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/Peaky8linders/eu-ai-act-scannerWrote 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/peaky8linders/eu-ai-act-scanner/ai-act-article)<a href="https://agentmods.dev/commands/peaky8linders/eu-ai-act-scanner/ai-act-article"><img src="https://agentmods.dev/badge/commands/peaky8linders/eu-ai-act-scanner/ai-act-article/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/peaky8linders/eu-ai-act-scanner/ai-act-article"><img src="https://agentmods.dev/badge/commands/peaky8linders/eu-ai-act-scanner/ai-act-article.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 | $0.00029 | $0.00715 |
| Opus 5 | $0.00015 | $0.00358 |
| Sonnet 5 | $0.00006 | $0.00143 |
| Haiku 4.5 | $0.00003 | $0.00072 |
Grade A, and why
ai-act-article 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.
How it starts
The opening of the file, as written. The whole thing — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/ai-act-article
Trace a single EU AI Act article from regulation → compliance dimensions → scanner analyzers → findings in the current codebase.
Arguments
$1(required) — article identifier. Acceptsart9,Art. 9,9,ART9, orarticle 9. Also accepts special identifiers:annex-iii,gpai,fria.
Behaviour
- Normalise
$1to the canonical lowercase form (e.g.art9). - Run:
python -m scanner.cli . --article art9 - Parse the filtered JSON. Present the result in this structure:
# Art. 9 — Risk Management **Regulation**: Continuous risk management throughout AI lifecycle (Art. 9(1-9)). **Compliance dimensions**: risk_mgmt, decision_governance **Current compliance in this repo**: - risk_mgmt: 34% - decision_governance: 28% **Evidence found**: - risk_mgmt → tests/test_risks.py - decision_governance → app/decision_hooks.py **Gaps**: - No post-market monitoring plan detected - No residual-risk communication artefact (`RISKS.md`, data card) - If the article has no mapped dimensions in the scanner (e.g. governance articles like Art. 65 on the AI Office), say so explicitly and note that the scanner targets obligations expressible in code/config, not governance/procedural articles.
Article coverage
The scanner currently maps evidence to these articles:
| Article | Dimensions | Focus |
|---|---|---|
| Art. 4 | ai_literacy | Training programmes (usually not code-observable) |
| Art. 9 | risk_mgmt, decision_governance | Risk management process |
| Art. 10 | data_gov | Training data governance |
| Art. 11 | tech_docs | Annex IV technical documentation |
| Art. 12 | logging | Automatic event logging |
| Art. 13 | transparency | User-facing disclosures |
| Art. 14 | human_oversight, decision_governance | Human-in-the-loop controls |
| Art. 15 | security, access_control, infra_mlops, supply_chain | Accuracy, robustness, cybersecurity |
| Art. 17 | quality_management | QMS procedures |
| Art. 26, 27 | deployer_obligations | Deployer/operator duties (often doc-only) |
| Art. 43, 47, 48 | conformity_assessment | CE marking / declarations |
| Art. 50 | transparency, content_transparency | Limited-risk transparency |
| Art. 51, 55 | gpai_systemic_risk | GPAI systemic risk obligations |
| Art. 53 | gpai | GPAI provider obligations |
| Art. 72 | decision_governance | Post-market monitoring |
| Art. 95 | voluntary_codes | Voluntary codes of conduct |
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 · 67 lines · 29 tokens per session scan A 43ed7cbf1597
ai-act-article is a command published in the GitHub repository Peaky8linders/eu-ai-act-scanner (5 stars, last pushed 3d ago), licensed Apache-2.0. It adds 29 tokens to every session and 715 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.
audit
Generate a structured audit report for the current session or a specified time range. The report summarises every governed action, lists any blocked requests, and provides a compliance-ready summary you can download or share.
tcop
Generate a Technology Code of Practice (TCoP) review document for a UK Government technology project.
soa-generator
Generate ISO 27001 Statement of Applicability (SOA) with control selection justifications.
ssp-section-generate
Generate System Security Plan (SSP) sections for NIST 800-53 controls.