# Swarm

> Fan out N parallel workers, drain them, and return one report. Use for /swarm, 'swarm this', or parallel coverage, races, gauntlets, and exploration.

- Skill: `shiwenbin1617/swarm` (Agent Skill)
- Install (CLI): `npx skillmds@latest add shiwenbin1617/swarm`
- Raw SKILL.md: https://api.skillmd.com/api/skills/shiwenbin1617/swarm/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: Docs & Writing
- Author: shiwenbin1617 (https://skillmd.com/u/shiwenbin1617)
- Updated: 2026-09-17
- Page: https://skillmd.com/skills/shiwenbin1617/swarm

---


# 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

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 the pstack model config (`/setup-pstack` writes it) when present. Otherwise use your fast code model. 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

Spawn all N general-purpose workers in one message, in the background, on the configured model. Run a worker on this machine only when it needs something that exists only here (a simulator, local auth, local transcripts).

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.