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 global-greenwashing-claim-auditorgit 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/global-greenwashing-claim-auditor)<a href="https://agentmods.dev/skills/microsoft/cat-agent-skills/global-greenwashing-claim-auditor"><img src="https://agentmods.dev/badge/skills/microsoft/cat-agent-skills/global-greenwashing-claim-auditor/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/global-greenwashing-claim-auditor"><img src="https://agentmods.dev/badge/skills/microsoft/cat-agent-skills/global-greenwashing-claim-auditor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00096 | $0.01175 |
| Opus 5.5 | $0.00038 | $0.00470 |
| Sonnet 5.5 | $0.00019 | $0.00235 |
| Haiku 4.5 | $0.00010 | $0.00118 |
Grade A, and why
global-greenwashing-claim-auditor 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 1mo 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 — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Global Greenwashing Claim Auditor
Audit public-facing environmental claims using the bundled global vocabulary, regional taxonomy, legal research, and detection method. Treat the result as compliance triage, not legal advice.
Required references
Read these before making final findings:
references/Greenwashing-vocab.mdreferences/greenwashing-risk-taxonomy.mdreferences/greenwashing-detection.mdreferences/greenwashing-analysis-research.md
Use ANY only for universal vocabulary and claim-construction risks. Use CA, EU, and UK only when the corresponding regional rule, law, regulation, or guidance supports the finding.
Workflow
- Determine the input type and intended markets. If markets are unknown, analyze
ANY,CA,EU, andUK, but mark regional applicability as unconfirmed. - Extract all claim-bearing text while preserving source locations:
- CSV: row and column.
- XLSX: sheet and cell.
- DOCX: paragraph or table cell.
- PPTX: slide and shape.
- Conversation: supplied text block.
- URL: page URL and extracted block.
- Run the matching script for first-pass triage.
- Review every flagged unit against the full references. Keyword matches are leads, not verdicts.
- Add claims missed by keywords, including implied claims, imagery, omissions, comparisons, labels, scope overreach, lifecycle issues, and unsupported future commitments.
- Report separate findings for every applicable jurisdiction and retain the highest risk as the overall rating.
- Suggest a bounded rewrite, but never invent evidence, percentages, certifications, methods, or environmental benefits.
Scripts
Run scripts from the skill directory with Python 3. Use workspace-relative paths so commands remain portable across supported environments.
CSV
python scripts/analyze_csv.py "claims.csv" --jurisdictions CA EU UK --out audit.json
Use --text-column NAME repeatedly to choose columns. Without it, the script scans text-like columns and then all string columns if necessary.
What ships with it
15 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.
- metadata.json 643 B
- README.md 4.7 KB
- references/greenwashing-analysis-research.md 18 KB
- references/greenwashing-detection.md 14 KB
- references/greenwashing-risk-taxonomy.md 14 KB
- references/greenwashing-rules.json 3.0 KB
- references/Greenwashing-vocab.md 15 KB
- scripts/analyze_csv.py 107 B runs code
- scripts/analyze_docx.py 108 B runs code
- scripts/analyze_pptx.py 108 B runs code
- scripts/analyze_text.py 108 B runs code
- scripts/analyze_url.py 107 B runs code
- scripts/analyze_xlsx.py 108 B runs code
- scripts/audit_core.py 26 KB runs code
- scripts/test_audit_core.py 6.0 KB runs code
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.
- 1mo ago First seen · 136 lines · 96 tokens per session scan A 62af549291ed
global-greenwashing-claim-auditor is a skill published in the GitHub repository microsoft/cat-agent-skills (93 stars, last pushed today), licensed MIT. It adds 96 tokens to every session and 1,175 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 2026-08-30.
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…