51 lines
1.9 KiB
Markdown
51 lines
1.9 KiB
Markdown
---
|
|
name: dispatching-parallel-agents
|
|
description: Dispatch focused subagents in parallel for genuinely independent problem domains
|
|
permalink: opencode-config/skills/dispatching-parallel-agents/skill
|
|
---
|
|
|
|
# Dispatching Parallel Agents
|
|
|
|
## Core Value
|
|
|
|
When there are 2+ genuinely independent failures/problem domains, dispatch one focused agent per domain concurrently instead of serial investigation.
|
|
|
|
## When to Use
|
|
|
|
Use when all are true:
|
|
- You have multiple failures across separate domains.
|
|
- Each domain can be investigated without shared context/state.
|
|
- Agents can work without touching the same files or interfering.
|
|
|
|
Do **not** parallelize when:
|
|
- Failures may share a root cause.
|
|
- You still need a single root-cause investigation first.
|
|
- Agents would edit the same area and conflict.
|
|
|
|
## Dispatch Pattern
|
|
|
|
1. Split failures into independent domains.
|
|
2. Write one prompt per domain.
|
|
3. Dispatch subagents concurrently with the `task` tool.
|
|
4. Review results, integrate non-conflicting fixes, then run full verification.
|
|
|
|
Example dispatch intent (tool-level wording):
|
|
- `task`: "Investigate and fix failures in <domain A only>"
|
|
- `task`: "Investigate and fix failures in <domain B only>"
|
|
|
|
## Prompt Quality Requirements
|
|
|
|
Each subagent prompt must include:
|
|
1. **One clear problem domain** (single file/subsystem/failure cluster).
|
|
2. **Self-contained context** (errors, failing tests, relevant constraints).
|
|
3. **Explicit constraints** (what not to change; scope boundaries).
|
|
4. **Explicit expected output** (root cause + files changed + validation run).
|
|
|
|
## Verification and Quality Pipeline
|
|
|
|
After subagents return:
|
|
1. Check for overlapping edits or assumption conflicts.
|
|
2. Run required verification for the integrated result (not partial checks).
|
|
3. Send the feature through reviewer, then tester when behavior is user-facing.
|
|
4. Do not claim completion without fresh verification evidence.
|