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 appeal-draftgit 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/appeal-draft)<a href="https://agentmods.dev/skills/microsoft/cat-agent-skills/appeal-draft"><img src="https://agentmods.dev/badge/skills/microsoft/cat-agent-skills/appeal-draft/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/appeal-draft"><img src="https://agentmods.dev/badge/skills/microsoft/cat-agent-skills/appeal-draft.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 | $0.00169 | $0.01497 |
| Opus 5.5 | $0.00068 | $0.00599 |
| Sonnet 5.5 | $0.00034 | $0.00299 |
| Haiku 4.5 | $0.00017 | $0.00150 |
Grade A, and why
appeal-draft 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 — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Appeal Draft
Purpose
Produce the appeal letter text for coordinator review.
When to use
Use after evidence-assemble and after deadline-track has set coding_decision and deadline_status - typical asks are "draft the appeal letter", "write our response to this denial", "redraft it on the original code".
When NOT to Use
Do NOT use when: the denial has not been classified yet ("start an appeal on CLM-..." from a remittance) - use denial-classify instead; policy_citations or chart_evidence are still empty (there is nothing to cite, so drafting would invent the case) - use policy-retrieve or evidence-assemble instead; the ask is to submit, file, fax, e-mail or upload the appeal to a payer portal, or to mark it submitted or closed - that is refused, not delegated; the ask is to draft around a code the chart does not cite; or the ask is for the deadline, queue order or coding decision - use deadline-track instead.
Inputs
denial; policy_citations; chart_evidence (with its citations); deadline_result (coding_decision, deadline, days_remaining, deadline_status); config/payer-appeal-windows.json (appeal level).
Steps
- Confirm policy_citations and chart_evidence are populated. If deadline_result is absent, or its provenance.computed_as_of is not today, run deadline-track first (tool:
python3 base/scripts/deadline_engine.py --question <contract.json> --payers config/payer-appeal-windows.json --out <result.json>, no--today) and use its result. - Read deadline_result.deadline_status: if
expiredorurgent, put that status, the deadline and the day count in the first line of the draft header and in the coordinator notes; ifunconfigured, say no deadline could be computed. - Draft the letter at the level carried in config for the payer (config/payer-appeal-windows.json payers[payer].level, payer name matched case-insensitively).
- Cite the policy clause_id and every chart_evidence citation used, inline, in the forms "(clause_id)" and "(note, date)". If the clause text is not on the contract, cite it by clause_id only and say the wording is not on file.
- If coding_decision is refused_evidence_gap, draft on the original, chart-supported code only and state in the coordinator notes that the coding question is open for human decision.
- Return the letter as a draft for coordinator review before anything is sent - never as a sent or filed item.
What ships with it
4 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 · 52 lines · 169 tokens per session scan A 9249440454d3
appeal-draft is a skill published in the GitHub repository microsoft/cat-agent-skills (101 stars, last pushed yesterday), licensed MIT. It adds 169 tokens to every session and 1,497 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.
appeal-draft compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| appeal-draftmicrosoft/cat-agent-skills | Skill | 101 | yesterday | MIT | A | 169 | 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 |