Orchestrate parallel subagent execution across isolated jj workspaces with wave-based scheduling and spec-informed peer review, then reunify results into a single change. Use when the user asks to "fan out tasks", "run tasks in parallel with isolation", "dispatch subagents for independent tasks", or when subagent-driven-development routes here via CLAUDE.md override in a jj repo.
Phase 2 of /peer-review. Use after generalist dispatch completes to aggregate findings, present results, and manage specialist lifecycle.
Phase 1 of /peer-review. Use when dispatching generalist reviewers for a jj change. Triggers after completing work, before committing, or when reviewing a change.