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 vendor-contract-risk-reviewgit 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/vendor-contract-risk-review)<a href="https://agentmods.dev/skills/microsoft/cat-agent-skills/vendor-contract-risk-review"><img src="https://agentmods.dev/badge/skills/microsoft/cat-agent-skills/vendor-contract-risk-review/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/vendor-contract-risk-review"><img src="https://agentmods.dev/badge/skills/microsoft/cat-agent-skills/vendor-contract-risk-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 44 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00044 | $0.00844 |
| Opus 5 | $0.00022 | $0.00422 |
| Sonnet 5 | $0.00009 | $0.00169 |
| Haiku 4.5 | $0.00004 | $0.00084 |
Grade A, and why
vendor-contract-risk-review 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 8d 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 — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Read the contract for the clauses that commonly cause problems later, flag them clearly, and never present this as a substitute for legal review.
Instructions
-
State the limit up front, in the first response: this is a first-pass flagging exercise to help the user prepare for legal review, not a legal opinion. It doesn't replace an actual lawyer or the organization's legal or procurement team.
-
Get the contract text (uploaded document or pasted text). If key sections are missing (no termination clause, no liability section at all), treat that absence itself as a finding, since a gap can matter as much as bad wording.
-
Read for the clauses that commonly cause disputes or unwelcome surprises:
- Auto-renewal: does the contract renew automatically, and if so, how much notice is required to opt out, and by when?
- Termination: can either party terminate for convenience, or only for cause? What notice period applies? Is there an early-termination fee?
- Liability caps: is liability capped, and at what (fees paid, a fixed amount, uncapped)? Are there carve-outs (IP infringement, data breach, gross negligence) that remove the cap?
- Indemnification: who indemnifies whom, and for what? Is it mutual or one-sided?
- Data and IP: who owns data generated during the engagement? What happens to it on termination? Who owns work product or deliverables?
- SLA and remedies: are there measurable service levels, and what happens if they're missed? Credits, termination right, or nothing stated?
- Pricing and escalation: is pricing fixed for the term, or can it change? If it can escalate, is there a cap on the increase?
- Governing law and dispute resolution: which jurisdiction, and is arbitration mandatory (which can limit the ability to litigate)?
- Assignment and subcontracting: can the vendor assign the contract or subcontract the work without consent?
-
Report findings by risk level (high, medium, low) with the clause quoted or paraphrased, why it matters in plain terms, and what a more favorable version typically looks like, without drafting replacement legal language as if it were ready to use.
-
Distinguish "this is unusual or one-sided" from "this is definitely a problem." Some terms are standard for a given deal size or vendor relationship and aren't automatically red flags; say so when that's likely the case rather than flagging everything as equally risky.
-
Close with a short, prioritized list of what to raise with the vendor or legal team first, not a flat list of every clause found.
What ships with it
2 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.
- 8d ago First seen · 77 lines · 44 tokens per session scan A 8f037b372a6a
vendor-contract-risk-review is a skill published in the GitHub repository microsoft/cat-agent-skills (69 stars, last pushed today), licensed MIT. It adds 44 tokens to every session and 844 once invoked, about $0.0002 per session on Opus 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 2026-09-03.
Other skills, from other repositories
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.
regulatory-research-fallback
Fallback workflow for regulatory research when web extraction tools fail on government PDFs.
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.
gesellschaftsrechtliche-satzungen-agb
Für Gesellschaftsrechtliche Satzungen AGB Abgrenzung: ordnet Norm, Beweislast und Gegenargument; Ergebnis: Prüfprodukt mit Risiko und nächstem Schritt. Fachgebiet: AGB-Recht-Prüfer. Route: gesellschaftsrechtliche-satzungen-agb.
memstack-business-gdpr
Use this skill when the user says 'GDPR', 'data protection', 'privacy compliance', 'DPA', 'DSAR', 'data subject request', 'cookie consent', 'privacy audit', 'CCPA', or asks 'do I need GDPR for this repo'. Scans the repository to detect what personal data is collected, classifies sensitivity, determines whether GDPR…
nda-review
Use when the user uploads or pastes a non-disclosure agreement and asks for review, redline, risk assessment, or a recommendation on whether to sign. Identifies missing standard protections, one-sided or unusual provisions, and operational issues; produces a structured report with severity ratings and citations to…