prompts: strengthen subagent spawn bias for parallel independent tasks
This commit is contained in:
parent
792ea4663f
commit
427161638f
|
|
@ -4,11 +4,16 @@ Use `subagent_spawn` to delegate work to one or more specialized agents running
|
||||||
|
|
||||||
## When to spawn
|
## When to spawn
|
||||||
|
|
||||||
- A task can be decomposed into N independent subtasks that share no state
|
When a task has N independent subtasks that each require multi-step reasoning or multiple tool calls, spawn N subagents and run them in parallel rather than executing sequentially. Do not wait until one subtask is done to start the next if they share no state.
|
||||||
- You want to run the same prompt against multiple inputs in parallel
|
|
||||||
|
Spawn when:
|
||||||
|
- A task decomposes into N independent subtasks, each requiring reasoning or multiple tool calls
|
||||||
|
- You are processing N items (files, repos, hosts) with the same operation
|
||||||
- A subtask is better handled by a different agent (different model, backend, or system prompt)
|
- A subtask is better handled by a different agent (different model, backend, or system prompt)
|
||||||
- You want to isolate a long-running or risky operation from the current session
|
- You want to isolate a long-running or risky operation from the current session
|
||||||
|
|
||||||
|
Use `execute_code` parallel steps instead when the subtasks are single shell commands. Subagents are for agent-level work; parallel code steps are for parallel shell execution.
|
||||||
|
|
||||||
## How to use
|
## How to use
|
||||||
|
|
||||||
```
|
```
|
||||||
|
|
|
||||||
Loading…
Reference in New Issue