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 analyze-related-contractsgit 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/analyze-related-contracts)<a href="https://agentmods.dev/skills/microsoft/cat-agent-skills/analyze-related-contracts"><img src="https://agentmods.dev/badge/skills/microsoft/cat-agent-skills/analyze-related-contracts/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/analyze-related-contracts"><img src="https://agentmods.dev/badge/skills/microsoft/cat-agent-skills/analyze-related-contracts.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 | $0.00170 | $0.03291 |
| Opus 5.5 | $0.00068 | $0.01316 |
| Sonnet 5.5 | $0.00034 | $0.00658 |
| Haiku 4.5 | $0.00017 | $0.00329 |
Grade A, and why
analyze-related-contracts 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 — 252 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Analyze related contracts
Take the set of related contract documents the user supplies and produce one Related Contracts Report for a lawyer or contract manager. A contract family takes many forms and no single shape is assumed — a master agreement with amendments and SOWs, a lease with rent reviews and licences to alter, a facility agreement with accession deeds and waivers, a share purchase agreement with disclosure letters and deeds of variation, a settlement deed superseding earlier terms, a chain of NDAs and side letters, or any mix of novations, assignments, renewals and terminations. Derive the family's actual shape from the documents; never force them into an assumed master-and-amendment structure.
The report answers three questions:
- How do these documents relate? Which one amends, restates, replaces, terminates, supplements, or is incorporated by reference into which.
- In what sequence did they take effect? A dated chronology of the family.
- What is operative today? For each key term, the version currently in force and the exact provision that governs it.
The output is a deliverable — a Word report, an Excel workbook, or a complete chat report — marked "Draft — for counsel review". It is not legal advice and not a determination that any document is validly executed or enforceable.
When NOT to Use
- A question answered inline about one agreement family, including
assembling an agreement with its amendments into the current position in
chat — use
legal-reasoning. This skill is for a set of documents where the deliverable is a Related Contracts Report; the moment the ask is a chat answer about a single stack, hand it over and stop. - The same fields compared side by side across documents — use
compare-key-terms. - Obligations, deadlines, or who must do what by when — use
extract-obligations-and-deadlines. - Tracked changes inside one document — use
summarize-redlines. - A memorandum of advice — use
draft-legal-memo; review guidance from many precedents — usecreate-playbook; a new agreement from one precedent — usedraft-new-contract. - Whether one document is complete enough to sign — use
check-execution-readiness. - A single contract with no amendments or related documents — there is no
family to map; use
legal-reasoning. - A legal opinion on validity, enforceability or which party wins — out of scope; see Guardrails.
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.
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 · 252 lines · 170 tokens per session scan A 9dfb4693d516
analyze-related-contracts is a skill published in the GitHub repository microsoft/cat-agent-skills (101 stars, last pushed yesterday), licensed MIT. It adds 170 tokens to every session and 3,291 once invoked, about $0.0007 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.
analyze-related-contracts compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| analyze-related-contractsmicrosoft/cat-agent-skills | Skill | 101 | yesterday | MIT | A | 170 | Claude Code, Codex |
| fto-triageanthropics/claude-for-legal | Skill | 9.9k | yesterday | Apache-2.0 | A | 81 | Claude Code |
| legal-holdanthropics/claude-for-legal | Skill | 9.9k | yesterday | Apache-2.0 | A | 68 | Claude Code |
| specification-writingwanshuiyin/Auto-claude-code-research-in-sleep | Skill | 19k | today | MIT | A | 49 | Claude Code |
| regulatory-research-fallbackHKUDS/OpenSpace | Skill | 7.9k | 2d ago | MIT | A | 20 | Claude Code, Codex |
| terms-of-servicegenspark-ai/genoffice | Skill | 12k | today | Apache-2.0 | A | 32 | Claude Code, Codex |
| x-scorecardx-cmd/x-cmd | Skill | 4.7k | 8d ago | Apache-2.0 | A | 57 | Claude Code, Codex |