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 validity-classifygit 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/validity-classify)<a href="https://agentmods.dev/skills/microsoft/cat-agent-skills/validity-classify"><img src="https://agentmods.dev/badge/skills/microsoft/cat-agent-skills/validity-classify/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/validity-classify"><img src="https://agentmods.dev/badge/skills/microsoft/cat-agent-skills/validity-classify.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 | $0.00065 | $0.00402 |
| Opus 5.5 | $0.00026 | $0.00161 |
| Sonnet 5.5 | $0.00013 | $0.00080 |
| Haiku 4.5 | $0.00006 | $0.00040 |
Grade A, and why
validity-classify 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
Validity Classify (Govern)
Purpose
The compliance determination IS the work: valid / partial / unsupported with entitled-vs-claimed arithmetic shown (#2.1-#2.3). Lift runs only with the account P&L foundation (#3.1).
When to use
After claim-match in every case; on any write-off question.
Inputs
matched.json + config/rgm-scoping.json (+ scan extract when lift is in scope).
Steps
- Run scripts/deduction_classify.py --matched matched.json --scoping rgm-scoping.json --out governed.json
- Quote verdicts and calculations verbatim. "Not worth chasing" is a business decision a human takes with the number in front of them - the engine quantifies, it never writes off (#2.4).
- If scoping skips lift, say so and why - scoped-out is a design decision, not a failure (#3.1).
Output
governed.json - the {validity, promo_lift} hop.
Grounding requirements
Every verdict cites the signed term and rule section; every disputable amount shows its calculation.
Constraints
- The engine decides; the model never adjusts an entitled amount or softens a partial to valid.
- No credits posted, no write-offs, no term changes (plugin boundary).
Escalation / uncertainty
Confidence < 0.75 -> analyst review before the dispute goes out (#4).
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 · 27 lines · 65 tokens per session scan A e19bb8119eac
validity-classify is a skill published in the GitHub repository microsoft/cat-agent-skills (93 stars, last pushed today), licensed MIT. It adds 65 tokens to every session and 402 once invoked, about $0.0003 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
expense-review-policy
Review invoices and contracts against accounts-payable policy before human approval.
audit-support
Support SOX 404 compliance with control testing methodology, sample selection, and documentation standards. Use when generating testing workpapers, selecting audit samples, classifying control deficiencies, or preparing for internal or external audits.
kyc-doc-parse
Parse an investor or client onboarding packet into structured KYC fields — identity, ownership, control, source of funds, and document inventory. Use as the first step of KYC screening; output feeds the rules engine.
ma-playbook
M&A strategy for acquiring companies or being acquired. Due diligence, valuation, integration, and deal structure. Use when evaluating acquisitions, preparing for acquisition, M&A due diligence, integration planning, or deal negotiation.
subcontractor-payment-tracker
Track subcontractor payments, lien waivers, and compliance. Manage payment schedules and documentation.
fiscaliste
Fiscaliste IA pour la fiscalité personnelle des particuliers français : optimisation et déclaration de l'impôt sur le revenu, IFI, revenus du capital, revenus fonciers, equity salarial, crypto-actifs et PER. Couvre le calcul de l'IR (barème, quotient familial, décote, PAS, CEHR, revenus exceptionnels), la déclaration…