amylyra

agent-prompt-author

Write, revise, and diagnose system prompts, orchestrator instructions, subagent delegation contracts, tool descriptions, and harness text for LLM agents you build and ship. Use whenever someone wants an agent to behave differently by changing its text — "write a system prompt for X", "improve this orchestrator prompt", "my agent keeps ignoring this rule", "the prompt got worse after I edited it", "add a constraint so it stops doing Y", "write a tool description", "should I run GEPA or DSPy on this", "review this agent prompt", "is this prompt any good", "how much of this is still needed". Also use when a prompt has grown past ~200 lines, when a refinement loop has stopped helping, or before investing in automated prompt optimization. Do NOT use for one-off chat prompts, for CLAUDE.md and repo context files (opposite policy — see Route C), or for brand voice and creative style guides.