microsoft/cat-agent-skills is a static website that catalogs reusable instruction sets and related packages for AI agents. People use it to search, filter, rate, and download skills for Cowork, Copilot Studio, and Scout, along with Copilot plugins and Scout automations. The catalogue entries are the skills, instructions, plugins, and settings displayed by the site.
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.
npx skills add microsoft/cat-agent-skills --skill review-contractgit clone --depth 1 https://github.com/microsoft/cat-agent-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/skills/microsoft/cat-agent-skills/review-contract)<a href="https://agentmods.dev/skills/microsoft/cat-agent-skills/review-contract"><img src="https://agentmods.dev/badge/skills/microsoft/cat-agent-skills/review-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.
<a href="https://agentmods.dev/skills/microsoft/cat-agent-skills/review-contract"><img src="https://agentmods.dev/badge/skills/microsoft/cat-agent-skills/review-contract.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 | $0.00112 | $0.01846 |
| Opus 5.5 | $0.00045 | $0.00738 |
| Sonnet 5.5 | $0.00022 | $0.00369 |
| Haiku 4.5 | $0.00011 | $0.00185 |
Grade A, and why
review-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 2d 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 — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Review contract
Review a contract against a playbook while keeping the playbook instructions, contract evidence, findings, and edits clearly separated.
Non-negotiable tracked changes rule
Before editing the contract, ensure tracked changes are enabled and used for every modification. Keep them enabled throughout the work. Do not accept or reject tracked changes on the user's behalf. Findings that do not require text changes remain report-only.
When NOT to Use
- A specific edit the user has already described, with no playbook — use
edit-contract. - Building a playbook from approved precedents — use
create-playbook. - Checking a document against a term sheet or other agreed deal terms — out of scope for this skill.
- Checking a document against legislation, regulation or an internal policy — use
identify-regulatory-gaps. - Explaining what changed between marked-up versions — use
summarize-redlines. - Legal advice or sign-off.
Hand-off rule. If a request, or part of one, matches an item above that names another skill, do
not do that part here — even when the documents are already open and the work looks quick. Name the
skill that handles it (for example, "That part is a job for edit-contract") and stop that part;
finish only what belongs to this skill. If the named skill is not installed, say so plainly and do
not attempt it here.
Playbook availability
- If the playbook was confirmed in an earlier turn, proceed directly to the review.
- If the playbook is supplied for the first time in the current request, or has not yet been confirmed, complete Phase 1 and wait for confirmation before reviewing the contract.
- If no playbook is available, ask the user to provide or select one and do not begin the review.
- If more than one document could be the playbook, ask the user to identify the intended one rather than guessing.
- Do not impose an unstated size limit. If the platform or document reading tool reports an explicit whole-document limit and the contract exceeds it, state the reported limit and the measured contract size when available, then stop rather than sampling or truncating the review.
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.
- 2d ago First seen · 128 lines · 112 tokens per session scan A cf7d22ad01d5
review-contract is a skill published in the GitHub repository microsoft/cat-agent-skills (101 stars, last pushed yesterday), licensed MIT. It adds 112 tokens to every session and 1,846 once invoked, about $0.0004 per session on Opus 5.5. 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 2026-11-06.
review-contract compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| review-contractmicrosoft/cat-agent-skills | Skill | 101 | yesterday | MIT | A | 112 | Claude Code, Codex |
| compiler-reviewreact/react | Skill | 252k | yesterday | MIT | A | 27 | Claude Code |
| prowler-compliance-reviewprowler-cloud/prowler | Skill | 15k | today | Apache-2.0 | A | 62 | Claude Code |
| compliance-checkerAffitor/affiliate-skills | Skill | 773 | 20d ago | MIT | A | 87 | Claude Code, Codex |
| self-improverAffitor/affiliate-skills | Skill | 773 | 20d ago | MIT | A | 87 | Claude Code |
| ring:adding-multi-tenancyLerianStudio/ring | Skill | 218 | 7d ago | Apache-2.0 | A | 95 | Cursor |
| rds-operation-reviewaws/tools-for-devops-agent | Skill | 137 | today | Apache-2.0 | A | 118 | Claude Code, Codex |