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 evidence-assemblegit 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/evidence-assemble)<a href="https://agentmods.dev/skills/microsoft/cat-agent-skills/evidence-assemble"><img src="https://agentmods.dev/badge/skills/microsoft/cat-agent-skills/evidence-assemble/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/evidence-assemble"><img src="https://agentmods.dev/badge/skills/microsoft/cat-agent-skills/evidence-assemble.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 | $0.01312 |
| Opus 5.5 | $0.00069 | $0.00525 |
| Sonnet 5.5 | $0.00035 | $0.00262 |
| Haiku 4.5 | $0.00017 | $0.00131 |
Grade A, and why
evidence-assemble 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 — 47 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Evidence Assemble
Purpose
Build the cited evidence base the appeal will rely on.
When to use
Use after policy-retrieve and before deadline-track and appeal-draft - typical asks are "pull the chart evidence for this appeal", "does the documentation support the billed code", "what in the record answers this denial".
When NOT to Use
Do NOT use when: no policy clause has been retrieved yet (the evidence has nothing to answer) - use policy-retrieve first; the ask is to read a remittance or classify a denial - use denial-classify instead; the ask is to interpret payer policy - use policy-retrieve instead; the ask is to compose the appeal letter - use appeal-draft instead; the ask is to approve or apply a coding change - use deadline-track instead (it enforces that boundary, and no skill applies codes); or the ask is to make the evidence "look stronger" than the chart supports - that is out of bounds, not a task.
Inputs
The clinical record, read through [TO CONFIGURE: clinical record source / EHR connector] with the session's file or connector tool (until it is configured, only the chart_evidence already on the contract is available); original claim and coding; the denial reason; the retrieved policy clause; coding_request (if any).
Steps
- Read the denial reason and the retrieved policy clause to fix what the evidence has to answer, and name the code being defended: the coding_request's requested code if one exists, otherwise the billed original_code.
- Gather the clinical notes/results that speak to that question from the configured record source, including any that weaken the appeal.
- Record each one in chart_evidence.citations[] with note, date, supports_code and a short verbatim excerpt.
- Set chart_evidence.supports_requested_code true only when a citation in that list names a specific note and date whose supports_code is the code named in step 1; otherwise leave it false.
- Compare the clause's setting or service type with the claim's (e.g. an inpatient-observation clause against an office E/M code) and record any mismatch as a gap.
- Hand off to deadline-track (coding decision and clock) and then appeal-draft.
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 · 47 lines · 173 tokens per session scan A 765c34c93198
evidence-assemble 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 1,312 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.
evidence-assemble compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| evidence-assemblemicrosoft/cat-agent-skills | Skill | 101 | yesterday | MIT | A | 173 | Claude Code, Codex |
| sector-rotationHKUDS/Vibe-Trading | Skill | 38k | today | MIT | A | 39 | Claude Code, Codex |
| strategy-pivot-designertradermonty/claude-trading-skills | Skill | 3.7k | today | MIT | A | 28 | Claude Code, Codex |
| twitter-readerhimself65/finance-skills | Skill | 3.5k | 4d ago | MIT | A | 110 | Claude Code |
| energy-procurementhashgraph-online/awesome-codex-plugins | Skill | 1.5k | today | Apache-2.0 | A | 93 | Claude Code, Codex |
| airdrop-hunting-guidenirholas/three.ws | Skill | 271 | today | Apache-2.0 | A | 54 | Claude Code, Codex |
| multi-expert-analyzerdigoal/blog | Skill | 8.6k | 4d ago | GPL-2.0 | A | 292 | Codex |