Interacts with a running lightjj instance (browser-based Jujutsu/jj viewer) via the lightjj api CLI. Reads diffs, posts inline review comments, posts doc-mode suggestions, and steers the user's view. Use when the user has lightjj running and wants the agent to review changes, annotate diffs, or comment on markdown…
Use when working in Jujutsu repositories for problem tracking, solution management, and code review — implements Popperian epistemology (problems → solutions → critiques) directly in version control.
Use when working in a repository that has jjj initialized (a .jj/jjj-meta directory), or when coordinating several agents on shared work — tracking problems, proposing competing solutions, critiquing them, and reaching decisions that survive history rewrites. Also use when asked to set up multi-agent collaboration…
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.
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…