signed-audit-trails-recipe — Skills

What it does

Regulated environments (finance, healthcare, critical infrastructure)

CI/CD pipelines where you want to prove that a policy gate held for

Multi-party collaboration where a counterparty wants to verify your

Compliance contexts (EU AI Act Article 12, SLSA provenance for

Read-oriented tools always allowed

Bash allowed for safe command patterns (git, npm, etc.)

Bash rm -rf and similar destructive commands explicitly denied

signed audit trails recipe

Source

Repository: https://github.com/wshobson/agents

signed-audit-trails-recipe FAQ

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. Regulated environments (finance, healthcare, critical infrastructure) CI/CD pipelines where you want to prove that a policy gate held for

What does signed-audit-trails-recipe require?

where you need tamper-evident evidence of agent behavior The auditor does not need to trust the operator's tooling choice: the format review-agent-governance — require Configuration keys: TOOL_NAME, TOOL_INPUT, TOOL_OUTPUT.

How do I install signed-audit-trails-recipe?

Run: npx -y skills add https://github.com/wshobson/agents --skill signed-audit-trails-recipe --agent claude-code — the source lives at github.com/wshobson/agents.

Maintain signed-audit-trails-recipe?

Let people know it's listed here — add the badge (live metrics, light/dark aware) or a plain link to your README or docs.

[signed-audit-trails-recipe on getagentictools](https://getagentictools.com/skills/wshobson-agents-signed-audit-trails-recipe?ref=badge)

npx agentictools info skills/wshobson-agents-signed-audit-trails-recipe

The second line is the CLI lookup for this page — handy in READMEs and docs.