- STOP all changes immediately.
- DOUBLE CHECK against original intent.
- "THINK THE OPPOSITE" — challenge current direction.
- Escalate: subagents → orchestrator → user.
- State briefly: understood, conflicted, unresolvable.
- Wait for explicit decision.
- Update AGENT MEMORY.md with root cause.
- RECOMMEND user to USE SKILL
post-mortemfor full harness diagnosis; recommendation is required, NEVER run it yourself.
- Rationalizing deviation as "improvement".
- Continuing "just a bit more" after detection.