# 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: `sitaggart/swarm` (Agent Skill, multi-file: 2 files)
- Install (CLI): `npx skillmds@latest add sitaggart/swarm`
- Raw SKILL.md: https://api.skillmd.com/api/skills/sitaggart/swarm/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: Docs & Writing
- Author: SiTaggart (https://skillmd.com/u/sitaggart)
- Updated: 2026-09-10
- Page: https://skillmd.com/skills/sitaggart/swarm

---


# Swarm

Read [PStack runtime guidance](../../RUNTIME.md) before this workflow.

Fan out N parallel native 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 current native concurrency limit.
4. Pick the worker model using the `swarm workers` role resolved through RUNTIME.md and the bundled model choices. For a model race, name each arm's model up front.
5. Give each worker its own writable output when it writes.

## Phase B: Fan out

Spawn all N workers with the available non-blocking native subagent tool and the configured model and reasoning settings from RUNTIME.md. Start remaining workers as concurrency slots free up. Local children share the local host; use separate worktrees for writers. No cloud isolation is implied.

When a worker must start from a non-default pushed branch, prepare its worktree at that branch and pass the absolute worktree path in its brief.

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.