dispatching-parallel-agents
Use when parallel workers have a net benefit over coordinated sequential work.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
메뉴
Use when parallel workers have a net benefit over coordinated sequential work.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
Consult after receiving review feedback and before implementation when the feedback needs evidence-based evaluation.
Consult before delegating implementation when an approved plan benefits from worker context isolation and durable coordination.
Consult before attempting a fix when root cause or behavior is unclear, failures repeat, components interact, or guessing would be unsafe.
Consult before implementing an observable behavior change when a meaningful automated test seam exists; use proportional red-green evidence.
Consult directly matching task playbooks before substantial design, debugging, implementation, review, or completion work without forcing full workflow execution.
Consult before making a substantive completion claim; require current trustworthy evidence and semantic acceptance.
| name | dispatching-parallel-agents |
| description | Use when parallel workers have a net benefit over coordinated sequential work. |
Choose parallel work from independence, cost, coordination, and harness safety. Dispatch only when the net benefit exceeds added integration and recovery cost. Group related work when splitting it would create more reconciliation than insight.
Give each worker a bounded contract, ownership boundary, and expected evidence. Avoid shared mutable targets unless the harness coordinates them safely.
After workers return, verify the real impact boundary: shared interfaces, persisted state, user-visible behavior, and integration points their reports could miss. Isolated green results are not integration evidence by themselves.