ai-act-settings

ai-act-settings is a command for Claude Code from Peaky8linders/eu-ai-act-scanner. It costs 46 tokens per session (462 once invoked), scanned A, original, Apache-2.0.

A settings command for an EU AI Act code scanner. It lets you view or change whether scanning uses only static analysis or also your own Claude Code session, and whether approved fixes may be applied automatically.

In plain words
What is it for?
Use it to inspect settings, switch between deterministic and assisted scanning, and enable or disable automatic application of approved fixes.
Why use it?
It makes the scanner's analysis and editing behavior explicit and configurable. This helps teams keep scans offline and read-only by default, or opt into assisted analysis and applying approved edits.

Command for Claude Code

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

Good fit Use it to inspect settings, switch between deterministic and assisted scanning, and enable or disable automatic application of approved fixes.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/peaky8linders/eu-ai-act-scanner/ai-act-settings
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-settings

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

Your own site · 80×15
<a href="https://agentmods.dev/commands/peaky8linders/eu-ai-act-scanner/ai-act-settings"><img src="https://agentmods.dev/badge/commands/peaky8linders/eu-ai-act-scanner/ai-act-settings.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 46 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 462 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 $0.00046 $0.00462
Opus 5 $0.00023 $0.00231
Sonnet 5 $0.00009 $0.00092
Haiku 4.5 $0.00005 $0.00046

Measured 10d ago against content hash ef74704ef279, 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-settings 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.

commands/ai-act-settings.md · 47 lines

What it actually says

/ai-act-settings

View or change how much the scanner leans on your own Claude Code.

Behaviour

  1. To show the current settings:
    python -m scanner.cli --settings
    
    Reports mode, auto_apply, where the values came from (source), and the optional headless LLM-bridge config.
  2. To change a setting, persist it to .eu-ai-act-scanner.toml in the project root:
    python -m scanner.cli --set mode=assisted
    python -m scanner.cli --set auto-apply=true
    
    --set is repeatable; invalid values are rejected.

Settings

  • mode
    • deterministic (default) — pure static analysis. No LLM, no network, no telemetry.
    • assisteduse your own Claude Code power. The slash commands drive this Claude Code session to run a semantic pass over the deterministic findings (/ai-act-scan), answer grounded questions (/ai-act-ask), and apply fixes (/ai-act-scan-fix). No API key and no wrapper are needed — the plugin already runs inside your Claude Code.
  • auto_apply (default false) — in assisted mode, let /ai-act-scan-fix apply approved edits directly with your own edit tools instead of only proposing them. A scan is never destructive unless you opt in.

Notes

  • The deterministic scanner output is always the objective baseline; assisted mode augments it, never overwrites the scores.
  • The headless wrapper bridge (EU_AI_ACT_SCANNER_LLM=…, --llm-status) is a separate path for running the CLI outside Claude Code; it is not required for assisted mode.
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. 10d ago First seen · 47 lines · 46 tokens per session scan A ef74704ef279

Subscribe to this mod's changes

ai-act-settings 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 46 tokens to every session and 462 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.