contract-review

contract-review is a skill for Claude Code from aAAaqwq/AGI-Super-Team. It costs 50 tokens per session (3,510 once invoked), scanned A, original, MIT.

A contract-review tool that examines legal agreements for important terms, missing information, and possible risks. It supports documents such as NDAs, software agreements, mergers, employment contracts, and payment agreements, but its output is not legal advice.

In plain words
What is it for?
Use it to extract contract terms, flag risk categories, compare wording with common market practices, and suggest redlines, which are proposed text changes.
Why use it?
Contracts can contain hidden obligations, blank fields, missing attachments, or risky clauses that are easy to overlook. Reviewing these items before signing helps identify questions and possible changes for a lawyer to assess.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Part of the agi-super-team plugin — 194 skills, 1 agent shipped together

Good fit Use it to extract contract terms, flag risk categories, compare wording with common market practices, and suggest redlines, which are proposed text changes.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/aaaaqwq/agi-super-team/contract-review
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 aAAaqwq/AGI-Super-Team --skill contract-review
Clone the repo
git clone --depth 1 https://github.com/aAAaqwq/AGI-Super-Team

Made for: Claude Code.

Or install agi-super-team, the plugin that ships this one along with the rest of its 194 skills, 1 agent.

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 contract-review

README.md
[![agentmods](https://agentmods.dev/badge/skills/aaaaqwq/agi-super-team/contract-review/github.svg)](https://agentmods.dev/skills/aaaaqwq/agi-super-team/contract-review)
Your own site
<a href="https://agentmods.dev/skills/aaaaqwq/agi-super-team/contract-review"><img src="https://agentmods.dev/badge/skills/aaaaqwq/agi-super-team/contract-review/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 contract-review

Your own site · 80×15
<a href="https://agentmods.dev/skills/aaaaqwq/agi-super-team/contract-review"><img src="https://agentmods.dev/badge/skills/aaaaqwq/agi-super-team/contract-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 50 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,510 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00050 $0.03510
Opus 5 $0.00025 $0.01755
Sonnet 5 $0.00010 $0.00702
Haiku 4.5 $0.00005 $0.00351

Measured 7d ago against content hash 06cf0af5efe5, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

contract-review 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 7d 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.

skills/contract-review/SKILL.md · 449 lines

How it starts

The opening of the file, as written. The whole thing — 449 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Contract Review

Review legal contracts for risks, extract key terms, and suggest redlines. Built on the CUAD dataset (41 risk categories), ContractEval benchmarks, and LegalBench.

Disclaimer: This skill provides informational analysis only. It is not legal advice. Material terms should be reviewed by qualified legal counsel before signing.

When to Activate

  • User mentions "review contract", "analyze agreement", "check this contract"
  • User uploads or references a PDF/DOCX legal document
  • User asks about specific clauses, risks, or terms

Step 1: Pre-Review Checklist

Before analyzing content, verify document completeness:

  • Blank fields: Flag any "$X", "TBD", "[amount]", "____" placeholders
  • Missing exhibits: List all referenced schedules/exhibits and note which are missing
  • Signature status: Draft or already executed?
  • All pages present: Check for truncation or missing sections

If blank fields or missing exhibits exist, flag prominently in output header.


Step 2: Identify Document Type & User Position

Ask if unclear: "Which party are you? (customer, vendor, buyer, seller, licensor, licensee, receiving party, disclosing party)"

This affects what's "risky":

  • Customer reviewing vendor agreement: flag vendor-favorable terms
  • Vendor reviewing own template: flag customer-favorable terms
  • Buyer in M&A: flag seller-favorable terms
  • Seller in M&A: flag buyer-favorable terms
  • Receiving party in NDA: flag disclosing party-favorable terms

Assess power dynamic:

  • Startup vs. large enterprise? (limited negotiating leverage)
  • Standard form vs. negotiated? (some terms non-negotiable)
  • Regulated industry? (some terms legally required)

Output Format

Use markdown for readable, scannable output.


Example Output

# Contract Review: [Document Name]

**Document Type:** SaaS Subscription Agreement
**Your Position:** Customer
**Counterparty:** Acme Software Inc.
**Risk Level:** Medium
**Document Status:** Draft / Executed on [date]

## Pre-Signing Alerts

- **Blank field:** Fee amount in Section 4.1 is "$____"
- **Missing exhibit:** Exhibit B (SLA) referenced but not attached

## Executive Summary

Standard vendor agreement with some one-sided terms. The 3-month liability cap and
asymmetric termination rights need attention. Data ownership is clear.

---

## Key Terms

| Term | Value | Location |
|------|-------|----------|
| Initial Term | 12 months | Section 8.1 |
| Auto-Renewal | 12-month periods, 60-day notice | Section 8.2 |
| Liability Cap | 3 months' fees | Section 10.2 |
| Governing Law | Delaware | Section 12.1 |

---

## Red Flags (Quick Scan)

| Flag | Found | Location |
|------|-------|----------|
| Liability cap < 6 months | Yes | Section 10.2 |
| Uncapped indemnification | No | -- |
| Unilateral amendment rights | Yes | Section 14.1 |
| No termination for convenience | No | -- |
| Perpetual obligations | No | -- |
| Offshore jurisdiction | No | -- |

---

## Risk Analysis

### Critical

**Limitation of Liability** (Section 10.2)
> "Liability shall not exceed fees paid in the preceding three (3) months"

- **Issue:** 3-month cap is below market standard (typically 12 months)
- **Risk:** For $120K annual contract, liability capped at $30K
- **Market Standard:** 12 months' fees
- **Negotiability:** Medium -- most vendors accept 6-12 months
- **Redline:** Change "three (3) months" to "twelve (12) months"
- **Fallback:** Accept 6 months as compromise

---

### Important

**Termination for Convenience** (Section 8.5)
> "Vendor may terminate for any reason upon 30 days notice"

- **Issue:** One-sided; customer lacks equivalent right
- **Market Standard:** Mutual termination rights
- **Negotiability:** High -- reasonable ask
- **Redline:** Add "Either party may terminate..." or change to "90 days"

---

### Reviewed & Acceptable

| Category | Status | Notes |
|----------|--------|-------|
| Data Ownership | OK | Customer owns all customer data |
| IP Rights | OK | Clear separation, no broad assignment |
| Confidentiality | OK | Mutual, 3-year term, standard exceptions |
| Governing Law | OK | Delaware -- neutral for commercial |

---

## Missing Provisions

| Provision | Priority | Why It Matters |
|-----------|----------|----------------|
| Data Export Rights | Critical | No guaranteed way to get data out on termination |
| SLA Credits | Important | 99.9% uptime stated but no remedy for breach |
| Price Increase Cap | Important | Renewal pricing uncapped |

**Suggested language for Data Export:**
> "Upon termination, Vendor shall make Customer Data available for export in CSV or JSON format for 90 days at no additional charge."

---

## Internal Consistency Issues

- Section 5.2 references "Exhibit C" but no Exhibit C exists
- "Confidential Information" defined in Section 3.1 but used lowercase in Section 7

---

## Negotiation Priority

| # | Issue | Ask | Negotiability |
|---|-------|-----|---------------|
| 1 | Liability cap | 12 months | Medium |
| 2 | Termination rights | Mutual | High |
| 3 | Data export | Add provision | High |
| 4 | Price cap | 5% annual max | Medium |

---

*This review is for informational purposes only. Material terms should be reviewed by qualified legal counsel.*

Read the full file on GitHub · 449 lines

Files

What ships with it

2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 7d ago First seen · 449 lines · 50 tokens per session scan A 06cf0af5efe5

Subscribe to this mod's changes

contract-review is a skill published in the GitHub repository aAAaqwq/AGI-Super-Team (92 stars, last pushed yesterday), licensed MIT. It adds 50 tokens to every session and 3,510 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 2026-09-05.

Related

Other skills, from other repositories

generate-fillable-contract-html

A generator for Chinese HTML templates with fill-in fields for contracts, quotations, and authorization letters. The fields are marked so a later HTML-to-Word conversion can identify and fill them.

rojim666/SztuCode · 52 tokens

contract-drafter

Draft a contract from a versioned template with explicit parties and terms, reconciling every clause against the rendered baseline deterministically and keeping delivery behind a human gate.

runxhq/runx · 38 tokens

ai-legal-document-generation

AI legal document generation powered by CellCog. Contracts, NDAs, terms of service, privacy policies, freelance agreements, employment contracts, compliance reviews, legal research. Precision legal drafting from natural language prompts. Not legal advice.

rondoflow/rondoflow · 51 tokens

go-guide

Adds a new conceptual guide to a project's knowledge folder. Runs in three modes: interactive (user-invoked), from-task (auto-invoked from ship-first after a fast-track completes), from-epic (from epic closure). Storage: local .md file under project-knowledge/guides/{topic}/, registered via git commit + push. No…

bearded-illirian/trailmark · 163 tokens

reviewing-data-privacy

Use when reviewing data privacy within security lifecycle boundaries, especially when does the artifact make the owned decision for reviewing data privacy explicit and bounded?.

Nolane-x/forge-os · 33 tokens

legal-discovery

Audit e-discovery and litigation document review systems -- data collection pipelines (PST, MBOX, SharePoint, Slack), document processing (OCR via Tesseract/ABBYY, metadata extraction, deduplication), Technology Assisted Review (TAR 1.0/2.0/CAL with recall/precision tracking).

tinh2/skills-hub-registry · 70 tokens