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/generate-evidence-pack)<a href="https://agentmods.dev/commands/lexbeam-software/eu-ai-governance-plugin/generate-evidence-pack"><img src="https://agentmods.dev/badge/commands/lexbeam-software/eu-ai-governance-plugin/generate-evidence-pack/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/generate-evidence-pack"><img src="https://agentmods.dev/badge/commands/lexbeam-software/eu-ai-governance-plugin/generate-evidence-pack.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 | $0.00437 |
| Opus 5 | $0.00009 | $0.00218 |
| Sonnet 5 | $0.00004 | $0.00087 |
| Haiku 4.5 | $0.00002 | $0.00044 |
Grade A, and why
generate-evidence-pack 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 9d 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:generate-evidence-pack
Use the governance-documentation skill and connected sources. Ask permission before retrieving organisational material not already placed in scope.
Workflow
- Confirm audience, purpose, system scope and versions, cutoff date, actors, classification, jurisdiction, confidentiality, redaction, format, and storage location.
- Build a requirement-to-evidence index before assembling files. When available, use
euaiact_get_obligations,euaiact_annex_iv_checklist, and the versioned summary and official URL fromeuaiact_get_article. Read the complete official provision for exact wording. - Inventory source items with owner, version, approval, location, integrity marker, retention rule, and status.
- Flag missing, stale, conflicting, inaccessible, draft, or unapproved evidence. Do not silently fill gaps with generated prose.
- Preserve originals. Create redacted or audience-specific copies where authorised.
- Validate links, dates, system versions, actor allocation, legal anchors, and the pack index.
Output
Create:
- cover note with scope, cutoff, legal baseline, limitations, and open gaps
- evidence index linking each requirement to an artifact and owner
- selected artifacts or stable references to them
- decision and change log
- missing-evidence action list
- source note
Distinguish Article 11/Annex IV technical documentation, Article 12 logging capability, Article 18 documentation keeping, Article 19 provider logs, Article 26(6) deployer logs, Article 43 conformity assessment, Article 47 declaration, Article 48 CE marking, and Article 49 registration.
Use review pack, not auditor-ready or regulator-ready, unless an identified assurance owner has verified the stated acceptance criteria.
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.
- 9d ago First seen · 33 lines · 18 tokens per session scan A 559ebfeab815
generate-evidence-pack 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 437 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.