agentmods.dev

ai-act-graph

ai-act-graph is a command for Claude Code from Peaky8linders/eu-ai-act-scanner. It costs 35 tokens per session (424 once invoked), scanned A, original, Apache-2.0.

A codebase scanner that builds an interactive diagram of an AI system and marks its components with EU AI Act compliance status. Selecting a component shows related source files, legal requirements, detected gaps, and suggested code changes.

In plain words
What is it for?
Use it to inspect architecture, review AI governance controls, investigate compliance findings, and copy suggested fixes into the relevant files.
Why use it?
It turns a large compliance review into a navigable view of the system, so gaps and their supporting evidence are easier to find. It also connects each issue to a concrete place in the code.

Command for Claude Code

Written for Claude Code: a Claude Code command (commands/*.md).

not rated 5repo 5d ago A scan 35 tokens original Apache-2.0

Good fit Use it to inspect architecture, review AI governance controls, investigate compliance findings, and copy suggested fixes into the relevant files.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/peaky8linders/eu-ai-act-scanner/ai-act-graph
View source ↗ Peaky8linders/eu-ai-act-scanner
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.

agentmods badge for ai-act-graph

README.md
[![agentmods](https://agentmods.dev/badge/commands/peaky8linders/eu-ai-act-scanner/ai-act-graph/github.svg)](https://agentmods.dev/commands/peaky8linders/eu-ai-act-scanner/ai-act-graph)
Your own site
<a href="https://agentmods.dev/commands/peaky8linders/eu-ai-act-scanner/ai-act-graph"><img src="https://agentmods.dev/badge/commands/peaky8linders/eu-ai-act-scanner/ai-act-graph/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 ai-act-graph

Your own site · 80×15
<a href="https://agentmods.dev/commands/peaky8linders/eu-ai-act-scanner/ai-act-graph"><img src="https://agentmods.dev/badge/commands/peaky8linders/eu-ai-act-scanner/ai-act-graph.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 35 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 424 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 $0.00035 $0.00424
Opus 5.5 $0.00014 $0.00170
Sonnet 5.5 $0.00007 $0.00085
Haiku 4.5 $0.00003 $0.00042

Measured 8d ago against content hash 9bf3e61bfd8b, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

ai-act-graph 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 8d 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-graph.md · 40 lines

What it actually says

/ai-act-graph

Generate and explore a standalone, interactive visual context graph of the audited AI system.

Usage

/ai-act-graph [PATH]

Or via CLI:

python -m scanner.cli [PATH] --graph context-graph.html

What it does

  1. Scans the codebase at PATH (defaults to current directory).
  2. Generates an interactive, self-contained visual context graph (context-graph.html).
  3. Renders a node-link visual diagram where:
    • Nodes represent discovered architecture components, agent runtimes, and governance gates.
    • Badges indicate compliance status:
      • ● Compliant (evidence verified in codebase)
      • ● Partial (partial controls found; extra evidence recommended)
      • ● Gap (immediate statutory remediation required)
    • Inspector Panel: Clicking any node opens a comprehensive drilldown:
      • Exact EU AI Act Article & Paragraph grounding
      • Enacted timeline under Digital Omnibus Regulation (EU) 2026/1744
      • Contributing project source files
      • Detected gaps
      • Cross-framework synergies (NIST AI RMF, ISO 42001, OWASP LLM / ASI, GDPR)
      • Recommended Fix: Target file path, rationale, and a production-ready, copyable code patch
      • Grounded real-world incident case studies from the vendored incident corpus
  4. Presents a summary in chat with the path to the interactive HTML artifact and highlights the top gap nodes needing attention.
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. 8d ago First seen · 40 lines · 35 tokens per session scan A 9bf3e61bfd8b

Subscribe to this mod's changes

ai-act-graph is a command published in the GitHub repository Peaky8linders/eu-ai-act-scanner (5 stars, last pushed 5d ago), licensed Apache-2.0. It adds 35 tokens to every session and 424 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-10-09.

AI SafetyLegal and compliancePythonai-governanceclaude-code-plugincomplianceeu-ai-act
Related

Other commands, from other repositories

evidence

Export a signed compliance evidence package as JSON or PDF for regulatory handoff.

airblackbox/airblackbox · 14 tokens

comply

Run a full EU AI Act compliance scan on your Python AI project.

airblackbox/airblackbox · 13 tokens

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.

dingdawg/dingdawg-governance · 0 tokens

tcop

Generate a Technology Code of Practice (TCoP) review document for a UK Government technology project.

tractorjuice/arc-kit · 19 tokens

soa-generator

Generate ISO 27001 Statement of Applicability (SOA) with control selection justifications.

GRCEngClub/claude-grc-engineering · 18 tokens

service-auditor-prep

Generate complete auditor-ready evidence package for SOC 2.

GRCEngClub/claude-grc-engineering · 10 tokens