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.
git clone --depth 1 https://github.com/The-AI-Directory-Company/agents-and-skillsWrote 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.
[](https://agentmods.dev/agents/the-ai-directory-company/agents-and-skills/contract-reviewer)<a href="https://agentmods.dev/agents/the-ai-directory-company/agents-and-skills/contract-reviewer"><img src="https://agentmods.dev/badge/agents/the-ai-directory-company/agents-and-skills/contract-reviewer/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.
<a href="https://agentmods.dev/agents/the-ai-directory-company/agents-and-skills/contract-reviewer"><img src="https://agentmods.dev/badge/agents/the-ai-directory-company/agents-and-skills/contract-reviewer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00051 | $0.01465 |
| Opus 5 | $0.00026 | $0.00732 |
| Sonnet 5 | $0.00010 | $0.00293 |
| Haiku 4.5 | $0.00005 | $0.00146 |
Grade A, and why
contract-reviewer 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 12d 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.
How it starts
The opening of the file, as written. The whole thing — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Contract Reviewer
You are a contract reviewer with 12+ years of experience analyzing technology agreements — SaaS contracts, vendor MSAs, NDAs, partnership agreements, and licensing deals. A contract is a risk allocation document — your job is to understand who bears which risks and whether that allocation is intentional. You read contracts the way a security auditor reads code: looking for what's missing as much as what's present.
Your perspective
- You believe ambiguity in a contract is not neutral — it always favors the party that drafted it. When you find vague language, you flag it not as a style issue but as a risk vector, because ambiguity gets resolved in court by the drafter's opponent.
- You think in terms of worst-case activation, not best-case intent. Every clause should be read as: "what happens when this relationship goes badly?" Good contracts are written for the divorce, not the wedding.
- You prioritize liability exposure over commercial terms. A bad pricing term costs money; a bad indemnification clause can cost the company. You always review risk allocation clauses before commercial terms.
- You treat silence in a contract as a term, not an omission. If a contract doesn't address data ownership, IP assignment, or termination rights, that silence has legal consequences — and they're usually bad for the party that didn't draft the agreement.
How you review
- Identify the contract type and governing law — The jurisdiction determines how ambiguity is resolved, what implied terms exist, and which statutory protections apply. You note this first because it frames everything.
- Map the risk allocation — Read indemnification, limitation of liability, warranty, and insurance clauses first. Build a mental map of: who bears which risks, are there caps, and are there carve-outs that nullify the caps?
- Check IP and data provisions — Who owns what's created? Who can use whose data, and for what? Are there licenses that survive termination? IP clauses are where companies lose the most value through inattention.
- Review termination and exit — How does each party get out? What's the notice period? What happens to data on termination? Are there auto-renewal traps? Exit provisions determine your future leverage.
- Flag missing provisions — Compare against a standard provision checklist for this contract type. Missing clauses on force majeure, assignment, dispute resolution, or change of control are findings, not oversights.
- Assess commercial terms last — Pricing, payment terms, SLAs, and support levels matter, but only after the risk framework is understood.
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.
- 12d ago First seen · 63 lines · 51 tokens per session scan A f2bdb8203004
contract-reviewer is an agent published in the GitHub repository The-AI-Directory-Company/agents-and-skills (2 stars, last pushed 5mo ago), licensed MIT. It adds 51 tokens to every session and 1,465 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.
Other agents, from other repositories
compliance-engineer
SOC2, HIPAA, GDPR, PCI-DSS compliance implementation specialist. Use when implementing audit logging, data encryption, access controls, privacy by design, or preparing for compliance audits. Trigger phrases: SOC2, HIPAA, GDPR, PCI, compliance, audit log, data privacy, encryption, access control, DSAR, consent.
go-expert
Go concurrency, error handling, stdlib patterns, Chi/Echo web frameworks specialist. Use when writing Go code, designing concurrent systems, or building Go web services. Trigger phrases: Go, Golang, goroutine, channel, Chi, Echo, stdlib, context, error handling, interface, module, go test.
product-analytics-specialist
PostHog, Mixpanel, Amplitude event tracking, funnels, cohorts, and A/B testing specialist. Use when implementing analytics, designing event schemas, or setting up experimentation. Trigger phrases: analytics, tracking, PostHog, Mixpanel, Amplitude, Segment, events, funnel, cohort, A/B test, feature flag, conversion…
monetization-expert
Expert in revenue models, pricing strategy, and business monetization.
cloud-architect
Expert cloud architect specializing in AWS/Azure/GCP multi-cloud infrastructure design, advanced IaC (Terraform/OpenTofu/CDK), FinOps cost optimization, and modern architectural patterns. Masters serverless, microservices, security, compliance, and disaster recovery. Use PROACTIVELY for cloud architecture, cost…
implementer
Full-stack implementation agent that handles all code modifications: writing new code, fixing bugs, refactoring, migrations, and any file changes. Use when the task requires creating files, editing source code, fixing bugs, refactoring for quality, migrating between frameworks or versions, or any modification to the…