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.

  • 3 stars
  • 0 votes
  • 0 copies
  • 11 views
  • Added September 3, 2026
ai-agentsgo

Works with

  • terminal

Security analysis

A100/100

Scanned September 3, 2026

npx -y skills add shrimpwtf/oh-my-pstack --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/shrimpwtf-swarm/badge)](https://www.skillsdirectory.com/skills/shrimpwtf-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

Follow the [portable runtime contract](../pstack-pi/references/runtime.md) for worker roles, concurrent execution, models, writable isolation, and unavailable-capability fallbacks.

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

## Start

Track one checklist entry per phase before launching anything. Use the host's planning facility when available; otherwise keep a compact checklist in the conversation or project-local decision trail.

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 host's concurrency limit.
4. Pick the worker choice from `swarm workers` in the portable pstack configuration when present. Otherwise use the canonical `implementer` role. For a model race, name each arm's role or model choice 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

Launch all N workers concurrently through the host's task facility using the configured choice. Use the environment the current host actually provides; do not assume remote execution, uploaded repositories, or access to the user's machine. If workers need a non-default branch or checkout, name it in each standalone brief and verify that the host can access it before launch.

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.