives the client no right to audit, inspect, or obtain compliance evidence.

**Why it matters:** Without an audit or reporting right, the client must take the counterparty's compliance on trust and may be unable to detect a breach until it causes harm.

**What to check:**
- Does the client have any audit, inspection, or reporting right?
- For security and data obligations, is there a right to obtain third-party audit reports or certifications in place of, or alongside, a direct audit?
- Are there obligations whose breach the client could not otherwise detect?

**Most exposed:** Client with regulatory exposure, usage-based pricing, or sensitive-data obligations flowing to the counterparty.

---

### 15.2 One-sided audit right running against the client

**Pattern:** The counterparty has a broad right to audit the client's use of a product or service (a license "true-up" audit), often including entry to premises, inspection of systems, and back-charges for any underpayment — with no reciprocal right and few limits.

**Why it matters:** A broad vendor audit right can be used to generate surprise back-charges, disrupt operations, and create leverage at renewal.

**What to check:**
- What triggers the audit right, and how often can it be exercised?
- Is there advance-notice, business-hours, scope, and confidentiality protection?
- Who bears audit costs, and what are the consequences of an adverse finding?

**Most exposed:** Licensee or customer subject to usage-based or seat-based licensing.

---

### 15.3 Audit right with no procedural limits

**Pattern:** An audit right (in either direction) is granted with no limits on notice, frequency, scope, duration, location, who conducts it, the confidentiality of what is reviewed, or who pays.

**Why it matters:** An unbounded audit right is disruptive and can expose the audited party's sensitive information. Procedural limits are what make an audit right workable.

**What to check:**
- Notice period, frequency cap, scope limitation, and business-hours restriction.
- Confidentiality protection for information reviewed during the audit.
- Cost allocation, including any shifting rule if the audit finds a material discrepancy.

**Most exposed:** Whichever party is subject to the audit.

---

## 16. Publicity, Marketing, and Use of Name

### 16.1 Counterparty may use the client's name, marks, or a case study without consent

**Pattern:** The counterparty is permitted to use the client's name, logo, or trademarks, to identify the client as a customer, or to publish a case study or testimonial — without the client's prior written consent for each use.

**Why it matters:** Unconsented use of the client's name and marks can create unwanted public association, implied endorsement, brand-control problems, and trademark-licensing issues.

**What to check:**
- Does the counterparty need the client's prior written consent for each public use?
- Is any permitted use narrowly limited (e.g., to a customer list) and revocable?
- Is the right mutual, and does it survive termination?

**Most exposed:** Client sensitive about brand, public association, or confidentiality of the relationship.

---

### 16.2 No mutual control over public statements about the relationship

**Pattern:** The contract is silent on press releases and public announcements, or allows one party to announce the deal unilaterally.

**Why it matters:** A unilateral announcement can disclose a relationship the client wanted kept confidential, or mischaracterize it.

**What to check:**
- Is there a mutual prior-approval requirement for press releases and public statements?
- Are disclosures required by law or stock-exchange rule carved out?

**Most exposed:** Client with confidentiality, competitive, or regulatory sensitivity about the relationship.

---

## 17. Non-Solicitation and Non-Competition

This section expands on Section 11.5, which flags restrictive covenants embedded in routine commercial agreements. Enforceability of restrictive covenants is highly jurisdiction-dependent and, in some jurisdictions, restricted or prohibited `[verify jurisdiction]`.

### 17.1 Non-compete restricting the client's ordinary business

**Pattern:** The client is restricted from competing with the counterparty, from working with the counterparty's competitors, or from offering certain products or services — in a way that reaches the client's ordinary business activity.

**Why it matters:** A non-compete can constrain the client's core operations, future deals, and strategic flexibility, often far beyond the value of the contract.

**What to check:**
- What activity is restricted, for how long, and in what geography or market?
- Does the restriction reach beyond the subject matter of this contract?
- Is the restriction mutual, and is it enforceable in the governing jurisdiction `[verify jurisdiction]`?

**Most exposed:** Client whose business overlaps with the counterparty's market.

---

### 17.2 Overbroad non-solicitation of employees

**Pattern:** A non-solicit of employees has no carve-out for general advertising, job postings, or unsolicited inbound applications, and/or covers all employees rather than those connected to the engagement.

**Why it matters:** An overbroad non-solicit can be triggered by ordinary recruiting and restrict the client's hiring well beyond the people connected to the deal.

**What to check:**
- Is there a carve-out for general solicitations not targeted at the counterparty's staff, and for unsolicited applicants?
- Is the covered population limited to employees connected to the engagement?
- What is the duration, and does it run from termination?

**Most exposed:** Client that recruits in the same talent market as the counterparty.

---

### 17.3 Customer non-solicitation or exclusivity embedded in the deal

**Pattern:** The agreement restricts the client from soliciting, serving, or contracting with certain customers or categories of customers, or grants the counterparty exclusivity.

**Why it matters:** Customer non-solicits and exclusivity provisions can foreclose revenue opportunities and lock the client out of markets.

**What to check:**
- What customers or segments are covered, and for how long?
- Is exclusivity reciprocal, and is it tied to minimum commitments?
- Flag the provision prominently regardless of where it appears.

**Most exposed:** Client whose growth depends on access to the restricted customers or markets.

---

## 18. Governing Law and Choice of Forum

See also Section 8 (Dispute Resolution) for arbitration-specific patterns.

### 18.1 Governing law or forum with no connection to the parties or transaction

**Pattern:** The agreement selects a governing law or an exclusive forum that has no relationship to either party, the place of performance, or the subject matter.

**Why it matters:** An unrelated governing law can introduce unfamiliar legal rules; an unrelated or distant forum raises the cost and burden of any dispute and can deter the client from enforcing its rights. A choice with no reasonable connection may also face enforceability questions `[verify jurisdiction]`.

**What to check:**
- What law governs, and what is the exclusive forum or venue?
- Is there a reasonable connection between the chosen law or forum and the deal?
- Is the forum the counterparty's home turf and inconvenient for the client?

**Most exposed:** Client distant from the chosen forum, or a smaller party with limited litigation resources.

---

### 18.2 Inconsistent or split governing-law, forum, and arbitration provisions

**Pattern:** Different provisions point in different directions — a governing-law clause naming one jurisdiction, a forum-selection clause naming another, an arbitration clause naming a third seat — or incorporated documents (online terms, exhibits) carry their own conflicting clauses.

**Why it matters:** Inconsistent dispute provisions create uncertainty about where and under what law a dispute would proceed, and can trigger expensive threshold litigation about the dispute clause itself.

**What to check:**
- Do the governing-law, forum-selection, and arbitration clauses align?
- Do incorporated or online terms contain their own, conflicting clauses?
- Is there a clear order-of-precedence rule?

**Most exposed:** Either party, if a dispute arises.

---

### 18.3 Jury-trial waiver

**Pattern:** The agreement waives the right to a jury trial for any dispute.

**Why it matters:** A jury-trial waiver changes who decides the facts in any litigation. Its enforceability and effect vary by jurisdiction `[verify jurisdiction]`.

**What to check:**
- Is a jury-trial waiver present, and is it mutual?
- Is it enforceable under the governing law `[verify jurisdiction]`?

**Most exposed:** Either party; the effect depends on the dispute and the jurisdiction.

---

## Reviewer Notes

- A red flag is a prompt to look closely and flag for attorney attention — not a conclusion that a clause is unenforceable or unacceptable.
- Whether a flagged clause is a problem depends on the client's role, leverage, business context, and risk tolerance — all of which are for the attorney to assess.
- This catalog is not exhaustive. Unusual or deal-specific provisions not listed here may still warrant a flag in the "Unusual or One-Sided Clauses" category of the risk matrix.
- See `skills/contracts/contract-risk-review/SKILL.md` for the full clause-by-clause review workflow.
- See `skills/contracts/nda-review/SKILL.md` for the NDA-specific scope check and risk table workflow.

=== END AGENTCOUNSEL MODULE: contract-red-flags ===

=== BEGIN AGENTCOUNSEL MODULE: negotiability-ratings ===
Kind: reference
Canonical path: skills/contracts/references/negotiability-ratings.md
Load when: standard or deep-review mode when negotiation prioritization is requested

> Shared reference material supporting the AgentCounsel contracts skills, used to help produce draft legal work product for attorney review — not legal advice.

# Negotiability Ratings Framework

This framework gives a reviewer a structured way to rate, for each material issue in a contract, how hard the client should push and what that posture means in practice. It is a reasoning tool — not a fixed list of which clauses are always negotiable and which are not. How negotiable a term is depends on factors that vary by deal, and the supervising attorney determines the final negotiating strategy.

All negotiability ratings are draft assessments for attorney review. The attorney confirms whether a rating is appropriate given the client's actual leverage, the counterparty's behavior, the client's risk tolerance, and strategic priorities.

---

## The Rating Scale

The framework uses six ratings. Each rating combines two judgments: how serious the issue is for the client, and how the lawyer should handle it in the negotiation. The ratings are recommendations to the attorney and the business — not conclusions.

The six ratings, in order:

1. **Must Push** — change it or escalate; do not sign over it.
2. **Strong Push** — negotiate hard; real exposure, movement likely.
3. **Business Call** — a commercial tradeoff for the business to decide.
4. **Acceptable if Balanced** — fine if made mutual or balanced.
5. **Low Priority** — minor; flag it, don't spend capital on it.
6. **Do Not Spend Leverage** — do not raise it.

Must Push, Strong Push, and Low Priority describe descending intensity. Business Call and Acceptable if Balanced describe a *type* of handling rather than a point on that intensity line — they tell the lawyer *how* to treat the issue, not just how hard to press. Do Not Spend Leverage is the floor: a deliberate decision not to raise the issue at all.

---

### Must Push

**Definition:** The term, as written, creates risk the client should not accept. It must change before signature — or the decision to proceed anyway must be made consciously by a senior decision-maker, not reached by default.

**When to use it:**
- The term hits a defined "never accept" line in the client's playbook or practice profile.
- The risk it creates is disproportionate to the value of the deal.
- The term may be unenforceable or may create regulatory exposure `[verify jurisdiction]`.
- The supervising attorney has confirmed the term cannot stand as drafted.

**What it implies for the lawyer:**
- Raise the issue as a requirement, not a preference.
- Do not let the contract move to signature with the term unresolved.
- If the counterparty will not move, escalate to a senior business decision-maker for a conscious accept-or-reject decision.
- Record the item in the Open Items section and the Attorney Verification Checklist.

**Communicating it to business stakeholders (sample language):**
> "This term has to change before we can sign. This is not a preference — as written, it exposes us to [describe the risk in concrete terms]. We will tell the counterparty it is a requirement. If they will not move, this needs a leadership decision about whether the deal is still worth doing on these terms."

---

### Strong Push

**Definition:** A material, one-sided term that creates real exposure. It is not a standalone deal-breaker, but the client should negotiate it hard and can realistically expect to improve it.

**When to use it:**
- The term allocates meaningful financial, operational, or legal risk against the client.
- Movement is realistically possible given the deal context and the client's leverage.
- The issue is material enough to justify spending negotiating capital.
- A clear preferred position and a defined fallback both exist.

**What it implies for the lawyer:**
- Raise it as a priority redline; lead with the preferred position.
- Press for the preferred position; accept the fallback only if the counterparty genuinely resists.
- Be prepared to trade for it against lower-rated items.
- Document the preferred and fallback positions in the issue list.

**Communicating it to business stakeholders (sample language):**
> "We should push hard on this one. It is a real imbalance and we have a good chance of improving it. Our opening ask is [preferred position]; if they push back, the least we should accept is [fallback]. Expect some back-and-forth — this is worth the effort."

---

### Business Call

**Definition:** The legal risk is real and has been explained, but whether to accept it is a commercial judgment that depends on business priorities — price, timing, the relationship, the available alternatives — not a pure legal question.

**When to use it:**
- The issue is a genuine tradeoff between legal risk and a business benefit.
- Legal can frame the risk and the options but does not own the decision.
- Reasonable decision-makers could go either way depending on the client's risk appetite.

**What it implies for the lawyer:**
- Present the risk and the realistic options neutrally — do not hide the recommendation, but make clear the decision belongs to the business.
- Give the business what it needs to decide: what the term means, what could go wrong, how likely it is, and what accepting or rejecting it costs.
- Record the business's decision and its rationale, so the basis for the call is documented.

**Communicating it to business stakeholders (sample language):**
> "Here is a tradeoff for you to decide. Legally, this term means [plain-language consequence]. The risk is [likelihood and impact]. Pushing back may cost us [time / goodwill / leverage elsewhere]. Whether it is worth accepting depends on how much you value [speed / price / this relationship]. We need you to make the call — and we will document it."

---

### Acceptable if Balanced

**Definition:** The concept of the term is fine; the problem is that it runs only one way. The term would be acceptable if it were made mutual, or paired with a corresponding protection.

**When to use it:**
- A one-sided clause whose substance is reasonable if it is reciprocal — for example, a one-way indemnity, audit right, termination right, or limitation that should cut both ways.
- The fix is symmetry or a balancing carve-out, not deletion or a fight over the substance of the clause.

**What it implies for the lawyer:**
- Ask for mutuality, or for the balancing protection, rather than challenging the clause itself — usually a low-friction request.
- If the counterparty makes the term balanced, treat the issue as resolved.
- If the counterparty refuses to balance it, re-rate the issue — often upward to Strong Push — and reassess.

**Communicating it to business stakeholders (sample language):**
> "We can live with this as long as it cuts both ways. Right now it only protects them. We will ask them to make it mutual — that is usually an easy fix. If they agree, no further concern. If they will not, we will come back to you, because a one-way version is a bigger problem."

---

### Low Priority

**Definition:** A minor imbalance or a suboptimal drafting point. Worth recording so the attorney and the client are aware of it, but not worth significant negotiating capital.

**When to use it:**
- The issue has limited practical or financial impact.
- The cost of raising it — time, goodwill, capital — is out of proportion to the gain.
- It may be worth raising only if it can be bundled cheaply, or in a high-value or high-stakes deal.

**What it implies for the lawyer:**
- Note it in the issue list at Low priority.
- Raise it only opportunistically — bundled with larger items, or if the counterparty is moving freely.
- Do not let it slow the deal or consume capital reserved for higher-rated items.

**Communicating it to business stakeholders (sample language):**
> "Minor point — we have flagged it for the record. It is not worth holding up the deal or spending leverage on. We may mention it if it is easy to fold into the larger discussion, but we will not fight for it."

---

### Do Not Spend Leverage

**Definition:** The term should not be raised. It is either genuinely balanced, or it reflects an entrenched counterparty position where the cost of asking — in capital or in signaling — outweighs any realistic gain.

**When to use it:**
- The term is balanced or unremarkable as a general drafting matter (characterize it, do not assert market data — see `skills/contracts/references/market-benchmark-framework.md`).
- The term sits in the counterparty's standard form and is one they consistently hold.
- Raising it would consume capital better spent on higher-rated issues, or would signal inexperience.

**What it implies for the lawyer:**
- Do not raise the issue in the negotiation.
- Preserve negotiating capital for Must Push and Strong Push items.
- Still record the term and the rating, so the decision not to raise it is deliberate and visible — "not raised" should be a choice, not an oversight.

**Communicating it to business stakeholders (sample language):**
> "We looked at this and recommend leaving it alone. It is either standard or something they will not move on, and raising it would burn goodwill we need for the issues that matter. We are flagging it so you know it was a deliberate call, not an oversight."

---

## Factors That Drive the Rating

A rating is not assigned mechanically. The reviewer considers each of the following factors and how they interact.

### 1. Relative Leverage

Which party needs this deal more? Which party has viable alternatives? The party with more alternatives has more leverage to push on hard terms. A client who is one of many customers of a large platform vendor has less leverage than a client representing a significant share of the counterparty's revenue. Leverage is deal-specific — the reviewer notes the apparent leverage position and flags it for attorney confirmation.

### 2. Who Drafted the Form

A term appearing in the reviewing party's own form can often be adjusted without counterparty resistance. A term appearing in the counterparty's standard form signals an entrenched position and raises the cost of negotiation. The form's origin pushes the rating toward Do Not Spend Leverage (entrenched form term) or away from it (the client's own form).

### 3. Deal Value and Strategic Importance

High-value or strategically important deals warrant spending more negotiating capital. A term that would be rated Low Priority on a routine small transaction may warrant a Strong Push on a large or strategic deal, where the client's leverage and incentive to spend effort are both higher.

### 4. Market Norms and Standard Practice

Whether a term deviates from what is typical for this contract type, transaction size, and industry affects whether the counterparty will engage. A genuine deviation from market norms is a more credible basis for a push than a request to improve an already-balanced term. Market-norm assessments must be verified — see `skills/contracts/references/market-benchmark-framework.md`.

### 5. Regulatory Floor

Some terms cannot be negotiated below a regulatory minimum: required data-processing provisions, mandatory breach-notification timelines, required disclosures. A term that hits a regulatory floor is not negotiable below that floor regardless of leverage or deal value `[verify jurisdiction]`. The reviewer notes when a floor may apply and flags it for attorney verification.

### 6. Insurance and Underwriting Constraints

Liability caps, indemnification limits, and some insurance-requirement terms may be constrained by the counterparty's insurance underwriting. If the counterparty's insurer requires a particular liability allocation, the counterparty may have limited ability to move even if it is willing. The reviewer notes this factor when it is apparent from the contract structure.

### 7. The Client's Own Position

If the client has a playbook or practice profile with defined preferred, acceptable, and unacceptable positions, the rating is calibrated against those positions. A term that falls within the client's acceptable range affects priority. A term that hits a "never accept" threshold is Must Push regardless of other factors.

### 8. Pattern and History

If the client has prior contracts with the same counterparty, or the attorney has experience with this counterparty's negotiation posture, that history informs the rating. A counterparty that has moved on a term before is more likely to move again.

---

## How to Apply the Framework

1. **Identify the issue** being rated and note its current posture in the draft (client-favorable, neutral, counterparty-favorable, or missing).

2. **Work through the factors** above. Not all factors are relevant to every issue. Note which factors are present and how they push the rating.

3. **Assign one of the six ratings.** Where factors point in different directions, flag the tension and note which factors are driving the rating.

4. **Record the basis.** The rating is only as useful as its explanation. A bare rating without reasoning is not actionable.

5. **Note confidence level.** If key factors are unknown — for example, the client's leverage has not been confirmed — note the uncertainty. A rating based on incomplete information should be flagged: `[CONFIRM: leverage position before finalizing rating]`.

6. **Flag for attorney review.** All negotiability ratings are draft assessments. The attorney confirms strategy, adjusts for factors the reviewer cannot observe, and decides which issues to raise and in what order.

---

## Recording a Rating

When recording a negotiability rating in an issue list, a negotiability table, or a risk matrix, use the following pattern:

```
Issue:               [clause name or topic]
Current posture:     [counterparty-favorable / neutral / missing]
Negotiability:       [Must Push / Strong Push / Business Call /
                      Acceptable if Balanced / Low Priority /
                      Do Not Spend Leverage]
Basis:               [one to two sentences identifying the key factors]
Preferred position:  [what the client wants]
Fallback position:   [what the client would accept]
Attorney note:       [CONFIRM: ...] or [ATTORNEY TO CONFIRM: ...]
```

See `skills/contracts/references/redline-output-guidance.md` for guidance on expressing preferred and fallback positions, and `skills/contracts/references/fallback-language-bank.md` for sample fallback positions by clause type.

---

## Negotiability Rating and Issue Priority

The negotiability rating answers a different question from the issue's **priority** rating (High / Medium / Low), which the contract skills use in the risk matrix and issue list to reflect the *materiality* of the risk.

- **Priority** measures how much the issue matters — the size of the risk to the client.
- **Negotiability** measures how the lawyer should handle the issue — how hard to push, and in what manner.

The two interact, and the negotiability rating already absorbs much of the priority judgment:

- A **Must Push** issue is, by definition, High priority — and the negotiability rating tells the attorney that movement is required, not merely desirable.
- A **Strong Push** issue is typically High or Medium priority, with realistic prospects of movement.
- A **Business Call** can sit at any priority level; the rating signals that the *decision*, not the priority, is the open question.
- **Low Priority** and **Do Not Spend Leverage** both signal the issue is not worth significant capital — Low Priority leaves the door open to raise it opportunistically, while Do Not Spend Leverage recommends not raising it at all.

Record both the priority rating and the negotiability rating for each material issue. Together they tell the attorney what matters and what to do about it. See `skills/contracts/contract-risk-review/SKILL.md` for the priority rating definitions used in the issue list.

=== END AGENTCOUNSEL MODULE: negotiability-ratings ===

=== BEGIN AGENTCOUNSEL MODULE: market-benchmark-framework ===
Kind: reference
Canonical path: skills/contracts/references/market-benchmark-framework.md
Load when: deep-review mode or when market practice is requested

> Shared reference material supporting the AgentCounsel contracts skills, used to help produce draft legal work product for attorney review — not legal advice.

# Market Benchmark Framework

This framework gives a reviewer a disciplined method for recording how a contract term compares to market norms, citing the basis for any benchmark observation, and flagging every unverified benchmark for attorney confirmation.

**AgentCounsel does not supply market data.** This library contains no percentages, no assertions of what terms are "typically" offered, and no claims about what the market "standard" is for any clause. Every benchmark observation in a deliverable must come from a source the attorney can verify — and every such observation is an attorney-verification item until confirmed.

An unverified benchmark is more dangerous than no benchmark. A fabricated or unconfirmed market-data assertion can lead an attorney or client to make a negotiating decision on a false premise. This framework exists to ensure that any benchmark used in a review is clearly sourced, clearly qualified, and clearly flagged for confirmation.

---

## Why Market Benchmarks Are Attorney-Verification Items

Market norms for contract terms vary by:

- **Industry and sector** — what is typical in technology services differs from what is typical in construction, financial services, or life sciences.
- **Transaction type** — MSA terms differ from SaaS subscription terms, which differ from one-time professional services engagements.
- **Transaction size and deal value** — large-enterprise terms differ from mid-market or SMB terms.
- **Geography and governing law** — norms differ across jurisdictions `[verify jurisdiction]`.
- **Time** — what was standard practice several years ago may not reflect current market expectations.
- **Counterparty type** — terms offered by a large platform vendor differ from those offered by a boutique professional services firm.
- **Relative leverage** — "market standard" often means "what the party with more leverage typically gets."

An agent cannot verify any of these variables from a contract document alone. Only the attorney, drawing on active practice experience and current knowledge of the relevant market segment, can assess whether a benchmark observation is accurate for the specific deal.

---

## Permitted Sources for Benchmark Observations

A benchmark observation may only be recorded if it can be attributed to one of the following:

### Source 1: The Client's Practice Profile or Playbook

The client's own standard positions, as provided by the attorney or reflected in the client's supplied template, playbook, or prior agreements. Observations from this source describe what the client's standard is — not what "the market" is. Record as: _"Client's playbook [specify source] provides for [term]. The reviewed contract departs from client's standard in the following way: [description]."_

### Source 2: Attorney-Provided Comparables

Comparable contract terms specifically identified by the supervising attorney or the client as representative of market practice for this type of deal. Record as: _"Attorney-provided comparable [specify, e.g., 'prior agreement with similar vendor supplied by client'] contains [term]. The reviewed contract [matches / departs from] this comparable in the following way: [description]."_

### Source 3: The Counterparty's Own Prior Forms

Where the client has a prior contract with the same counterparty, or has obtained a prior version of the counterparty's standard form, terms from that prior form are a benchmark for what the counterparty has historically offered. Record as: _"Counterparty's prior form [specify source] contained [term]. The reviewed contract [matches / departs from / is more restrictive than] the counterparty's prior form in the following way: [description]."_

### Source 4: Industry Norms Supplied by the Attorney

The attorney identifies specific industry norms applicable to this deal, drawing on active practice knowledge for this sector, transaction type, and deal size. The attorney must supply the norm — the agent records and flags it. Record as: _"Attorney-supplied industry norm for [sector / transaction type]: [description of norm]. Flagged for attorney confirmation."_

---

## Prohibited Assertions

The following assertions must never appear in a deliverable produced using this framework:

- "Market standard is [X]."
- "It is typical for [clause] to be [Y]."
- "[X]% of contracts in this sector include [term]."
- "Most vendors accept [Y] on [term]."
- "Industry practice requires [Z]."
- Any percentage, frequency, or statistical claim about market practice.
- Any assertion about what a counterparty "usually" offers or "would normally" accept.

If a benchmark observation cannot be sourced to one of the four permitted sources above, it must not appear in the deliverable. Record an open item instead: `[ATTORNEY TO CONFIRM: market norm for [clause/term] in [transaction type] — no verified benchmark available]`.

---

## A Controlled Vocabulary for Characterizing Terms

A reviewer often needs to give the attorney a sense of *how a term reads* without asserting market data the reviewer cannot supply. The five characterizations below are the permitted way to do that. They replace prohibited statements like "market standard is X" with a qualitative, clearly-labeled impression.

**These five labels are general drafting heuristics.** They reflect a reviewer's qualitative impression of how a clause is constructed — not a measured or verified market position. They become reliable benchmarks **only** when supported by one of the four permitted sources above: a provided client playbook, attorney-provided comparables, the counterparty's prior form, or an attorney-supplied industry norm. Used on their own, every one of these characterizations is an attorney-verification item.

Use exactly one of these labels for any term the reviewer characterizes:

### Common

The clause follows a familiar, frequently-seen drafting pattern for this contract type. "Common" is **not** a claim that the term is "market standard," nor that any particular share of contracts use it. It means only this: the construction is unremarkable, and a reviewer would not be surprised to encounter it. A Common term may still carry real risk for the client — see "Benchmark Observations vs. Risk Ratings" below.

### Aggressive

The clause follows a recognizable pattern but is drafted notably toward one party — typically the drafting party. It is a familiar construction sitting at the one-sided end of the range. Always state which party it favors.

### Unusual

The clause departs from familiar drafting patterns. The reviewer has not commonly seen this construction, or it combines terms in an unexpected way. "Unusual" is a prompt for close attention and explanation — it does not by itself mean the term is unacceptable, but it warrants attorney scrutiny.

### Depends on Leverage

Whether the term reads as ordinary or as one-sided genuinely turns on the parties' relative bargaining power and cannot be characterized without knowing it. Many liability, indemnity, exclusivity, and pricing terms fall here. Record what is known about leverage and flag the gap.

### Needs Attorney Confirmation

The reviewer cannot characterize the term against any reference point — there is no playbook position, no comparable, no counterparty prior form, and the reviewer has no basis to call the term Common, Aggressive, or Unusual. The attorney must supply the market read. This is the correct default whenever the reviewer is uncertain; do not guess at one of the other four labels to avoid using this one.

### Recording a characterization

```
Clause / Term:        [name of the clause or issue]
Characterization:     [Common / Aggressive / Unusual /
                       Depends on Leverage / Needs Attorney Confirmation]
Basis:                [why the reviewer chose this label]
Supporting source:    [client playbook / attorney comparable /
                       counterparty prior form / attorney-supplied norm /
                       NONE — drafting heuristic only]
Verification status:  [UNVERIFIED — attorney confirmation required]
                      OR [CONFIRMED by: (attorney / playbook / comparables)]
```

When the supporting source is NONE, the characterization is a drafting heuristic only and must be flagged: `[ATTORNEY TO CONFIRM: characterization of [term] as "[label]" is a drafting heuristic, not verified market data — confirm against current market practice for [transaction type / sector / deal size]]`.

These characterizations are the vocabulary used in the **Market Practice Notes** output section of the contracts skills.

---

## How to Record a Benchmark Observation

Every benchmark observation in a deliverable must follow this structure:

```
Benchmark Observation
Clause / Term:        [name of the clause or issue]
Observed term:        [what the reviewed contract says, quoted or precisely described]
Benchmark source:     [one of the four permitted sources; identify the specific source]
Benchmark position:   [what the benchmark source says about this term]
Deviation:            [how the reviewed contract departs from the benchmark, if at all]
Verification status:  [UNVERIFIED — attorney confirmation required]
                      OR [CONFIRMED by: (attorney / playbook / comparables)]
```

All benchmark observations are marked UNVERIFIED until the supervising attorney confirms them.

---

## Flagging Unverified Benchmarks

Every unverified benchmark in a deliverable must be flagged as an open item. Use the following placeholder form:

`[ATTORNEY TO CONFIRM: benchmark for [clause] — basis is [source]; confirm whether this reflects current market practice for [transaction type / sector / deal size]]`

Do not omit the source basis in the placeholder. A bare `[verify]` tag is not sufficient; the attorney needs to know what assertion is being flagged and what the claimed source is.

---

## Benchmark Observations vs. Risk Ratings

A benchmark observation describes how a term compares to a reference point. A risk rating (High / Medium / Low in the risk matrix) describes the risk to the client. These are distinct assessments:

- A term can depart significantly from a benchmark but pose low risk to the client (e.g., a client-favorable deviation).
- A term can be consistent with a benchmark but still pose meaningful risk to the client (e.g., a term that is "typical" but still creates genuine exposure).

Do not conflate "consistent with market" with "acceptable risk." The risk assessment belongs to the attorney. The benchmark observation is one input to that assessment.

---

## Benchmark Observations in the Risk Matrix

When recording a benchmark observation in the risk matrix (see `skills/contracts/contract-risk-review/templates/contract-risk-matrix.md`), the Attorney Note column is the appropriate place to record the observation and its verification status. Example:

> Attorney Note: _Liability cap formula departs from client playbook standard (12-month fees; playbook calls for 24-month minimum). No external market benchmark available. `[ATTORNEY TO CONFIRM: whether 12-month cap is acceptable for this transaction type and deal value]`_

---

## A Note on "Market Standard" Claims in the Contract Itself

Counterparties sometimes include language in their agreements asserting that a term is "market standard," "industry standard," or "customary." These assertions are counterparty representations — they are not independently verified benchmarks. When such language appears in a reviewed contract, note it as a counterparty claim and flag it for attorney verification: `[ATTORNEY TO CONFIRM: counterparty's "market standard" assertion for [term] — independent verification required]`.

=== END AGENTCOUNSEL MODULE: market-benchmark-framework ===

=== BEGIN AGENTCOUNSEL MODULE: contracts-practice-profile ===
Kind: profile
Canonical path: practice-profiles/contracts.md
Load when: a populated and attorney-approved contracts profile is available

> **Internal practice-group configuration reference. This is not legal work product and is not legal advice.** This profile configures AI agent behavior for this practice group. It must be maintained and approved by a supervising attorney before use. This file must NOT contain privileged or client-sensitive facts. Source-of-truth documents are referenced by name and location only — never pasted in.

# Practice Profile: Contracts

## Profile Information

| Field | Value |
|---|---|
| Practice Group | Contracts |
| Profile Owner | `[CONFIRM: name and title of profile owner]` |
| Approving Attorney | `[CONFIRM: name and bar number of approving attorney]` |
| Last Reviewed Date | `[CONFIRM: date of last attorney review]` |
| Version | `[CONFIRM: version number, e.g., 1.0]` |

---

## Jurisdictions

Identify every jurisdiction, governing-law regime, and forum in which this group regularly works. Agents will gate jurisdiction-specific analysis on this list and flag anything outside it for attorney escalation.

| Field | Value |
|---|---|
| Primary Jurisdictions | `[CONFIRM: e.g., state/province, country]` |
| Secondary / Occasional Jurisdictions | `[CONFIRM: list or "none at this time"]` |
| Default Governing Law | `[CONFIRM: preferred governing-law clause, or "counterparty-dependent"]` |
| Preferred Dispute-Resolution Forum | `[CONFIRM: e.g., courts of a specified jurisdiction, arbitration body]` |
| International / Cross-Border Work | `[CONFIRM: yes/no; if yes, list regimes and any export-control considerations]` |

**Guiding prompts for this section:**
- What governing-law clause does the group prefer to propose as a starting position?
- In which jurisdictions does the group regularly enforce or defend contractual claims?
- Are there forum-selection clauses the group treats as standard or as automatic deal points?
- Does the group work on agreements subject to cross-border transfer restrictions or international arbitration rules?

---

## Client / Team Context

Describe who this group serves and how it is organized. Agents use this section to understand escalation paths and supervision structure.

| Field | Value |
|---|---|
| Internal Clients Served | `[CONFIRM: e.g., business units, product teams, procurement]` |
| External Client Types | `[CONFIRM: e.g., enterprise SaaS vendors, Fortune 500 buyers, startups]` |
| Team Composition | `[CONFIRM: partners, senior associates, associates, paralegals, contract managers]` |
| Supervising Attorney(s) | `[CONFIRM: name(s) with oversight responsibility for AI-assisted work]` |
| Matter-Intake Process | `[CONFIRM: how matters reach the group — ticketing system, direct request, etc.]` |

**Guiding prompts for this section:**
- Who is the primary internal or external client this group supports?
- Who is the designated supervising attorney for AI-assisted contract review or drafting?
- Does the group use a contract management system, intake form, or matter-management platform?

---

## Escalation Thresholds

Define the conditions under which an agent must stop autonomous work and route to a human reviewer. Agents treat these thresholds as hard stops.

| Trigger | Threshold / Description | Route To |
|---|---|---|
| Contract value | `[CONFIRM: e.g., above $[X], escalate to partner]` | `[CONFIRM: role or name]` |
| Liability cap below floor | `[CONFIRM: e.g., cap less than [X] months' fees or $[X] total]` | `[CONFIRM: role or name]` |
| Uncapped liability clause | `[CONFIRM: escalate any agreement with no liability cap]` | `[CONFIRM: role or name]` |
| Auto-renewal clause present | `[CONFIRM: flag for attorney review or client instruction]` | `[CONFIRM: role or name]` |
| IP assignment affecting core assets | `[CONFIRM: any assignment of patents, trademarks, or platform IP]` | `[CONFIRM: role or name]` |
| Indemnification — one-sided or uncapped | `[CONFIRM: escalation criteria]` | `[CONFIRM: role or name]` |
| Counterparty is a government entity | `[CONFIRM: always escalate / apply special review]` | `[CONFIRM: role or name]` |
| Non-standard dispute resolution | `[CONFIRM: e.g., mandatory arbitration in unfamiliar forum]` | `[CONFIRM: role or name]` |
| Any clause outside known playbook | `[CONFIRM: agent flags and pauses rather than improvising]` | `[CONFIRM: role or name]` |

**Guiding prompts for this section:**
- At what dollar value does a contract require partner or senior-attorney sign-off?
- Does the group have a minimum acceptable liability cap expressed as a dollar figure or a multiple of fees?
- Are auto-renewal clauses a standing concern requiring client notification before they trigger?
- What indemnification structures are outside the group's standard playbook and require escalation?

---

## Preferred Output Style

Specify the format, tone, and length conventions agents must follow when producing deliverables for this group.

| Preference | Setting |
|---|---|
| Deliverable format | `[CONFIRM: e.g., tabular risk matrix, memo, redline markup, clause-by-clause summary]` |
| Tone | `[CONFIRM: e.g., plain business language, formal legal prose]` |
| Length convention | `[CONFIRM: e.g., executive summary ≤ 1 page + full matrix; no single-section limit]` |
| Heading style | `[CONFIRM: e.g., numbered sections, H2/H3 Markdown]` |
| Risk-rating scheme | `[CONFIRM: e.g., High / Medium / Low aligned with contract-risk-matrix template]` |
| Redline conventions | `[CONFIRM: e.g., track-changes Word, Markdown strikethrough/insertion, inline annotations]` |
| Privilege designation line | `[CONFIRM: e.g., "Privileged and Confidential — Attorney Work Product"]` |

**Guiding prompts for this section:**
- Do clients expect a one-page executive summary or a full clause-by-clause walkthrough?
- Does the group use a standard risk-rating scheme that agents should align with?
- How should agents present redline suggestions — narrative, table, or markup?

---

## Source-of-Truth Documents

List the authoritative playbooks, templates, clause libraries, and reference materials this group uses. Reference by name and location only. Do not paste content here.

| Document | Location / Path | Notes |
|---|---|---|
| Standard contract-review playbook | `[CONFIRM: file name and location, e.g., internal drive path or system name]` | `[CONFIRM: version or last-updated date]` |
| Approved clause library | `[CONFIRM: file name and location]` | `[CONFIRM: version or last-updated date]` |
| NDA template (inbound) | `[CONFIRM: file name and location]` | |
| NDA template (outbound) | `[CONFIRM: file name and location]` | |
| MSA template | `[CONFIRM: file name and location]` | |
| SaaS / subscription agreement template | `[CONFIRM: file name and location]` | |
| Signature authority / approval matrix | `[CONFIRM: file name and location]` | |
| Contract risk matrix template | `skills/contracts/contract-risk-review/templates/contract-risk-matrix.md` | Canonical AgentCounsel template |

**Guiding prompts for this section:**
- Where does the group store its approved templates and clause fallbacks?
- Is there a playbook document that defines the group's standard positions for common clauses?
- What contract management system holds executed agreements?

---

## Standard Positions / Playbooks

Record the group's default negotiating positions for key contract terms. These are starting positions — an agent uses them to flag deviations but always defers final judgment to an attorney.

| Clause | Group's Default Position | Notes / Conditions |
|---|---|---|
| Governing law | `[CONFIRM: preferred jurisdiction]` | `[CONFIRM: when to accept counterparty's law]` |
| Limitation of liability — cap amount | `[CONFIRM: e.g., greater of total fees paid or $[X]]` | `[CONFIRM: when a lower cap is acceptable]` |
| Limitation of liability — consequential damages | `[CONFIRM: e.g., mutual exclusion with named carve-outs]` | `[CONFIRM: required carve-outs, e.g., IP indemnity, fraud, data breach]` |
| Indemnification — IP infringement | `[CONFIRM: e.g., mutual; each party indemnifies for its own IP]` | |
| Indemnification — data breach | `[CONFIRM: group's standard position]` | |
| Auto-renewal | `[CONFIRM: e.g., oppose; require affirmative renewal or minimum notice window]` | `[CONFIRM: minimum acceptable notice period]` |
| Term / initial contract duration | `[CONFIRM: preferred initial term length]` | |
| Termination for convenience | `[CONFIRM: e.g., require mutual right; minimum notice period]` | |
| Assignment / change of control | `[CONFIRM: e.g., require consent for assignment; termination right on change of control]` | |
| Confidentiality duration | `[CONFIRM: minimum post-termination confidentiality period]` | |
| Dispute resolution | `[CONFIRM: preferred mechanism — litigation, arbitration, mediation first]` | |

**Guiding prompts for this section:**
- What is the group's floor for a liability cap as a multiple of fees or an absolute dollar amount?
- Which carve-outs from the consequential-damages exclusion does the group always seek?
- Does the group have a standing position on auto-renewal notice windows?
- What governing-law clauses does the group accept from counterparties without escalation?

---

## Attorney Review Requirements

Specify what must be reviewed by a qualified attorney before any deliverable produced with this profile is used, sent, or relied upon.

| Deliverable Type | Required Reviewer | Conditions |
|---|---|---|
| Contract risk matrix or review memo | `[CONFIRM: e.g., supervising associate or partner]` | All; no exceptions |
| Redline or draft contract | `[CONFIRM: role]` | All; no exceptions |
| Clause library addition or update | `[CONFIRM: role]` | Requires written approval |
| Playbook update | `[CONFIRM: role]` | Requires written approval and version increment |
| Executed-agreement summary | `[CONFIRM: role]` | `[CONFIRM: before distribution to business?]` |
| Any output touching an uncapped liability or IP assignment | Partner-level review | Always |

**Guiding prompts for this section:**
- Is there a tiered review structure (associate drafts, partner approves) for different contract values?
- Which deliverables can be reviewed by a senior associate without partner sign-off?
- Does the group require countersignature by a second attorney for agreements above a certain value?

---

## Prohibited Assumptions

List what an agent must never assume and must always confirm with a human before proceeding.

| Item | Why It Cannot Be Assumed |
|---|---|
| Governing law is the group's preferred jurisdiction | Counterparty's form may specify a different law; must be confirmed |
| Liability cap meets the group's floor | Cap amount and basis must be read from the actual agreement |
| Auto-renewal clause is absent | Must be confirmed by reading every agreement; do not assume it is absent |
| Indemnification is mutual | One-sided indemnification is common; must be confirmed |
| Prior version of an agreement reflects current terms | Only the version provided for review controls |
| A standard-form agreement is unchanged from the template | Counterparties modify forms; read the actual document |
| Client entity name and authorized signatory are correct | Must be confirmed against authoritative records |
| Signature authority has been obtained | Approval matrix must be consulted for each agreement |
| `[CONFIRM: any additional group-specific prohibited assumption]` | `[CONFIRM: reason]` |

---

## How to Populate This Profile

Complete every bracketed placeholder with information specific to this practice group. Have a supervising attorney review and approve the completed profile before it is loaded alongside any skill.

For a guided, question-by-question setup process, use the cold-start interview skill at `skills/setup/contracts-cold-start-interview/SKILL.md`. That skill walks through each section of this profile and produces a draft-completed version for attorney review.

Do not include client names, matter numbers, confidential facts, or privileged analysis in this profile. This is a configuration document, not a work-product file.

=== END AGENTCOUNSEL MODULE: contracts-practice-profile ===
=== END AGENTCOUNSEL EXECUTION PACKAGE ===

First, confirm which Required Inputs you have and ask me for any that are missing. Then proceed with the Workflow.