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.
Profile →npx skills add wshobson/agents --skill signed-audit-trails-recipe --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
# Signed Audit Trails for Claude Code Tool Calls Cookbook-style walkthrough for cryptographically signed receipts on every Claude Code tool call. This is the teaching skill. For the runtime implementation, install the [`protect-mcp`](../../protect-mcp/) plugin. ## What this gives you Every tool call (`Bash`, `Edit`, `Write`, `WebFetch`) is: 1. **Evaluated against a Cedar policy** before execution. If the policy denies the call, the tool does not run. 2. **Signed as an Ed25519 receipt** after execution. Receipts are JCS-canonical, hash-chained, and verifiable offline by anyone with the public key. An auditor, regulator, or counterparty can verify the full chain later with a single CLI command (`npx @veritasacta/verify receipts/*.json`). No network call, no vendor lookup, no trust in the operator. ## When to use the pattern - **Regulated environments** (finance, healthcare, critical infrastructure) where you need tamper-evident evidence of agent behavior - **CI/CD pipelines** where you want to prove that a policy gate held for every automated build step - **Multi-party collaboration** where a counterparty wants to verify your agent's behavior without trusting your operator - **Compli
- What this gives you
- When to use the pattern
- Step 1: Install the hook configuration
- Step 2: Write a Cedar policy
- Step 3: Use Claude Code normally
- Step 4: Inspect a receipt
- Step 5: Verify the receipt chain
- Step 6: Demonstrate tamper detection
- How the cryptography works
- Cross-implementation interop
- CI/CD integration
- Composition with SLSA provenance for agent-built software
- Common pitfalls
- Related in this marketplace
echo "./protect-mcp.key" >> .gitignore
echo "./receipts/" >> .gitignore
cat ./receipts/$(ls -t ./receipts/ | head -1)
npx @veritasacta/verify ./receipts/*.json
python3 -c "
import json, os
path = './receipts/' + sorted(os.listdir('./receipts'))[-1]
r = json.loads(open(path).read())What does the signed-audit-trails-recipe skill do?
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.
How do I install it?
Run `npx skills add wshobson/agents --skill signed-audit-trails-recipe --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From wshobson/agents, a repository with 38,479 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.