Agents Swarm

Fan out N parallel subagent workers in one turn, aggregate their results, and report PASS, ISSUES, or BLOCKED per worker. Use for /agents-swarm, "swarm this", parallel coverage across slices, races between approaches, or broad exploration.

23 stars 1 forksAI, LLMs & Agents

Install

skills CLI (Claude Code, Cursor, Codex and more)
npx skills add jpoehnelt/skills --skill agents-swarm
Manual install
git clone --depth 1 https://github.com/jpoehnelt/skills.git /tmp/skills
mkdir -p ~/.claude/skills
cp -r /tmp/skills/agents-swarm ~/.claude/skills/agents-swarm

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

# Swarm

Fan out N workers, drain them, return one report. Keep a todo list with one entry per phase: Frame, Fan out, Aggregate, Report.

Repo facts (from AGENTS.md or CLAUDE.md): the local run command and whether parallel instances in separate worktrees get their own ports and data.

## Phase A: Frame

1. State the done predicate and the report the swarm must return.
2. Choose the shape:
   - **Partition.** Each worker owns one slice.
   - **Race.** N workers get the same brief. Declare the rule before spawning: `first pass`, `rank all`, or `best-of`.
   - **Mixed.** Slices, with a race inside some of them.
3. Pick N. Cover every required slice. Do not exceed what the machine and the task justify.
4. Give each writing worker its own output path or its own worktree so workers never edit the same file. A worker in its own worktree must commit there and report the branch and commit; integrate each partition slice, and only the winning arm of a race, into the main checkout (merge or cherry-pick) before reporting it PASS; leave losing arms unmerged. Read-only workers need nothing. A worker that runs the app uses the repo's local run command in its own worktree; if instances would share ports or data, run those workers in batches that cannot collide.
5. When workers verify or measure commits, each brief names the exact SHAs. A measurement brief also names the method: sample count, what one sample is, and the order.

## Phase B: Fan out
Read the full skill on GitHub

Details

Skill name
agents-swarm
Path
agents-swarm/SKILL.md
License
MIT
Repo updated
12 November 2026

FAQ

What does the Agents Swarm skill do?

Fan out N parallel subagent workers in one turn, aggregate their results, and report PASS, ISSUES, or BLOCKED per worker. Use for /agents-swarm, "swarm this", parallel coverage across slices, races between approaches, or broad exploration.

How do I install the Agents Swarm skill?

skills CLI (Claude Code, Cursor, Codex and more): npx skills add jpoehnelt/skills --skill agents-swarm. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is Agents Swarm popular?

It lives in jpoehnelt/skills, which has 23 GitHub stars and 1 forks.

Related skills

Agents Correct

23

jpoehnelt/skills

Find the mistakes agents keep repeating in a repo and make each one impossible, trying architecture first, then types, lint, tests, and docs last. Use when the operator keeps correcting the same mistake, or for /agents-correct.

AI, LLMs & Agents

Agents Create Verification Skill

23

jpoehnelt/skills

Generate a project-local verify skill that drives the app like a user through a browser with Playwright, a CLI, or HTTP. Use for /agents-create-verification-skill, "make a verify skill for this repo", or when a project has no scripted way to prove UI, CLI, or service behavior.

AI, LLMs & Agents

Agents Reflect

23

jpoehnelt/skills

After a work session, review what went wrong and right and turn each lesson into a concrete edit to an existing skill or AGENTS.md line. Use when the user says "reflect" or /agents-reflect.

AI, LLMs & Agents

Anc Camp

9

HA7CH/anc-fde-camp

Explain and position HA7CH ANC Camp for serious prospective participants. Clarify why FDE and ANC matter to the future of enterprise AI, identify who will gain the most value, assess readiness, and answer questions about field work, curriculum, Whiteboard Interview, assessment, historical field evidence, current cohort details, value, and registration consultation. Use when someone invokes /anc-camp, $anc-camp, /fde-camp or $fde-camp, asks whether the Camp is suitable or worthwhile, or wants to understand what they need and what the Camp can help them become.

AI, LLMs & Agents

Claude Sonar

9

AschoofAlpha/claude-sonar

Audit a local Windows proxy and system setup, with limited macOS/Linux environment collection, for routing, DNS, IPv6, IP reputation, timezone, language, and documented Claude Code privacy controls. Use for Clash Verge/Mihomo or other proxy-leak diagnosis and minimal privacy hardening without fingerprint spoofing or platform-evasion guidance.

AI, LLMs & Agents

Design Mobile Apps with Daisy

9

daisy-now/agent-skills

Design native mobile app screens with Daisy (daisy.now), an AI design agent with a canvas. Use when the user wants mobile screens or flows designed or mocked up (onboarding, settings, feeds, checkout), wants changes to screens in a Daisy project, or wants a Daisy screen as a PNG or as HTML. Mobile only, not web pages.

AI, LLMs & Agents

Browse the most popular Claude skills, all ai, llms & agents skills, or write your own with the skills generator.