swarm

# Swarm Before delegating, read [the harness instructions](../../harness/README.md) and the active harness file. Map agent names, tool arguments, and model roles there. Fan out N parallel cloud workers. They may cover separate slices, race the same brief, or mix both. The parent waits, aggregates, and returns one report. ## Start Open a todolist with one entry per phase before launching anything. 1. Frame 2. Fan out 3. Aggregate 4. Report ## Phase A: Frame 1. State the done predicate and the artifact or report the swarm must return. 2. Choose the shape. Partition into slices, race N workers on identical briefs, or mix both. For a race or mixed shape, declare `first pass`, `rank all`, or `best-of` before spawning. 3. Set N from the user or derive it from the shape. N is total workers, not the cloud concurrency limit. 4. Pick the worker model from `swarm workers` in `~/.pstack/models.md` when present. Otherwise use the active harness file's `swarm workers` default. For a model race, name each arm's model up front, and skip the race entirely on a harness with no per-subagent model override. 5. Give each worker its own writable output when it writes. ## Phase B: Fan out Spawn all N workers in one message, backgrounded, with the configured model, using the subagent tool the active harness file names. Cursor takes `environment: "cloud"` for workers that need no local access; every other harness runs workers locally, so give each one its own worktree or output directory instead (Phase A step 5) and treat the harness file's "long-running work" section as the ceiling on how detached a worker can be. When a worker must start from a non-default pushed branch, pass `cloud_base_branch`. Every brief stands alone. Include the goal, scope, exact slice or race arm, how to verify, and what to report. Reports use `PASS`, `ISSUES`, or `BLOCKED` with evidence. If a worker drops out, proceed with N-1 and note it. ## Phase C: Aggregate Read the terminal results. For coverage, every required slice needs a result. For a race, apply the selection rule declared up front. Use first pass, rank all, or best-of. Do not paste raw worker dumps. Keep a compact result table, one-line evidenced issues, and explicit gaps or dropouts. ## Phase D: Report Return one consolidated in-chat report with the table, issue one-liners, gaps or dropouts, and the race rule when used.