# 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: `theoklitosbam7/swarm` (Agent Skill, multi-file: 2 files)
- Install (CLI): `npx skillmds@latest add theoklitosbam7/swarm`
- Raw SKILL.md: https://api.skillmd.com/api/skills/theoklitosbam7/swarm/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: Docs & Writing
- Author: theoklitosBam7 (https://skillmd.com/u/theoklitosbam7)
- Updated: 2026-09-17
- Page: https://skillmd.com/skills/theoklitosbam7/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 the `swarm workers` role in the pstack model config, per the **harness** skill. Otherwise the adapter default. 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 workers in one message as background subagents with the configured model, per the **harness** skill. Run them on remote compute when the harness has it and the worker needs nothing from this machine. Run them locally when the worker needs access to something on the user's computer.

When a worker must start from a non-default pushed branch, name the branch in the brief so the worker checks it out.

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.