Spawn cost < task cost → delegate. Otherwise, do it yourself.
| Tier | Models | Cost | Use for |
|---|---|---|---|
| ------ | -------- | ------ | --------- |
| Small | Haiku, GPT-4o-mini, Gemini Flash | ~$0.25/1M | Search, summarize, format, classify |
| Medium | Sonnet, GPT-4o, Gemini Pro | ~$3/1M | Code, analysis, synthesis |
| Large | Opus, o1, Gemini Ultra | ~$15/1M | Architecture, complex reasoning |
Rule of thumb: Start with smallest tier. Escalate only if output quality insufficient.
Every spawn must include:
1. TASK: Single clear deliverable (not "help with X")
2. MODEL: Explicit tier choice
3. CONTEXT: Only files/info needed (never full history)
4. OUTPUT: Expected format ("return JSON with...", "write to file X")
5. DONE: How to signal completion
Check templates.md for copy-paste spawn templates.
| Error Type | Action |
|---|---|
| ------------ | -------- |
| Sub-agent timeout (>5 min no response) | Kill and retry once |
| Wrong output format | Retry with stricter instructions |
| Task too complex for tier | Escalate: Small→Medium→Large |
| Repeated failures (3x) | Abort, report to user |
Check errors.md for recovery patterns and escalation logic.
Never trust "done" without checking:
共 1 个版本