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 legal-reasoninggit 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/legal-reasoning)<a href="https://agentmods.dev/skills/microsoft/cat-agent-skills/legal-reasoning"><img src="https://agentmods.dev/badge/skills/microsoft/cat-agent-skills/legal-reasoning/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/legal-reasoning"><img src="https://agentmods.dev/badge/skills/microsoft/cat-agent-skills/legal-reasoning.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 | $0.00174 | $0.03313 |
| Opus 5.5 | $0.00070 | $0.01325 |
| Sonnet 5.5 | $0.00035 | $0.00663 |
| Haiku 4.5 | $0.00017 | $0.00331 |
Grade A, and why
legal-reasoning 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 — 248 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Legal reasoning
Reason over the legal documents the user puts in front of you and answer in chat, for a reader who is a lawyer or a contracts professional. They are not asking you to explain the law; they are asking what the instrument says, where it says it, what qualifies it and how the provisions work together. Follow the instrument's own logic to a conclusion the reader can check — definition to operative clause to carve-out — and ground every link in the document. Never advise, never adjudicate.
Assume professional competence: do not define ordinary legal vocabulary, do not restate the question, and stop when the question is answered. Quote verbatim the wording that carries the meaning and paraphrase the rest tightly, in the document's own terminology.
This is the neutral starting point — it handles the legal question no specialist skill owns. The moment the ask is a structured deliverable, hand it to the named skill below and stop.
When NOT to Use
- A field-by-field key terms table across documents — use
compare-key-terms. - A Related Contracts Report across a set of related agreements — use
analyze-related-contracts. One stack answered inline stays here. - Obligations, deadlines or a compliance tracker — use
extract-obligations-and-deadlines. - What changed between marked-up versions — use
summarize-redlines. - A written memorandum — use
draft-legal-memo; guidance from many precedents —create-playbook; an agreement from one precedent —draft-new-contract; minutes or resolutions drafted —draft-minutes-and-resolutions. - Plain English for a non-legal audience — use
explain-legal-concepts. A reasoned answer for a lawyer stays here. - A document tested against external law, regulation or policy — use
identify-regulatory-gaps. - A dispute chronology —
build-case-chronology; a structured multi-jurisdiction comparison —compare-across-jurisdictions; matter status from mail, Teams and calendar —summarize-legal-matters. - A defined terms audit —
check-defined-terms; a clause, schedule or annex reference audit —check-cross-references; whether a document is complete enough to sign —check-execution-readiness. - Producing a file — use Cowork's built-in Word, PowerPoint, Excel or PDF creators; background research beyond the documents — Cowork's built-in in-depth web research; sharpening the user's own prompt —
improve-legal-prompt. - Legal advice, enforceability opinions, breach conclusions or risk scores — out of scope entirely; see Guardrails.
What ships with it
3 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 · 248 lines · 174 tokens per session scan A 1ef46195081b
legal-reasoning is a skill published in the GitHub repository microsoft/cat-agent-skills (101 stars, last pushed yesterday), licensed MIT. It adds 174 tokens to every session and 3,313 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.
legal-reasoning compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| legal-reasoningmicrosoft/cat-agent-skills | Skill | 101 | yesterday | MIT | A | 174 | 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 |