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 summary-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/summary-draft)<a href="https://agentmods.dev/skills/microsoft/cat-agent-skills/summary-draft"><img src="https://agentmods.dev/badge/skills/microsoft/cat-agent-skills/summary-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/summary-draft"><img src="https://agentmods.dev/badge/skills/microsoft/cat-agent-skills/summary-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 | $0.00141 | $0.01285 |
| Opus 5.5 | $0.00056 | $0.00514 |
| Sonnet 5.5 | $0.00028 | $0.00257 |
| Haiku 4.5 | $0.00014 | $0.00128 |
Grade A, and why
summary-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 — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Summary Draft
Action level: L1 (draft for human approval). The summary is prepared and handed to a clinician; it is never signed, filed or transmitted by this plugin.
Purpose
Produce the legal discharge record draft for clinician signature.
When to use
After med-reconcile, for every discharge packet. Typical triggers: "draft the discharge summary", "write up the hospital course", "put the discharge summary together", "get the discharge summary ready for signature".
When NOT to use
When NOT to use: do not use it to produce patient-facing text (patient-instructions), the follow-up checklist (followup-plan), a medication diff (med-reconcile) or the structured admission facts (admission-synthesise). When the user asks to finalise, sign, file or send the summary into the chart, or to omit an open discrepancy to get the packet out, the draft is still produced but the finalise/file/omit part is refused (discharge-rules.md #2).
Inputs
encounter; reconciliation_report; the cited source_note/documented_date carried on every medication and change.
Steps
- If
reconciliation_reportis absent from the contract, run med-reconcile first (engine toolpython3 base/scripts/med_reconcile.py --question <payload> --out <payload>); never re-derive the list here. - Draft the discharge summary sections in order: hospital course, procedures, results, medications, disposition.
- Build the medication section only from the engine output: every
reconciliation_report.expected_discharge_medsentry as active, then everyreconciliation_report.stopped_medsentry as "stopped" with its reason, each carrying its citation - a documented discontinuation is never dropped from the summary. - If
reconciliation_report.cleanis false, add an explicit medication-section open-items list, one line per discrepancy with its type, rule citation and documenting note. - Mark the summary draft, pending clinician signature, and state the blocked status when it is not clean.
- Hand off for clinician review; never advance the state beyond draft.
What ships with it
5 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 · 71 lines · 141 tokens per session scan A 83d406666370
summary-draft is a skill published in the GitHub repository microsoft/cat-agent-skills (101 stars, last pushed yesterday), licensed MIT. It adds 141 tokens to every session and 1,285 once invoked, about $0.0006 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.
summary-draft compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| summary-draftmicrosoft/cat-agent-skills | Skill | 101 | yesterday | MIT | A | 141 | Claude Code, Codex |
| orbit-notionnexu-io/open-design | Skill | 107k | today | Apache-2.0 | A | 117 | Claude Code, Codex |
| instrument-data-to-allotropeanthropics/knowledge-work-plugins | Skill | 35k | yesterday | Apache-2.0 | A | 123 | Claude Code |
| apify-youtube-transcript-scrapersickn33/agentic-awesome-skills | Skill | 49k | 2d ago | MIT | A | 48 | Claude Code |
| legal-holdanthropics/claude-for-legal | Skill | 9.9k | yesterday | Apache-2.0 | A | 68 | Claude Code |
| report-to-pdfasgeirtj/system_prompts_leaks | Skill | 71k | today | CC0-1.0 | A | 17 | Claude Code, Codex |
| artifact-template-minimal-letterheadasgeirtj/system_prompts_leaks | Skill | 71k | today | CC0-1.0 | A | 54 | Claude Code, Codex |