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 admission-synthesisegit 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/admission-synthesise)<a href="https://agentmods.dev/skills/microsoft/cat-agent-skills/admission-synthesise"><img src="https://agentmods.dev/badge/skills/microsoft/cat-agent-skills/admission-synthesise/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/admission-synthesise"><img src="https://agentmods.dev/badge/skills/microsoft/cat-agent-skills/admission-synthesise.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 | $0.00138 | $0.01245 |
| Opus 5.5 | $0.00055 | $0.00498 |
| Sonnet 5.5 | $0.00028 | $0.00249 |
| Haiku 4.5 | $0.00014 | $0.00125 |
Grade A, and why
admission-synthesise 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 — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Admission Synthesise
Action level: L0 (read and analyse only). This skill writes to the contract; it files, sends and signs nothing.
Purpose
Establish the clinical narrative every later artefact is derived from.
When to use
Start of every discharge packet run - once discharge is ordered or anticipated. Typical triggers: "prep the discharge packet", "start the discharge packet", "pull together the hospital course", "summarise the stay".
When NOT to use
When NOT to use: do not use it to reconcile medications (med-reconcile owns the diff), to write the summary prose (summary-draft), to write patient-facing text (patient-instructions), or to build the follow-up list (followup-plan). Do not use it outside an inpatient encounter - there is no admission narrative to extract - and do not run it to "fill gaps" when the record is incomplete; escalate instead.
Inputs
Inpatient notes, procedure/operative reports, medication administration record, labs, imaging, problem list. Contract: base/contracts/hls.discharge-care-transition.v1.json.
Steps
- Read the admission diagnosis, hospital course and problem list into structured encounter facts; carry the
encounter's own
source_note/documented_datewhen the record gives them. - Extract procedures and key results with their dates.
- Record each medication and inpatient change with its
source_noteanddocumented_date(discharge-rules.md #9). - Write
encounter{},admission_meds[]andinpatient_changes[]to the contract as the entry hop. - Write a short readable recap for the clinician - one bullet per fact, each ending with its citation - drawn only from what step 4 wrote.
- Hand off to med-reconcile; report anything the record does not support as an escalation, never as a fact.
Output
Contract JSON conforming to hls.discharge-care-transition.v1: encounter{patient_id, admission_dx, discharge_date, source_note, documented_date}, admission_meds[{drug, dose, status, source_note, documented_date}] and inpatient_changes[{drug, action, dose, reason, source_note, documented_date}], plus
escalations[] for every absent field and a bulleted recap for the clinician.
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 · 68 lines · 138 tokens per session scan A c7810a8f74a4
admission-synthesise is a skill published in the GitHub repository microsoft/cat-agent-skills (101 stars, last pushed yesterday), licensed MIT. It adds 138 tokens to every session and 1,245 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.
admission-synthesise compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| admission-synthesisemicrosoft/cat-agent-skills | Skill | 101 | yesterday | MIT | A | 138 | 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 |