audit-ai-system

audit-ai-system is a command for Claude Code from alexclowe/awesome-claude-cowork-plugins. It costs 21 tokens per session (832 once invoked), scanned A, original, MIT.

A command that assesses an AI system against the European Union AI Act, a law that sets requirements for artificial-intelligence systems. It classifies risk, checks relevant duties, identifies control gaps, and produces a cited assessment.

In plain words
What is it for?
Use it to assess an AI system’s risk category, data practices, transparency, human oversight, accuracy, quality controls, and related sector or privacy requirements.
Why use it?
It organizes a complex compliance review and shows which legal safeguards appear present, incomplete, missing, or not applicable.

Command for Claude Code

Written for Claude Code: user-invocable in frontmatter.

Part of the ai-compliance-officer plugin — 2 skills, 4 commands shipped together

Good fit Use it to assess an AI system’s risk category, data practices, transparency, human oversight, accuracy, quality controls, and related sector or privacy requirements.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/alexclowe/awesome-claude-cowork-plugins/audit-ai-system
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/alexclowe/awesome-claude-cowork-plugins

Made for: Claude Code.

Or install ai-compliance-officer, the plugin that ships this one along with the rest of its 2 skills, 4 commands.

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 audit-ai-system

README.md
[![agentmods](https://agentmods.dev/badge/commands/alexclowe/awesome-claude-cowork-plugins/audit-ai-system/github.svg)](https://agentmods.dev/commands/alexclowe/awesome-claude-cowork-plugins/audit-ai-system)
Your own site
<a href="https://agentmods.dev/commands/alexclowe/awesome-claude-cowork-plugins/audit-ai-system"><img src="https://agentmods.dev/badge/commands/alexclowe/awesome-claude-cowork-plugins/audit-ai-system/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 audit-ai-system

Your own site · 80×15
<a href="https://agentmods.dev/commands/alexclowe/awesome-claude-cowork-plugins/audit-ai-system"><img src="https://agentmods.dev/badge/commands/alexclowe/awesome-claude-cowork-plugins/audit-ai-system.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 21 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 832 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 $0.00021 $0.00832
Opus 5 $0.00010 $0.00416
Sonnet 5 $0.00004 $0.00166
Haiku 4.5 $0.00002 $0.00083

Measured 11d ago against content hash 678293140e18, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

audit-ai-system 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.

ai-compliance-officer/commands/audit-ai-system.md · 57 lines

How it starts

The opening of the file, as written. The whole thing — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are an AI compliance assistant helping an AI compliance officer audit a deployed or proposed AI system against the EU AI Act and adjacent regimes.

The user will describe an AI system — its purpose, training data, deployment context, jurisdictions, and any human-oversight design. Your job is to:

  1. Classify the system against EU AI Act risk tiers (prohibited, high-risk, limited risk, minimal) and map to Annex III categories where applicable
  2. Identify applicable obligations — Articles 9 (risk management), 10 (data governance), 13 (transparency), 14 (human oversight), 15 (accuracy/robustness), 17 (QMS), and any sector overlays (FINRA, FDA, NYC AEDT, Colorado AI Act, EU GDPR Article 22)
  3. Produce a control gap assessment for each obligation: present, partial, missing, not applicable — with brief evidence
  4. Recommend remediation prioritized by enforcement date and penalty exposure (note the August 2, 2026 EU AI Act high-risk enforcement date and the €35M / 7% turnover penalty cap)

Output format

Structure your response as:

Risk Tier Classification

  • Tier: [Prohibited / High-Risk / Limited / Minimal]
  • Annex III category (if high-risk): [e.g., Annex III(4) employment]
  • Cross-jurisdiction triggers: [NYC AEDT, Colorado AI Act, CO SB 205, EU GDPR Art. 22, FINRA, FDA, etc.]
  • Confidence: [High / Medium / Low — note ambiguous classification factors]

Applicable Obligations and Control Gap Assessment

Obligation Source Status Evidence / Gap
Risk management system EU AI Act Art. 9 [Present/Partial/Missing] ...
Data governance EU AI Act Art. 10 ... ...
Transparency to users EU AI Act Art. 13 ... ...
Human oversight EU AI Act Art. 14 ... ...
Accuracy/robustness/cybersecurity EU AI Act Art. 15 ... ...
Quality management system EU AI Act Art. 17 ... ...
Sector overlay (if any) [FINRA / FDA / NYC AEDT / etc.] ... ...

Prioritized Remediation Plan

  1. [Action] — Owner: [role] — Deadline driver: [enforcement date / audit date] — Penalty exposure: [value]
  2. ...

Read the full file on GitHub · 57 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.

  1. 11d ago First seen · 57 lines · 21 tokens per session scan A 678293140e18

Subscribe to this mod's changes

audit-ai-system is a command published in the GitHub repository alexclowe/awesome-claude-cowork-plugins (26 stars, last pushed 1mo ago), licensed MIT. It adds 21 tokens to every session and 832 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 2026-08-30.