Load this skill before answering whenever a request mentions Codex, GPT-5.5, codex commands, or Fable 5, or asks which model or agent should handle, review, implement, or verify something. That includes advisory questions (should Claude or Codex handle this, who should review this branch diff, is this worth delegating), not just direct commands. Also covers delegating bounded implementation, independent code review, data gathering, or runtime verification to Codex; optimizing Fable 5 usage or effort settings; and requests to test a flow, verify UI behavior, inspect a running app, or capture screenshots needing local browser/computer-use automation. Do not use for ordinary implementation or review with no model-ownership question, and not for generic prompt rewriting.
2026-07-08