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 claim-checkgit 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/claim-check)<a href="https://agentmods.dev/skills/microsoft/cat-agent-skills/claim-check"><img src="https://agentmods.dev/badge/skills/microsoft/cat-agent-skills/claim-check/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/claim-check"><img src="https://agentmods.dev/badge/skills/microsoft/cat-agent-skills/claim-check.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 | $0.00051 | $0.00342 |
| Opus 5.5 | $0.00020 | $0.00137 |
| Sonnet 5.5 | $0.00010 | $0.00068 |
| Haiku 4.5 | $0.00005 | $0.00034 |
Grade A, and why
claim-check 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.
What it actually says
Claim Check (Govern)
Purpose
The compliance determination IS the work: a claim ships only with library substantiation for that GTIN and market (#4.1/#4.2); blocked claims never appear in copy, not even softened (#4.3).
When to use
After gap-score, before any copy is drafted.
Inputs
scored.json + config/claim-library.json + target market.
Steps
- Run scripts/claim_check.py --scored scored.json --library claim-library.json --market --out governed.json
- Quote verdicts verbatim. Supplier romance copy is not approval - "the supplier wrote it" changes nothing (#4.1).
Output
governed.json - the {claim_findings} hop.
Grounding requirements
Approvals cite the substantiation reference; blocks cite the regulated-term list.
Constraints
- The engine decides; the model never rephrases a blocked claim into the draft ("fights germs" for a blocked "antibacterial" is still the claim).
- Approving a regulated claim is a human/regulatory affair - out of scope.
Escalation / uncertainty
Every blocked claim escalates to the claim owner with the library citation.
What ships with it
9 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 · 26 lines · 51 tokens per session scan A 3d7c8955c7ec
claim-check is a skill published in the GitHub repository microsoft/cat-agent-skills (93 stars, last pushed today), licensed MIT. It adds 51 tokens to every session and 342 once invoked, about $0.0002 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
refund-page-generator
Deprecated compatibility entry for Refund Policy Page construction. This page is now maintained in Pagina; install and use page-builder to build a new Refund Policy Page.
customs-trade-compliance
Codified expertise for customs documentation, tariff classification, duty optimization, restricted party screening, and regulatory compliance across multiple jurisdictions. Informed by trade compliance specialists with 15+ years experience. Includes HS classification logic, Incoterms application, FTA utilization, and…
einbeziehung-online-clickwrap-browsewrap
Für Einbeziehung Online Clickwrap Browsewrap: ordnet Norm, Beweislast und Gegenargument; Ergebnis: Prüfprodukt mit Risiko und nächstem Schritt.
kurzfristige-preiserhoehung-lieferfrist
Für Kurzfristige Preiserhöhung 309: prüft Frist, Form, Zuständigkeit und Eilbedarf; Ergebnis: Fristen- und Risikoampel. Fachgebiet: AGB-Recht-Prüfer. Route: kurzfristige-preiserhoehung-lieferfrist.
plattform-online-gate-rollout-rangfolge
Für Plattform und Online Checkout: ordnet Norm, Beweislast und Gegenargument; Ergebnis: Prüfprodukt mit Risiko und nächstem Schritt. Fachgebiet: AGB-Recht-Prüfer. Route: plattform-online-gate-rollout-rangfolge.
lieferfrist-teillieferung
Für Lieferfrist Teillieferung: prüft Frist, Form, Zuständigkeit und Eilbedarf; Ergebnis: Fristen- und Risikoampel.