How to Install the AI Compliance Officer Claude Plugin (Cowork & Code)

Don't want to install anything? You don't have to. The free web tools for AI compliance officers on The AI Career Lab give you the same pre-built workflows in your browser — five runs a day on a free account, no terminal, no install. Create a free account if you'd rather skip straight to the tools.

The AI Compliance Officer Claude plugin from The AI Career Lab is the fastest way to turn Claude into an AI-compliance-aware co-worker. It bundles 4 pre-built slash commands and 2 auto-activating skills that already know what working AI compliance officers actually do — pre-legal risk classification under the EU AI Act, regulatory update triage against your system inventory, QMS and conformity assessment starting structures, and autonomous-agent eval harness building.

Every output from this plugin is framed as preparatory analysis, not regulatory determination. Final classification, conformity assessment, and supervisory deployment decisions remain with legal counsel, the notified body, and the responsible compliance/risk function.

The plugin works in both runtimes Claude offers:

• Claude Cowork — the chat product at claude.ai. The easiest path. Requires a paid Claude plan (Pro, Max, Team, or Enterprise).
• Claude Code — the terminal CLI. Particularly useful for AI compliance officers since Claude Code can read your regulatory documents (PDFs of guidance, system inventory CSVs, prior assessments) directly. Requires Node.js + npm.

What this plugin gives you

In this plugin you get:

• /risk-classification — pre-legal directional screen for EU AI Act tier classification (Annex III, Article 6(1) safety-component route, GPAI obligations) plus US state overlays. Produces questions for legal counsel and notified body
• /regulatory-triage — triages a new regulatory update against your AI system inventory with binding-vs-advisory framing and per-system severity tagging
• /qms-package — drafts a starting structure for the Article 17 QMS (13 elements) and Annex IV technical documentation. References existing ISO/IEC certifications
• /agent-eval-harness — builds a pre-deployment evaluation harness for autonomous agents in regulated contexts with quantitative pass/fail thresholds

Which runtime should you use?

Use Claude Cowork if:

• You already use claude.ai for chat work
• You prefer a graphical interface to a terminal
• You don't want to install anything else on your machine
• You have a paid Claude plan (Pro, Max, Team, or Enterprise)

Use Claude Code if:

• You're already in a terminal alongside your compliance documentation
• You want Claude to read regulatory PDFs, your system inventory CSV, or prior assessments directly
• You're on a free Claude account (Claude Code plugin install does not require a paid plan)

Path A: Install in Claude Cowork (easiest, no command lines)

1. Open claude.ai in your browser and sign in.
2. Make sure you're on a paid plan (Pro, Max, Team, or Enterprise).
3. Open the plugin settings and click Add marketplace.
4. In the modal, paste this into the URL field:

alexclowe/awesome-claude-cowork-plugins

5. Click Sync. Claude Cowork pulls the marketplace catalog from the public alexclowe/awesome-claude-cowork-plugins repo.
6. Browse the marketplace. Find the AI Compliance Officer plugin and click Install.

Path B: Install in Claude Code (terminal CLI, two commands)

One-time Claude Code setup

1. Install Claude Code. Open a terminal and run:

npm install -g @anthropic-ai/claude-code

2. Sign in once. Run claude in your terminal and follow the sign-in flow.

Install the plugin

Inside Claude Code, run these two commands:

/plugin marketplace add alexclowe/awesome-claude-cowork-plugins
/plugin install ai-compliance-officer@awesome-claude-cowork-plugins

To verify, type /help and you should see the new commands listed alongside Claude Code's built-ins.

Your first command

For most AI compliance officers, the highest-leverage starting point is the risk classification:

/risk-classification

When you run it, Claude asks for the system description, intended purpose (per EU AI Act Article 3(12)), deployment jurisdictions, provider vs deployer role, and system context. The output is flagged likely tiers and Annex categories, classification rationale with Article references, and direct questions for legal counsel and notified body.

That output goes to your next legal review meeting. It's preparatory analysis — counsel produces the actual classification.

First 4 workflows to try after install

1. Risk classification — /risk-classification in the plugin, or /tools/ai-compliance-risk-classification on the web. Run for one system in your inventory
2. Regulatory update triage — /regulatory-triage in the plugin, or /tools/ai-compliance-regulatory-update-triage on the web. Run on the next material guidance document that lands
3. QMS package — /qms-package in the plugin, or /tools/ai-compliance-qms-package on the web. Run for your next high-risk system going through QMS work
4. Agent eval harness — /agent-eval-harness in the plugin, or /tools/ai-compliance-agent-eval-harness on the web. Run before the next autonomous agent supervisory sign-off

Skills you get for free

This plugin also includes Claude Skills that activate automatically when you're working on relevant tasks:

• Pre-Legal Framing Discipline — when regulatory determinations come up, automatically frames output as preparatory analysis with explicit "consult counsel to confirm" framing throughout. Refuses to produce confident binding-status conclusions
• Provider vs Deployer Distinction — when describing AI system obligations, automatically distinguishes provider obligations (CE marking, declaration of conformity, technical documentation, QMS) from deployer obligations (data-input monitoring, log retention, human oversight, FRIA for public-service Annex III deployers)

The first time the pre-legal-framing skill auto-activates and refuses to give you a confident "this system is high-risk under Annex III(4)" determination — instead surfacing "likely flagged for Annex III(4) — consult counsel to confirm classification and Article 6(3) exemption applicability" — you'll see the difference between using Claude generically and using Claude as an AI compliance officer's co-worker.

Where to go from here

• Claude Cowork playbook for AI compliance officers — the full setup guide with the five high-leverage prompt structures
• Free web tools for AI compliance officers — same workflows, browser-based, no install required
• Best AI Tools for AI Compliance Officers in 2026 — the broader landscape including Claude, GRC platforms (Credo AI, Trustible, Holistic AI), model registries, bias-audit tooling, regulatory trackers
• AI for AI Compliance Officers guide — the working playbook for governing the system without becoming the single point of failure

Common issues

I don't see the "Add marketplace" option in Claude Cowork. You need to be on a paid plan. If you're on a free plan, install via Claude Code instead — it's free.

The marketplace sync failed in Claude Cowork. Double-check the URL field has exactly alexclowe/awesome-claude-cowork-plugins — a GitHub owner/repo format, no https://, no trailing slash.

The slash commands aren't showing up after install. Start a new chat (Cowork) or type /help (Claude Code). If you see the built-in commands but not the new ones, the install didn't complete — re-run the install.

I want to use this without installing anything. Use the free web tools instead. Same workflows, browser-based, no install or paid plan.

Ready to try it without installing

Create your free AI Career Lab account and try the AI compliance officer tools today. No credit card required.

---

This article is general guidance for AI compliance officers. The EU AI Act (Regulation (EU) 2024/1689), FINRA AI guidance, SEC AI risk alerts, FDA SaMD, HIPAA, GDPR Article 22, US state AI laws (Colorado AI Act, NYC Local Law 144 AEDT, Illinois BIPA, California CPRA), and related regulatory frameworks are evolving and jurisdiction-specific. The tools described produce pre-legal directional analysis and starting structures — they do not produce regulatory determinations, conformity assessments, or supervisory sign-offs. Legal counsel, notified bodies, and the responsible compliance and risk functions remain authoritative for those determinations.