Verifies AI agent code before it ships: hardcoded secrets, unbounded loops and retries, hallucinated tool references, oversized prompts, and language-specific quality checks.
No telemetry.
Skills 5 in the Claude listing
verification Full agent verification suite. Verify language Language-specific verification for Python, TypeScript/JavaScript, and Go. Verify patterns Verify AI agent patterns including loop safety, retry limits, tool consistency, context size, and graph cycle analysis. Verify quality Verify code quality including naming conventions, organization, documentation, and general best practices. Verify security Verify code for security issues including hardcoded secrets, input validation, error exposure, and dependency vulnerabilities.