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 severity-recordabilitygit 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/severity-recordability)<a href="https://agentmods.dev/skills/microsoft/cat-agent-skills/severity-recordability"><img src="https://agentmods.dev/badge/skills/microsoft/cat-agent-skills/severity-recordability/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/severity-recordability"><img src="https://agentmods.dev/badge/skills/microsoft/cat-agent-skills/severity-recordability.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 | $0.00093 | $0.00637 |
| Opus 5.5 | $0.00037 | $0.00255 |
| Sonnet 5.5 | $0.00019 | $0.00127 |
| Haiku 4.5 | $0.00009 | $0.00064 |
Grade A, and why
severity-recordability 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 today.
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.
Severity & Recordability
Purpose
Deterministically classify the incident: severity tier (low/medium/high/critical), near-miss flag, OSHA recordability (with the OSHA 300 classification column) and reportability to OSHA (with the 1904.39 regulatory clock). This is the determination the whole packet turns on.
When to use
- After ehs-knowledge-retrieve, in every run.
- "Is this recordable?" / "do we have to report this?" / "what severity is this?".
Inputs
- The contract payload with
injury{},incident_type,occurred_atandhistory{}(contractmfg.safety-incident-assist.v1).
Steps
- Validate the payload against the contract.
- Run
scripts/recordability_classify.py --intake incident-intake.json --out classification.json. - Do not restate or re-derive the determination in prose; quote the engine output verbatim.
- Emit the
{classification}contract payload and the preliminarynext_best_action.
Output
Contract mfg.safety-incident-assist.v1 with a populated classification{} object (severity,
near_miss, recordable{value,reason,osha_300_column}, reportable{value,type,deadline_hours},
confidence, source=engine:recordability_classify, citation) — the {classification} hop.
Grounding requirements
The recordability determination cites references/osha-recordability-rules.md #3; the reportability
determination cites #4; the severity cites #5.
Constraints
- All classification logic happens in the engine. The model must never decide recordability itself.
- A first-aid list item does not make a case recordable; treatment beyond first aid does (osha-recordability-rules.md #2). Do not blur the two.
- Never downgrade a recordable/reportable determination to first-aid to make a report go away (osha-recordability-rules.md #6.3) — that is the whole point of the control.
Escalation / uncertainty
- Incomplete treatment/outcome (confidence below the floor) or a downgrade request: the engine adds
to
escalations[]; surface it for EHS-manager sign-off and confirm with the treating clinician (osha-recordability-rules.md #6.2, #6.3).
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.
- today First seen · 52 lines · 93 tokens per session scan A a2360ea7b4b0
severity-recordability is a skill published in the GitHub repository microsoft/cat-agent-skills (93 stars, last pushed today), licensed MIT. It adds 93 tokens to every session and 637 once invoked, about $0.0004 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 2026-10-28.
Other skills, from other repositories
fto-triage
Freedom-to-operate triage — a structured first look at potentially blocking patents, not an FTO opinion. Use when a product, process, or feature is being evaluated for blocking patents, when asked whether anything stops a launch, or to build a claim-chart first pass against the most plausible patents before patent…
legal-hold
Issue, refresh, release, or report on legal holds — drafts the hold notice as .docx, updates legalhold fields in log.yaml, and calendars the next refresh. Use when the user says "issue a hold", "refresh hold", "release hold", or asks for a portfolio-wide hold status report.
specification-writing
A workflow for writing complete patent specifications from patent claims and an invention disclosure. It adapts the document to a chosen jurisdiction, such as the US, Europe, or China.
terms-of-service
Draft terms of service and a companion privacy notice matched to the product's form and feature modules, not legal advice, delivered as a Word document.
x-scorecard
OpenSSF Scorecard for assessing open source project security. Check security best practices and compliance. Dependency: This is an x-cmd module. Install x-cmd first (see x-cmd skill for installation options). see x-cmd skill for installation.
ai-risk-management
Apply the NIST AI Risk Management Framework (AI RMF 1.0) and adjacent guidance to AI / ML systems — model lifecycle governance, fairness and bias evaluation, robustness, transparency, accountability, third-party model risk, monitoring for drift, and AI incident response. Broader than prompt-injection (which is the…