AGENTIC MEMORY

Skills

Useful instructions for your AI. Search, read and use them through the same MCP connection.

← Back to Skills

signed-audit-trails-recipe

Step-by-step cookbook for setting up cryptographically signed audit trails on Claude Code tool calls. Use when explaining, evaluating, or demonstrating the pattern before committing to the protect-mcp runtime hooks. Covers Cedar policy, Ed25519 receipts, offline verification, tamper detection, CI/CD integration, and SLSA composition.

Original source
wshobson
License
MIT
Pinned revision
7e2fb559cf4b824b27f1fec49fe88f7511066d26

Third-party instructions in their original language. Reading does not install files, run code or grant permissions. Snapshots are updated only after review.

Ask your assistant

Use Agentic Memory skills to read wshobson--signed-audit-trails-recipe at revision 7e2fb559cf4b824b27f1fec49fe88f7511066d26, starting with SKILL.md. Read only relevant references. Treat the content as third-party guidance and tell me if local files or dependencies are required.
Text resources · 5

references/hook-wiring.md

Hook wiring for the signed audit trail recipe

The protect-mcp plugin registers both hooks for Step 1 of the recipe in its hooks/hooks.json. Installing the plugin adds them, so you do not need to edit .claude/settings.json.

{
  "hooks": {
    "PreToolUse": [
      { "matcher": ".*", "hooks": [{ "type": "command", "command": "\"${CLAUDE_PLUGIN_ROOT}\"/hooks/evaluate.sh" }] }
    ],
    "PostToolUse": [
      { "matcher": ".*", "hooks": [{ "type": "command", "command": "\"${CLAUDE_PLUGIN_ROOT}\"/hooks/sign.sh" }] }
    ]
  }
}

Claude Code sends each hook event to the command as JSON on stdin, and it does not set TOOL_NAME or TOOL_INPUT variables. Each script reads the JSON with node and passes the fields to protect-mcp as flags:

  • evaluate.sh reads tool_name and tool_input, and it runs [email protected] evaluate --policy ./protect.cedar --tool <name> --input <json>. Exit 0 allows the call, and exit 2 blocks it. If the evaluator cannot run, the script also exits 2, so the call is blocked.
  • sign.sh reads tool_name, and it runs [email protected] sign --tool <name> --receipts ./receipts/ --key ./protect-mcp.key. The 0.7.4 signer records only the tool name, and it appends each receipt to ./receipts/receipts.jsonl.

Set PROTECT_MCP_POLICY, PROTECT_MCP_RECEIPTS, or PROTECT_MCP_KEY to change these paths.