New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Official agent skill

Parallel Worker Swarm

by cursor in cursor/plugins

Launches many parallel cloud workers on slices of a task or on the same brief, waits for them all, and returns one aggregated report.

OfficialNo licenceAuto-check passedAgent Workflows

Install Parallel Worker Swarm

skills CLI
$ npx skills add cursor/plugins --skill swarm -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install cursor/plugins swarm --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/cursor/plugins.git skills-src && mkdir -p .claude/skills && cp -r skills-src/pstack/skills/swarm .claude/skills/swarm && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
swarm
GitHub stars
10k
Used in
7 other repos
Token cost
~738 tokens
SKILL.md length
460 words
Files
1
Skills in repo
99
Repo updated
First seen
Licence
None found

At a glance

Launches many parallel cloud workers on slices of a task or on the same brief, waits for them all, and returns one aggregated report.

  • Works in 4 steps: Frame → Fan out → Aggregate → …
  • Covering many independent slices of a task at the same time
  • SKILL.md covers Start, Phase A: Frame, Phase B: Fan out and Phase C: Aggregate, plus 1 more section
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

The agent opens a todo list with four phases: frame, fan out, aggregate and report. Framing sets a done predicate and the report the swarm must return, then picks a shape: partition the work into slices, race workers on identical briefs, or mix the two. Races need a declared rule, either first pass, rank all or best-of. The worker count is the total number of workers, not the cloud concurrency limit, and the worker model comes from a `swarm workers` line in a rules file, with a default if it is missing.

All workers start in one message as background cloud workers, or local ones only when they need something on your computer. Each brief stands alone with the goal, scope, exact slice or race arm, verification method and reporting format, and reports use PASS, ISSUES or BLOCKED with evidence. Workers that write get separate outputs, and measurement briefs name the exact commits and method. If a worker drops out, the swarm continues without it and notes the gap.

When your agent uses it

  • Covering many independent slices of a task at the same time
  • Racing several workers on one brief and ranking the results
  • Running parallel exploration or verification where one report is enough

Example prompts

  • “Swarm this: check every package in the monorepo for the deprecated logger call.”
  • “Race three workers on the flaky upload test and rank their proposed fixes.”
  • “Fan out one worker per API route to verify the new auth header, then give me a single report.”

Requirements

  • An agent that can start background cloud subagents

Workflow steps

4 steps, taken from the first numbered list in SKILL.md.

  1. Frame
  2. Fan out
  3. Aggregate
  4. Report

What it can do on your machine

Read from SKILL.md and the folder at commit ccb5507. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Parallel Worker Swarm loads about 738 tokens when it runs. Until then it costs about 39 tokens; SKILL.md has 460 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~39
When it runs · the whole SKILL.md, loaded when a task matches
~738

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

Without a licence we can't republish the file, so here is its outline and opening line. It has 460 words (~738 tokens).

“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.”

— opening of SKILL.md by cursor
name
swarm
disable-model-invocation
true

Read the full SKILL.md on GitHub

Files

Just SKILL.md in pstack/skills/swarm of cursor/plugins.

Open the folder on GitHubat commit ccb5507

Used in 7 other repositories

We found 7 copies of this SKILL.md (exact, near-identical or edited) in other folders, from 7 other GitHub owners. This page covers the copy in cursor/plugins, which our catalogue first saw on October 7, 2026.

Compare with similar skills

Parallel Worker Swarm next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Parallel Worker Swarm compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Parallel Worker Swarm this skillcursor/plugins10k7 repos~738Automated safety check: PassNone
Paseo Advisor Second Opiniongetpaseo/paseo20k1 repos~756Automated safety check: PassCustom licence
O2 Review Loopopenobserve/openobserve22k—~3.7kAutomated safety check: PassAGPL-3.0
Kimi Code DelegationCherryHQ/cherry-studio52k1 repos~504Automated safety check: PassAGPL-3.0
Harness Agent Team Designerrevfactory/harness9.1k—~4.5kAutomated safety check: PassApache-2.0
ClawTeam Multi-Agent Swarmwin4r/ClawTeam-OpenClaw1.5k1 repos~2.9kAutomated safety check: PassMIT

Similar skills

  • Paseo Advisor Second Opinion

    getpaseo/paseo

    Launches one separate agent through Paseo to give a second opinion on the current task, with a self-contained briefing and no permission to edit files.

    20k GitHub starsUsed in 1 repo~756 tokens
    Agent WorkflowsAuto-check passed

  • O2 Review Loop

    openobserve/openobserve

    Splits a change into planner, coder and independent reviewer roles: you confirm a spec, a subagent implements it, and a separate reviewer checks each round's local WIP commit.

    22k GitHub stars~3.7k tokensUpdated today
    Agent WorkflowsAuto-check passed

  • Kimi Code Delegation

    CherryHQ/cherry-studio

    Delegates one bounded repository task to Kimi Code in non-interactive prompt mode and reads back the final result from its JSON event stream.

    52k GitHub starsUsed in 1 repo~504 tokens
    Agent WorkflowsAuto-check passed

  • Harness Agent Team Designer

    revfactory/harness

    Designs a project-specific agent harness: defines specialist agents, writes the skills they follow, picks an execution mode and model for each, and keeps the setup maintained.

    9.1k GitHub stars~4.5k tokensUpdated 10 days ago
    Agent WorkflowsAuto-check passed

  • ClawTeam Multi-Agent Swarm

    win4r/ClawTeam-OpenClaw

    Launches a swarm of specialist Hermes agents in git-worktree-isolated tmux windows with a kanban board and file-based inboxes, using built-in templates like hedge-fund and code-review.

    1.5k GitHub starsUsed in 1 repo~2.9k tokens
    Agent WorkflowsAuto-check passed

  • Sub-Agent Delegation

    codewhale-hq/Codewhale

    Guides when and how to split multi-step coding, research or verification work into focused sub-agent runs while the parent keeps integration and final checks.

    41k GitHub stars~790 tokensUpdated today
    Agent WorkflowsAuto-check passed

More from cursor/plugins

All 99 skills in this repo

  • Show Me Your Work Decision Log

    cursor/plugins

    Official

    Keeps a TSV decision log for long or unattended agent runs, one row per decision with what, why, evidence and result, so a reviewer can check the work later.

    10k GitHub starsUsed in 9 repos~1.6k tokens
    Auto-check passed

  • Code Design Rationale Investigator

    cursor/plugins

    Official

    Digs into why code is shaped the way it is by checking git history, pull requests and connected tools in parallel, then reporting a cited read on the tradeoffs.

    10k GitHub starsUsed in 9 repos~2.6k tokens
    Auto-check passed

  • Reflect on Session Learnings

    cursor/plugins

    Official

    Starts three parallel reviewer subagents over the current conversation transcript, then turns their findings into concrete edits to existing skills.

    10k GitHub starsUsed in 5 repos~1.2k tokens
    Auto-check passed

  • Technical Writing Standard

    cursor/plugins

    Official

    Applies four layers of technical-writing rules to docs, RFCs, readmes, PR descriptions and commit messages so a tired engineer follows them on the first read.

    10k GitHub starsUsed in 10 repos~2.4k tokens
    Auto-check passed

  • Advisor Mode

    cursor/plugins

    Official

    Adds a second, stronger model that the main agent consults before major decisions, when stuck and before finishing, controlled by /advisor commands.

    10k GitHub stars~2.6k tokensUpdated today
    Auto-check: notes

  • Make PR Easy To Review

    cursor/plugins

    Official

    Prepare PRs for review by cleaning noisy history, improving PR descriptions, and adding reviewer guidance without changing code behavior.

    10k GitHub starsUsed in 3 repos~569 tokens
    Auto-check passed

Categories

Questions about Parallel Worker Swarm

What does Parallel Worker Swarm do?

Launches many parallel cloud workers on slices of a task or on the same brief, waits for them all, and returns one aggregated report. The agent opens a todo list with four phases: frame, fan out, aggregate and report. Framing sets a done predicate and the report the swarm must return, then picks a shape: partition the work into slices, race workers on identical briefs, or mix the two.

When should I use Parallel Worker Swarm?

Parallel Worker Swarm fits situations like: covering many independent slices of a task at the same time; racing several workers on one brief and ranking the results; running parallel exploration or verification where one report is enough.

How do I install Parallel Worker Swarm in Claude Code?

Run `npx skills add cursor/plugins --skill swarm -a claude-code`. Or copy the skill folder (pstack/skills/swarm in cursor/plugins) into .claude/skills/swarm in your project. Claude Code loads it when a task matches its description.

How do I install Parallel Worker Swarm in Codex?

Run `npx skills add cursor/plugins --skill swarm -a codex`. Or copy the skill folder (pstack/skills/swarm in cursor/plugins) into .agents/skills/swarm in your project. Codex loads it when a task matches its description.

Can I use Parallel Worker Swarm in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add cursor/plugins --skill swarm -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/swarm, .gemini/skills/swarm, .github/skills/swarm and .opencode/skills/swarm in your project.

What does Parallel Worker Swarm need to run?

SKILL.md names no scripts, command-line tools or credentials: Parallel Worker Swarm is instructions for the agent only. Our summary lists: An agent that can start background cloud subagents.

Does Parallel Worker Swarm access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Parallel Worker Swarm safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Parallel Worker Swarm use?

No licence was found for Parallel Worker Swarm or its repository. Without one, default copyright applies: ask the author before reusing or redistributing it.

How many tokens does Parallel Worker Swarm use?

About 738 tokens (SKILL.md is roughly 3k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Parallel Worker Swarm?

Skills that share tags, products or a category with Parallel Worker Swarm: Paseo Advisor Second Opinion (getpaseo/paseo, 20k stars), O2 Review Loop (openobserve/openobserve, 22k stars), Kimi Code Delegation (CherryHQ/cherry-studio, 52k stars) and Harness Agent Team Designer (revfactory/harness, 9.1k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Parallel Worker Swarm?

cursor (a GitHub organization, an official publisher) maintains it in cursor/plugins, which has 10,278 GitHub stars. The repository holds 99 skills in this directory. The repository was last updated on October 8, 2026.

Source: cursor/plugins on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.