---
name: swarm
description: "Fan out N parallel workers, drain them, and return one report. Use for /skill:swarm, 'swarm this', or parallel coverage, races, gauntlets, and exploration."
disable-model-invocation: true
---

# Swarm

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

Keep a checklist 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. Use the current session or workspace model preset by default. Pass an explicit worker model only when a valid configured id is already available. For a model race, name each arm's model up front.
5. Give each worker its own writable output when it writes. Use a worktree, branch, or `/tmp/swarm-<slug>/worker-<n>/`.

## Phase B: Fan out

Discover the policy-gated Open Session session tools and call `spawn_task` for all N workers in parallel. Begin every brief with `/pstack`. Use ask mode for read-only slices and code mode with separate isolated worktrees for writes. Give each task explicit file pointers and prevent concurrent writes to shared paths.

When a worker must start from a non-default branch, use the session tool's supported branch or isolated-worktree inputs. Never invent a branch parameter or attach an existing shared main checkout.

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.