Open source by default
The 10 Clawproof checks are open source (MIT) and packaged as a Claude skill. Clone the repo, audit your agent, run the skill inside Claude Code, or propose a new check from your own production failures.
The repo →
10 YAML checks, the bundled Claude skill, schema docs, validation workflow. MIT licensed. Star it if it saves you a Monday morning.
The Claude skill →
Drop it into any Claude Code or Claude Agent SDK project. Ask the agent to audit your codebase. Get a scored report back.
Install the skill
# Clone the repo git clone https://github.com/lexbeam-software/clawproof-checks.git /tmp/clawproof # Copy the skill into your Claude Code project mkdir -p .claude/skills cp -r /tmp/clawproof/skills/clawproof-audit .claude/skills/ # In Claude Code: > /skills # Select: clawproof-audit > audit this agent for production readiness
Use it programmatically
Every check is bundled into a single JSON file (checks.json) for programmatic use outside Claude. Read the schema at checks/SCHEMA.md.
Roadmap
- ✓ 10 checks as YAML (v1)
- ✓ Claude skill + audit-report template
- ✓ Bundled
checks.jsonfor programmatic use - □ MCP server exposing
list_checksandrun_checktools (planned) - □ Language-specific playbooks (PRs welcome)
- □ German and French translations (PRs welcome)
Contributing. New failure modes, additional checklist items, translations, language-specific playbooks — all welcome. See CONTRIBUTING.md. For private disclosure, reach out via the address on the Impressum.