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 policy-gap-analysisgit 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/policy-gap-analysis)<a href="https://agentmods.dev/skills/microsoft/cat-agent-skills/policy-gap-analysis"><img src="https://agentmods.dev/badge/skills/microsoft/cat-agent-skills/policy-gap-analysis/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/policy-gap-analysis"><img src="https://agentmods.dev/badge/skills/microsoft/cat-agent-skills/policy-gap-analysis.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 | $0.00173 | $0.02213 |
| Opus 5.5 | $0.00069 | $0.00885 |
| Sonnet 5.5 | $0.00035 | $0.00443 |
| Haiku 4.5 | $0.00017 | $0.00221 |
Grade A, and why
policy-gap-analysis 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 — 162 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Scope
Do: compare specific regulation sections to a firm policy clause by clause, quote both sides, assign coverage states, suggest owner-reviewed edits Do not: conclude compliant, non-compliant, or in violation, score unretrieved requirements, treat drafts or unretrieved referenced documents as coverage, alter source systems, send, or file anything
When NOT to Use
- Triaging a newly published rule across the firm — use
reg-change-triageinstead. - An examiner request list or PDL response tracker — use
exam-request-responseinstead. - Formatting, charting, or restyling an existing workbook — use
xlsxinstead.
Policy-to-Regulation Gap Analysis
Clause-by-clause: what the regulation requires, what the policy says, and whether the second addresses the first.
This skill never concludes compliance. It reports coverage states with both sides quoted.
Whether the firm complies is a determination by a qualified owner — house-rules.md § 2.
Read first
Read these in full before step 1. They are binding; this body only summarises them.
references/workflow.md— the full text of every step below, with the guardrails, source resolution, and footer detail.references/house-rules.md— destination gate, determination gate, authority tiers, markers, footers, and § 12 data minimisation (every artifact, search, and chat reply, declines included).references/reg-source-access.md— routing, the codification gap, precision filtering.references/document-extraction.md— policy version and approval discipline.references/gap-outline.md— default table and memo structure: the output format.references/self-check.md— the final self-check (step 7).
Workflow
1. Establish both sides before comparing
Detail: workflow.md § 1.
- Regulation: agency · citation · type · tier · sections in scope. Retrieve per
reg-source-access.mdand run the codification check; an effective later final rule governs (PENDING CODIFICATION), a future one is a forthcoming change in theSourcecell. House-rules markers only, plusPROPOSED DRAFTING. - Policy: name · version · approval status · approval date · owner · scope. A draft is
DRAFT — not approved, never the control of record. When the policy given is a draft or superseded, find and open the approved version and stateControl of record: <doc> v<x>, approved <date> (<location>)in § 2 and the chat reply: a fact, never a D-bullet. Version or approval unknown →GAP — policy version not established, and no row is scored as covered. - Scope is load-bearing. Quote the policy's scope clause. Which entities, accounts, or
products the rule covers is proposed applicability:
NOT DETERMINED, compliance owner decides, with the retrieved defining provision cited. If that provision was not retrieved, the reasoning reads exactlynone - defining provision not retrieved. No hedge words.
What ships with it
7 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 · 162 lines · 173 tokens per session scan A 862dc08e8d45
policy-gap-analysis is a skill published in the GitHub repository microsoft/cat-agent-skills (101 stars, last pushed yesterday), licensed MIT. It adds 173 tokens to every session and 2,213 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.
policy-gap-analysis compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| policy-gap-analysismicrosoft/cat-agent-skills | Skill | 101 | yesterday | MIT | A | 173 | 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 |