Claude Code / Codex skill: generate a lean, high-signal CLAUDE.md from scratch via repo scan + focused user interview.

Don't trust an autoresearch paper at face value. Reviewer-side integrity forensics (self-consistency + fabrication), deterministic verdict. 61 signals: 46 integrity hack-patterns (families A–H, verdict-bearing) + 13 zero-weight AI writing-style impressions (AIS) + 2 advisory. Not an opaque AI-text classifier. The dual of ARIS.

Agent Skill for generating AGENTS.md files following the agents.md convention | Claude Code compatible