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 explain-legal-conceptsgit 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/explain-legal-concepts)<a href="https://agentmods.dev/skills/microsoft/cat-agent-skills/explain-legal-concepts"><img src="https://agentmods.dev/badge/skills/microsoft/cat-agent-skills/explain-legal-concepts/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/explain-legal-concepts"><img src="https://agentmods.dev/badge/skills/microsoft/cat-agent-skills/explain-legal-concepts.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 | $0.03042 |
| Opus 5.5 | $0.00068 | $0.01217 |
| Sonnet 5.5 | $0.00034 | $0.00608 |
| Haiku 4.5 | $0.00017 | $0.00304 |
Grade A, and why
explain-legal-concepts 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 — 188 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Explain legal concepts
Turn what an agreement actually says into language a commercial colleague can act on, without losing the numbers, deadlines, conditions, exceptions or clause references a lawyer needs to check the answer. The output translates the documents. It is never legal advice, a risk rating or approval to proceed. Two people use it: an in-house lawyer explaining a document or portfolio to a non-legal audience, and a deal team member working out what a deal commits them to and when to ask Legal.
Default delivery
Deliver in chat by default and do not ask where the output should go. Honour an explicit request for a Word document or another supported format; otherwise give the complete explanation, and any draft message, in chat. Length, document count and portfolio size never trigger file creation.
When NOT to Use
- A reasoned legal answer, analysis or opinion written for a lawyer — use
legal-reasoning. This skill is for a non-legal audience; that one is for a legal reader. - A formal written memo for a legal reader — use
draft-legal-memo. - A structured key terms grid, contract abstract or side-by-side extraction table — use
compare-key-terms. - Who must do what by when, as a tracker — use
extract-obligations-and-deadlines. - Testing a document against legislation, a rulebook or internal policy — use
identify-regulatory-gaps. - Explaining what changed between marked-up versions — use
summarize-redlinesfirst, then this skill to translate that explanation for a non-legal reader. - The same question across legal systems — use
compare-across-jurisdictions. - Precedent positions and fallbacks — use
create-playbook; drafting a new document from precedent — usedraft-new-contract. - A business or leadership update not grounded in a specific legal document, and general mail sending, replying, forwarding or triage.
- Legal advice, enforceability, market standard benchmarking, "is this a good deal?", "should we sign?" or a risk score. Decline that part, explain what the documents say, and route the judgment to counsel.
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 · 188 lines · 170 tokens per session scan A 326cd0a75458
explain-legal-concepts 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 3,042 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.
explain-legal-concepts compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| explain-legal-conceptsmicrosoft/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 |