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/run-dpia)<a href="https://agentmods.dev/commands/lexbeam-software/eu-ai-governance-plugin/run-dpia"><img src="https://agentmods.dev/badge/commands/lexbeam-software/eu-ai-governance-plugin/run-dpia.svg" alt="Measured on agentmods" 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 | $0.00024 | $0.00448 |
| Opus 5 | $0.00012 | $0.00224 |
| Sonnet 5 | $0.00005 | $0.00090 |
| Haiku 4.5 | $0.00002 | $0.00045 |
Grade A, and why
run-dpia 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 7d 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:run-dpia
Use the dpia-ai skill. This workflow supports the controller; it does not provide legal advice or certify the processing.
Workflow
- Establish controller, processors, purpose, affected persons, geography, data, model and system flow, recipients, transfers, retention, automated effects, and existing controls. If decisive facts are missing, issue a provisional decision and identify them instead of inventing or withholding the available analysis.
- Determine and document the Article 35 trigger. Label supervisory-authority and EDPB/WP29 criteria as guidance rather than statutory text.
- Describe the processing and data flows at system-version level.
- Assess necessity, proportionality, legal basis, data minimisation, accuracy, transparency, rights, Article 22 where relevant, alternatives, and processor controls.
- Build a people-centred risk register with inherent risk, measures, owner, evidence, due date, test method, and residual risk.
- If a DPO is designated, seek and record the DPO’s advice under Article 35(2). Do not require DPO approval as a universal GDPR rule.
- If high residual risk remains without mitigating measures, route to Article 36 prior consultation before processing.
- Assess Article 27 FRIA scope separately using the
ai-act-classificationskill and legal source protocol. Cross-reference overlap; do not treat one assessment as automatically replacing the other.
Output
Produce a versioned DPIA with administrative details, trigger decision, processing and data-flow description, necessity and proportionality, risk register, measures, residual-risk decision, consultation record, controller decision record, review triggers, evidence index, and source note. Keep DPO advice separate from the controller decision.
With --lang de, use idiomatic German, exact GDPR and EU AI Act citations, and explicit controller/DPO role separation.
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.
- 7d ago First seen · 26 lines · 24 tokens per session scan A c06a810a4985
run-dpia 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 24 tokens to every session and 448 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
tcop
Generate a Technology Code of Practice (TCoP) review document for a UK Government technology project.
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.
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.