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.
git clone --depth 1 https://github.com/lexbeam-software/eu-ai-governance-pluginWrote 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/commands/lexbeam-software/eu-ai-governance-plugin/assess-ai-vendor)<a href="https://agentmods.dev/commands/lexbeam-software/eu-ai-governance-plugin/assess-ai-vendor"><img src="https://agentmods.dev/badge/commands/lexbeam-software/eu-ai-governance-plugin/assess-ai-vendor/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/commands/lexbeam-software/eu-ai-governance-plugin/assess-ai-vendor"><img src="https://agentmods.dev/badge/commands/lexbeam-software/eu-ai-governance-plugin/assess-ai-vendor.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 | $0.00018 | $0.00405 |
| Opus 5 | $0.00009 | $0.00202 |
| Sonnet 5 | $0.00004 | $0.00081 |
| Haiku 4.5 | $0.00002 | $0.00040 |
Grade A, and why
assess-ai-vendor 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 10d 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.
What it actually says
/eu-ai-governance:assess-ai-vendor
Use the ai-vendor-assessment skill. Follow the legal source protocol. See connected sources.
Workflow
- Identify the exact service, version, contract entities, intended use, deployment, geography, data, model chain, and documents reviewed. For a sparse file, issue a provisional matrix and
hold pending evidencerecommendation rather than inventing terms or withholding useful triage. - Separate signed terms, incorporated policies, technical evidence, independent assurance, marketing claims, and missing material.
- Determine all AI Act roles and check Article 25 role-change triggers. Classify the intended use before applying Article 26 or high-risk provider duties.
- When available, use the Lexbeam MCP to validate classification, obligations, deadlines, and decisive provisions.
- Review AI Act evidence, GPAI and downstream support, GDPR terms, transfers, security, monitoring, incidents, audit access, change control, exit, liability, and insurance.
Output
Return:
- recommendation:
approve,approve with conditions,hold, orreject - scope, facts, assumptions, and document register
- role and classification analysis
- evidence matrix with
provided,missing,conflicting, ornot applicable - ranked issues and redlines, each labelled legal duty, contractual control, or recommended practice
- pre-signing conditions and operating controls
- unresolved questions and source note
Quote contract language sparingly and include page or section references. Do not rely on static vendor profiles or uncited claims. Do not state that fines are automatically insurable or indemnifiable.
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.
- 10d ago First seen · 31 lines · 18 tokens per session scan A 91e23b6032f7
assess-ai-vendor is a command published in the GitHub repository lexbeam-software/eu-ai-governance-plugin (2 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 18 tokens to every session and 405 once invoked, about $0.0001 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 2026-08-31.
Other commands, from other repositories
evidence
Export a signed compliance evidence package as JSON or PDF for regulatory handoff.
comply
Run a full EU AI Act compliance scan on your Python AI project.
tcop
Generate a Technology Code of Practice (TCoP) review document for a UK Government technology project.
ai-act-scan
Scan a codebase for EU AI Act compliance evidence and gaps. Produces a dimension-scored report with per-file findings, architecture graph, and prioritized recommendations.
ai-act-article
Show which analyzers, compliance dimensions, and current findings in this codebase map to a specific EU AI Act article.
ai-act-scan-fix
Scan a codebase, then propose concrete remediation (code edits, new files, tests) for the top compliance gaps. Does NOT auto-apply — always shows the plan first.