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 check-defined-termsgit 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/check-defined-terms)<a href="https://agentmods.dev/skills/microsoft/cat-agent-skills/check-defined-terms"><img src="https://agentmods.dev/badge/skills/microsoft/cat-agent-skills/check-defined-terms/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/check-defined-terms"><img src="https://agentmods.dev/badge/skills/microsoft/cat-agent-skills/check-defined-terms.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 | $0.00157 | $0.03074 |
| Opus 5.5 | $0.00063 | $0.01230 |
| Sonnet 5.5 | $0.00031 | $0.00615 |
| Haiku 4.5 | $0.00016 | $0.00307 |
Grade C, and why
check-defined-terms scanned grade C with 1 finding 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.
Tells the agent never to refusehighAnti-refusal
Suppressing the ability to decline removes a core safety control; a later harmful request then succeeds.
review. Never refuse, stop or ask the user to continue merely because the How it starts
The opening of the file, as written. The whole thing — 227 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Check defined terms
Audit the defined term system of the legal document the user supplied, report what is broken with citations, then set out suggested corrections the user can apply. A defined term is a word or phrase given a specific contractual meaning, so that every later use carries that meaning. This is a document quality check, not a commercial one: test whether the definitional machinery is internally sound, never whether the deal terms are good. Never comment on the merits of a definition unless the user asks.
Begin the audit as soon as you are asked. Do not ask which issues to look for, whether to correct as well as report, or to confirm scope — asking for a defined terms check is the whole instruction, and the answer is always the full audit below. Use a question card only where the document is unreadable or empty, where no document has been supplied and you cannot tell which file to audit, or where the user says "this" or "the selected clause" without quoting it.
When NOT to Use
- Broken, outdated or unverifiable clause, schedule, annex or exhibit references
— use
check-cross-references. That skill audits reference integrity; this one audits definition integrity, and each names the other. - Blanks,
[●]placeholders, unresolved tracked changes or signature blocks checked for completeness before signing — usecheck-execution-readiness. - A question about what a clause means or how it operates — use
legal-reasoning; plain English for a non-legal audience — useexplain-legal-concepts. - The same fields pulled out of several contracts — use
compare-key-terms; what changed between versions — usesummarize-redlines. - Drafting new wording from a precedent — use
draft-new-contract; a written memorandum — usedraft-legal-memo. - Producing the findings as a file — dispatch
docx,xlsxorpdf. - Carrying out an edit the user has already specified, or any playbook-based contract review — out of scope; this skill reports and proposes wording only.
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 · 227 lines · 157 tokens per session scan C 4bdbf4ac3d12
check-defined-terms is a skill published in the GitHub repository microsoft/cat-agent-skills (101 stars, last pushed yesterday), licensed MIT. It adds 157 tokens to every session and 3,074 once invoked, about $0.0006 per session on Opus 5.5. A static security scan graded it C with 1 finding (tells the agent never to refuse). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-11-06.
check-defined-terms compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| check-defined-termsmicrosoft/cat-agent-skills | Skill | 101 | yesterday | MIT | C | 157 | 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 |