review-a-contract

review-a-contract is a skill for Claude Code, Codex from akiotanaka847/qaio-desktop. It costs 68 tokens per session (2,058 once invoked), scanned A, original, MIT.

A contract-reading tool that explains an agreement in plain language and flags clauses that need attention. An NDA is a confidentiality agreement; an MSA is a master services agreement that sets the main terms for ongoing customer work.

In plain words
What is it for?
Use it to review MSAs, data-processing agreements, order forms, and NDAs for terms such as renewal, termination, liability, indemnity, intellectual property, governing law, data handling, and exit rights.
Why use it?
It helps you understand what another party is asking you to accept before signing, without guessing about clauses that are not present. Depending on the mode, it gives a risk verdict, a quick NDA check, or an organised clause map without a verdict.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents).

Good fit Use it to review MSAs, data-processing agreements, order forms, and NDAs for terms such as renewal, termination, liability, indemnity, intellectual property, governing law, data handling, and exit rights.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/akiotanaka847/qaio-desktop/review-a-contract
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add akiotanaka847/qaio-desktop --skill review-a-contract
Clone the repo
git clone --depth 1 https://github.com/akiotanaka847/qaio-desktop

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for review-a-contract

README.md
[![agentmods](https://agentmods.dev/badge/skills/akiotanaka847/qaio-desktop/review-a-contract/github.svg)](https://agentmods.dev/skills/akiotanaka847/qaio-desktop/review-a-contract)
Your own site
<a href="https://agentmods.dev/skills/akiotanaka847/qaio-desktop/review-a-contract"><img src="https://agentmods.dev/badge/skills/akiotanaka847/qaio-desktop/review-a-contract/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for review-a-contract

Your own site · 80×15
<a href="https://agentmods.dev/skills/akiotanaka847/qaio-desktop/review-a-contract"><img src="https://agentmods.dev/badge/skills/akiotanaka847/qaio-desktop/review-a-contract.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 68 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,058 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00068 $0.02058
Opus 5 $0.00034 $0.01029
Sonnet 5 $0.00014 $0.00412
Haiku 4.5 $0.00007 $0.00206

Measured 11d ago against content hash 88c0ae71a3a7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

review-a-contract scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

store/agents/legal/.agents/skills/review-a-contract/SKILL.md · 96 lines

How it starts

The opening of the file, as written. The whole thing — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Review a Contract

One skill for first-read of counterparty contract. mode pick depth. Structured clause extraction + "never invent clause-standard can't cite" discipline shared.

Parameter: mode

  • full - full MSA / DPA / order-form review: clause map + Green (accept) / Yellow (pushback OK) / Red (redline required) verdict per clause + plain-English summary + accept / redline / walk rec. Writes to contract-reviews/{counterparty}-{YYYY-MM-DD}.md.
  • nda-traffic-light - fast 6-dimension rubric for inbound NDAs (term, mutuality, confidential-info definition, carve-outs, jurisdiction, non-solicit smuggling, return/destruction). Writes to ndas/{counterparty-slug}-{YYYY-MM-DD}.md with specific redlines on every Red item.
  • clauses-only - structured extraction, no verdict. Reads supplied contract (file / URL / paste), extracts clauses that matter (term, termination, renewal, liability cap, indemnity, IP, governing law, DPA, AI training, data residency, exit rights), writes human-readable map to clause-extracts/{counterparty}-{YYYY-MM-DD}.md, updates counterparty-tracker.json with key fields.

User name mode in plain English ("traffic-light this", "just extract the clauses", "full review with a verdict") → infer. Ambiguous → ask ONE question naming 3 options.

When to use

  • Explicit: "review this contract", "traffic-light this NDA", "is this signable?", "what's in this agreement", "extract clauses".
  • Plain-English asks map to a mode: "fully review this customer contract / MSA" / "is this MSA safe to sign" → full; "quick check on this NDA" / "is this NDA OK to sign" → nda-traffic-light; "just lay out the clauses" / "pull out the clauses, no verdict" / "review the IP clause" (run full and lead with the IP section) → clauses-only or full with IP focus.
  • Implicit: called by sort-my-legal-inbox when detects MSA / NDA / DPA and routes to review. Chained into plan-contract-pushback when output has any Red items.

Ledger fields I read

Read the full file on GitHub · 96 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 11d ago First seen · 96 lines · 68 tokens per session scan A 88c0ae71a3a7

Subscribe to this mod's changes

review-a-contract is a skill published in the GitHub repository akiotanaka847/qaio-desktop (2 stars, last pushed 8d ago), licensed MIT. It adds 68 tokens to every session and 2,058 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

contracts

Use when drafting or reviewing business contracts and clauses in plain language — NDAs, MSAs, SOWs, contractor agreements, risk boilerplate (liability caps, indemnity, force majeure, termination, IP) — or redlining a counterparty's paper. NOT consumer Terms of Service (that is terms-conditions) and NOT the signing…

ericrisco/rsc-harness · 80 tokens

lawyer-expert

Expert-level legal systems, contracts, compliance, and legal technology. Use when the user mentions legal, contracts, compliance, law, or legal tech, or when the task involves Legal Systems, Legal Technology, Compliance Frameworks, or Contract Management.

personamanagmentlayer/pcl · 54 tokens

legaltech-expert

Expert in legal technology: contract lifecycle management, e-discovery, AI-assisted legal research, case and matter management, document automation, and compliance tooling. Use when the user mentions legal case or matter management, e-discovery and legal holds, CLM or contract review and obligation tracking, legal…

personamanagmentlayer/pcl · 74 tokens

Contract Drafter

Generate legal contracts from templates with variable substitution and clause management.

eddiebelaval/squire · 15 tokens

Contract Risk Review

Use when reviewing a general commercial contract — such as a master services agreement, vendor agreement, supplier contract, or professional services agreement — to produce a structured risk assessment and prioritized issue list for attorney review.

zgbrenner/agentcounsel · 44 tokens

NDA Review

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.

zgbrenner/agentcounsel · 42 tokens