Testing Prompts With Subagents Test any prompt before deployment: commands, hooks, skills, subagent instructions, or production LLM prompts. Overview Testing prompts is TDD applied to LLM instructions. Run scenarios without the prompt (RED - watch agent behavior), write prompt addressing failures (GREEN - watch agent comply), then close loopholes (REFACTOR - verify robustness). Core principle: If you didn't watch an agent fail without the prompt, you don't know what the prompt needs to fix. REQUIRED BACKGROUND: - You MUST understand - defines RED-GREEN-REFACTOR cycle - You SHOULD understand s…