Improve the reliability and output quality of multi-agent coding workflows by giving the main agent structured visibility into delegated subagents. Use when Codex or another agent runtime delegates parallel work and needs authoritative lifecycle tracking, factual child checkpoints, explicit blockers or input requests, bounded recovery, persistent history, or a local dashboard. This skill does not expose hidden reasoning.
설치
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
Improve the reliability and output quality of multi-agent coding workflows by giving the main agent structured visibility into delegated subagents. Use when Codex or another agent runtime delegates parallel work and needs authoritative lifecycle tracking, factual child checkpoints, explicit blockers or input requests, bounded recovery, persistent history, or a local dashboard. This skill does not expose hidden reasoning.
Supervise Subagents
Turn fire-and-forget delegation into an observable, recoverable workflow. Native runtime state remains authoritative; structured progress events add the work context needed for supervision.