generate-evidence-pack

generate-evidence-pack is a command for Claude Code from lexbeam-software/eu-ai-governance-plugin. It costs 18 tokens per session (437 once invoked), scanned A, original, Apache-2.0.

A command for compiling traceable evidence about how an organisation governs an AI system into a review pack. The pack is scoped to a defined audience, purpose, system, time period, and legal context.

In plain words
What is it for?
Use it to create a cover note, evidence index, source inventory, and authorised redacted copies for an AI governance review.
Why use it?
It helps reviewers find which documents support each requirement and exposes missing, outdated, conflicting, inaccessible, draft, or unapproved evidence.

Command for Claude Code

Written for Claude Code: argument-hint in frontmatter.

Part of the eu-ai-governance plugin — 6 skills, 6 commands, 1 MCP server shipped together

Good fit Use it to create a cover note, evidence index, source inventory, and authorised redacted copies for an AI governance review.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/lexbeam-software/eu-ai-governance-plugin/generate-evidence-pack
Install

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.

Clone the repo
git clone --depth 1 https://github.com/lexbeam-software/eu-ai-governance-plugin

Made for: Claude Code.

Or install eu-ai-governance, the plugin that ships this one along with the rest of its 6 skills, 6 commands, 1 MCP server.

Wrote 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.

agentmods badge for generate-evidence-pack

README.md
[![agentmods](https://agentmods.dev/badge/commands/lexbeam-software/eu-ai-governance-plugin/generate-evidence-pack/github.svg)](https://agentmods.dev/commands/lexbeam-software/eu-ai-governance-plugin/generate-evidence-pack)
Your own site
<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.

agentmods 80×15 button for generate-evidence-pack

Your own site · 80×15
<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>
Per session 18 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 437 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured 9d ago against content hash 559ebfeab815, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

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.

commands/generate-evidence-pack.md · 33 lines

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

  1. Confirm audience, purpose, system scope and versions, cutoff date, actors, classification, jurisdiction, confidentiality, redaction, format, and storage location.
  2. 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 from euaiact_get_article. Read the complete official provision for exact wording.
  3. Inventory source items with owner, version, approval, location, integrity marker, retention rule, and status.
  4. Flag missing, stale, conflicting, inaccessible, draft, or unapproved evidence. Do not silently fill gaps with generated prose.
  5. Preserve originals. Create redacted or audience-specific copies where authorised.
  6. 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.

Changes

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.

  1. 9d ago First seen · 33 lines · 18 tokens per session scan A 559ebfeab815

Subscribe to this mod's changes

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.