agentic-audit-hook 0.1.0

CLI hook for Claude Code and Cowork — automatic compliance monitoring for AI coding agents

AgentAudit Hook CLI

CLI for auditing Claude Code and Cowork sessions automatically.

Every tool call — file reads, writes, shell commands, web fetches — is logged, classified, and audit-ready with zero token overhead.

Install

pip install agentic-audit-hook

Setup

Add hooks to Claude Code:

// ~/.claude/settings.json
{
  "hooks": {
    "PreToolUse": [
      {
        "matcher": "",
        "hooks": [
          {"type": "command", "command": "agentaudit-hook pre"}
        ]
      }
    ],
    "PostToolUse": [
      {
        "matcher": "",
        "hooks": [
          {"type": "command", "command": "agentaudit-hook post"}
        ]
      }
    ]
  }
}

Set environment variables:

export AGENTAUDIT_API_KEY="aa_live_xxxxx"
export AGENTAUDIT_BASE_URL="http://localhost:8000"

Commands

Command	Hook	Description
agentaudit-hook pre	PreToolUse	Classify risk, optionally block
agentaudit-hook post	PostToolUse	Log completion
agentaudit-hook session-start	SessionStart	Log session start
agentaudit-hook session-end	SessionEnd	Log session end

Links

• Claude Code integration guide
• Cowork integration guide
• GitHub

License

Apache 2.0