A codebase scanner for checking evidence related to the European Union Artificial Intelligence Act, the EU law governing certain AI systems. It produces scored findings by compliance area, lists affected files and components, maps the architecture, and prioritizes recommendations.

Use it to scan a project, check whether it falls within the law's scope, filter findings by article, inspect AI-related signals and components, and review prioritized risks.

It helps distinguish projects that are actually AI systems from ordinary codebases and shows where documented compliance evidence is missing. The scores and findings provide a structured starting point for review.

ai-act-scan — Command for Claude Code by Peaky8linders

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/Peaky8linders/eu-ai-act-scanner

Made for: Claude Code.

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.

README.md

[![agentmods](https://agentmods.dev/badge/commands/peaky8linders/eu-ai-act-scanner/ai-act-scan/github.svg)](https://agentmods.dev/commands/peaky8linders/eu-ai-act-scanner/ai-act-scan)

Your own site

<a href="https://agentmods.dev/commands/peaky8linders/eu-ai-act-scanner/ai-act-scan"><img src="https://agentmods.dev/badge/commands/peaky8linders/eu-ai-act-scanner/ai-act-scan/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.

Your own site · 80×15

<a href="https://agentmods.dev/commands/peaky8linders/eu-ai-act-scanner/ai-act-scan"><img src="https://agentmods.dev/badge/commands/peaky8linders/eu-ai-act-scanner/ai-act-scan.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 37 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 1,165 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.

Model	Per session	Once invoked
Fable 5.1	$0.00037	$0.01165
Opus 5	$0.00018	$0.00583
Sonnet 5	$0.00007	$0.00233
Haiku 4.5	$0.00004	$0.00117

Measured 11d ago against content hash 0a292d5fa1a0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

ai-act-scan 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 11d 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/ai-act-scan.md · 93 lines

How it starts

The opening of the file, as written. The whole thing — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/ai-act-scan

Run the EU AI Act compliance scanner on a local codebase and summarise the findings.

Arguments

$1 (optional) — path to scan. Defaults to the current working directory.
--article ARTN — filter results to a single article (e.g. art9, art15, art50).

Behaviour

Run the scanner CLI in JSON mode:
```
python -m scanner.cli "$1" --json
```
If $1 is empty, scan the current directory.
Parse the JSON output. Key fields:
- is_ai_system — bool. Check this first. When false the codebase is out of EU AI Act scope (no AI/ML/agent signal): compliance_scores is empty and overall_compliance_pct is 0.0 but not a compliance measure.
- ai_system_signals — the AI evidence that put the project in scope (e.g. ai_framework:pytorch, model_typology:llm); empty when out of scope.
- scope_note — populated only when is_ai_system is false; explains why scoring was skipped.
- overall_compliance_pct — 0–100 (only meaningful when is_ai_system is true)
- compliance_scores — map of dimension id → 0–100
- components — list of discovered components with component_type, compliance_impact, compliance_dimensions
- risk_indicators — top 10 gap-severity findings
- recommendations — prioritised remediation suggestions
- file_findings — per-file roll-up of findings/gaps/status
If is_ai_system is false: do not present a compliance percentage. State that the project is not an AI system and is out of EU AI Act scope, show scope_note verbatim, and stop (optionally point to CONTRIBUTING.md if the user believes an AI pattern was missed). Otherwise present a summary in this order:
1. Headline: overall compliance % and file count
2. Lowest-scoring dimensions (bottom 3) with article references — use the eu-ai-act-reference skill if the user wants deeper article context
3. Top 3 risk indicators verbatim from the result
4. Top 3 recommendations verbatim
5. Offer to drill into a specific dimension, article, or file
Never invent findings. If the scanner reports zero components, say so and suggest the project may not be an AI system or may use patterns the scanner does not yet recognise (and link to CONTRIBUTING.md for adding an analyzer).

Read the full file on GitHub · 93 lines

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.

11d ago First seen · 93 lines · 37 tokens per session scan A 0a292d5fa1a0

Subscribe to this mod's changes

ai-act-scan 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 37 tokens to every session and 1,165 once invoked, about $0.0002 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.

AI Safety Legal and compliance Planning Python ai-governance claude-code-plugin compliance eu-ai-act

ai-act-scan

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

/ai-act-scan

Arguments

Behaviour

What this file has done since we first saw it

Other commands, from other repositories

evidence

comply

audit

tcop

soa-generator

ssp-section-generate