Update to Caveman

{
  "name": "safe-refactor",
  "description": "Use when restructuring code while preserving observable behavior and proving the refactor with tests or other evidence.",
  "included_files": [
    {
      "relative_path": "agents/openai.yaml",
      "size_in_bytes": 265
    }
  ],
  "skill_md_contents": "---\nname: safe-refactor\ndescription: Use when restructuring code while preserving observable behavior and proving the refactor with tests or other\n  evidence.\n---\n\n# Safe refactor\n\nDefine behavior-preservation boundary and establish verification before structural edits.\n\n- Keep feature changes outside refactor.\n- Move one ownership boundary at a time.\n- Preserve public interfaces, failure behavior, ordering, and compatibility unless explicitly scoped.\n- Keep intermediate states buildable and testable.\n- Avoid dependency or configuration growth without correctness need.\n\nRun same proof after change. Stop when behavior matches and requested structure is achieved.\n"
}