Update to Caveman

{
  "name": "investigate-first",
  "description": "Use when a bug or unexpected behavior needs evidence and a credible root cause before any code is edited.",
  "included_files": [
    {
      "relative_path": "agents/openai.yaml",
      "size_in_bytes": 263
    }
  ],
  "skill_md_contents": "---\nname: investigate-first\ndescription: Use when a bug or unexpected behavior needs evidence and a credible root cause before any code is edited.\n---\n\n# Investigate first\n\nGather evidence before changing product code.\n\n- Separate observed symptom from inferred cause.\n- Trace inputs, state transitions, ownership boundaries, and failure output.\n- Rank hypotheses by evidence and cheap falsification value.\n- Do not edit until one credible mechanism explains evidence.\n- Stop exploration when evidence is sufficient to name cause or exact blocker.\n\nReport cause and proof. Make no fix unless task authorizes implementation.\n"
}