Skip to content
Back to skills

Swarm

ASecurity

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

  • 2 stars
  • 0 votes
  • 0 copies
  • 6 views
  • Added October 2, 2026
ai-agentsgo

Works with

  • terminal

Security analysis

A100/100

Scanned October 2, 2026

npx -y skills add EvanBatten/pstack-for-cc --skill swarm --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Swarm?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for Swarm
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/evanbatten-swarm/badge)](https://www.skillsdirectory.com/skills/evanbatten-swarm)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

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

# Swarm

Fan out N parallel workers. They may cover separate slices, race the same brief, or mix both. The parent waits, aggregates, and returns one report.

## Start

Open a task list with TaskCreate (a deferred tool, loaded through ToolSearch) with one item per phase before launching anything. Where no task tool exists, carry one line per phase in your reply, each with its state.

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 `~/.claude/pstack-models.md` when present. Otherwise use `sonnet`. 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 in one message with `subagent_type: general-purpose`, `isolation: "worktree"`, and the configured model. Drop the isolation only when the worker needs the user's live working tree.

When a worker must start from a non-default pushed branch, tell it to check that branch out in its worktree first.

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.

Attribution

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments

Loading comments…

Newsletter

Get the weekly list of safe new skills, and the ones we pulled.