paniolo-scan — scan and remediate

Diagnose the repo's AI-agent harness with the deterministic @paniolo/scan CLI, then fix the findings in the working tree. The scanner is read-only — it never writes files; you (the agent) apply every change.

When to use

Use this skill when the user wants to measure or improve how well a repository is set up for coding agents — for example: "scan my harness", "check my AI agent setup", "audit CLAUDE.md / AGENTS.md", "optimize my agent rules and skills", or the /paniolo-scan trigger. Works in any harness: Claude Code, Cursor, Copilot, Codex, Gemini, and Antigravity.

Flow

1. Scan (deterministic, no writes)

Run the published CLI and capture JSON: