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

Agent skill

Swarm

by guaardvark in guaardvark/guaardvark

Launch and watch Guaardvark's Swarm Orchestrator: parallel coding agents, each in its own git worktree, working a markdown plan and merging back deterministically.

MITAuto-check passedAgent Workflows

Install Swarm

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

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

GitHub CLI
$ gh skill install guaardvark/guaardvark 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/guaardvark/guaardvark.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/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
257
Token cost
~746 tokens
SKILL.md length
249 words
Files
1
Skills in repo
15
Repo updated
First seen
Licence
MIT

At a glance

Launch and watch Guaardvark's Swarm Orchestrator: parallel coding agents, each in its own git worktree, working a markdown plan and merging back deterministically.

  • Works in 3 steps: Write the plan file → Launch → Watch, merge, clean up
  • The user wants several agents on one codebase at once
  • SKILL.md covers 1. Write the plan file, 2. Launch, 3. Watch, merge, clean up and Rules
  • Calls curl

What it does

Swarm is an agent skill from guaardvark/guaardvark. Launch and watch Guaardvark's Swarm Orchestrator: parallel coding agents, each in its own git worktree, working a markdown plan and merging back deterministically. Use when the user wants several agents on one codebase at once, says "swarm this", or asks about a running swarm, worktrees, or merge status.

Its SKILL.md is about 750 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Agent Workflows, covering Git worktrees. It works with Git, Model Context Protocol and Ollama. The repository describes itself as: Self-hosted AI studio on your own GPU: chat with your files (RAG), screen and browser agents, coding swarms, LoRA training, an MCP server for Claude Code and Cursor, and local… The licence is MIT.

When your agent uses it

  • The user wants several agents on one codebase at once
  • Says swarm this
  • Asks about a running swarm

Example prompts

  • “swarm this”
  • “/swarm”

Workflow steps

3 steps, taken from the step headings in SKILL.md.

  1. Write the plan file
  2. Launch
  3. Watch, merge, clean up

What it can do on your machine

Read from SKILL.md and the folder at commit 2a33110. 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

    Shell commands in SKILL.md call:

    • curl

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

  • Network

    No URLs in SKILL.md. Its commands use curl, which can reach the network depending on how they are called.

    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

Swarm loads about 746 tokens when it runs. Until then it costs about 78 tokens; SKILL.md has 249 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~78
When it runs · the whole SKILL.md, loaded when a task matches
~746

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

The full file from guaardvark/guaardvark at commit 2a33110, republished under its MIT licence (© guaardvark). 249 words, ~746 tokens.

Download SKILL.mdSave it as .claude/skills/swarm/SKILL.md (or your agent's skills folder).
name
swarm
description
Launch and watch Guaardvark's Swarm Orchestrator: parallel coding agents, each in its own git worktree, working a markdown plan and merging back deterministically. Use when the user wants several agents on one codebase at once, says "swarm this", or asks about a running swarm, worktrees, or merge status.

Swarm with Guaardvark

Read setup first; needs the swarm plugin (POST /api/plugins/swarm/start). B=${GUAARDVARK_URL:-http://localhost:5000}. Status is also the MCP tool swarm_status.

1. Write the plan file

A markdown file in the target repo. Each ## heading is one task. Structured fields are optional; the parser infers file scope from paths in the prose when they are absent:

markdown
# Plan: split the settings page

## Extract the GPU panel
- files: frontend/src/pages/SettingsPage.jsx, frontend/src/components/settings/GpuPanel.jsx
- backend: claude
Move the GPU section into its own component with the same props.

## Add a test for the panel
- files: frontend/src/__tests__/GpuPanel.test.jsx
- depends_on: Extract the GPU panel

backend / assign to picks the agent backend (Claude Code, or a local Cline/OpenClaw agent on Ollama in Flight Mode). Tasks that touch the same files should depend on each other; the parser warns about conflicts.

2. Launch

bash
curl -s -X POST $B/api/swarm/launch -H 'Content-Type: application/json' -d '{
  "plan_path": "/abs/path/repo/docs/plan.md", "repo_path": "/abs/path/repo",
  "max_agents": 4, "auto_merge": false, "flight_mode": false, "dry_run": false,
  "acknowledge_dirty_tree": false
}'
  • A dirty working tree is refused unless acknowledge_dirty_tree: true; tell the user what is uncommitted first.
  • self_code: true targets Guaardvark's own checkout and is only allowed on the configured root.
  • dry_run: true parses the plan and reports tasks and conflicts without starting agents.

3. Watch, merge, clean up

call
GET $B/api/swarm/status and GET $B/api/swarm/status/<swarm_id>tasks, states, worktrees
GET $B/api/swarm/<swarm_id>/logs/<task_id>?lines=100one agent's log
GET $B/api/swarm/<swarm_id>/diff/<task_id>its diff before merge
POST $B/api/swarm/<swarm_id>/bus/broadcastmessage every agent
POST $B/api/swarm/merge {"swarm_id": "...", "repo_path": "..."}merge finished branches in dependency order
POST $B/api/swarm/cancelstop
POST $B/api/swarm/cleanup {"swarm_id": "...", "delete_branches": false}remove worktrees
GET $B/api/swarm/templatessaved plan templates

Rules

  • Review diffs before merge unless the user asked for auto_merge.
  • Keep max_agents at or below the machine's capacity; each Claude agent is a separate session and each local agent competes for the GPU with generation jobs.
  • Report per task: state, files touched, whether it merged. Never say "done" on a swarm that still has running or failed tasks.

© guaardvark, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in .agents/skills/swarm of guaardvark/guaardvark.

Open the folder on GitHubat commit 2a33110

Compare with similar skills

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.

Swarm compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Swarm this skillguaardvark/guaardvark257—~746Automated safety check: PassMIT
Agtx Task Sweepfynnfluegge/agtx1.7k—~1.7kAutomated safety check: PassApache-2.0
Devcontainer Devstacklok/toolhive-studio170—~3.8kAutomated safety check: NotesApache-2.0
Parallel Feature ManagersCotal-AI/Cotal313—~5.3kAutomated safety check: PassApache-2.0
PmApra-Labs/apra-fleet101—~5.4kAutomated safety check: PassCustom licence
RoveSma1lboy/rove160—~8.9kAutomated safety check: PassMIT

Similar skills

  • Agtx Task Sweep

    fynnfluegge/agtx

    Breaks a conversation's results into feature-level tasks and pushes them to the agtx kanban board, where each task gets its own worktree and agent session.

    1.7k GitHub stars~1.7k tokensUpdated 7 days ago
    Agent WorkflowsAuto-check passed

  • Devcontainer Dev

    stacklok/toolhive-studio

    Spin up and interact with ToolHive Studio's containerized dev environment (Xvfb + noVNC + DinD).

    170 GitHub stars~3.8k tokensUpdated today
    Agent WorkflowsAuto-check: notes

  • Parallel Feature Managers

    Cotal-AI/Cotal

    Run several independent Cotal features concurrently by creating one Git worktree and one spawn-capable mesh manager per feature; each manager staffs a review panel in a dedicated channel, adds one…

    313 GitHub stars~5.3k tokensUpdated today
    Agent WorkflowsAuto-check passed

  • Pm

    Apra-Labs/apra-fleet

    Project Manager skill. An agent skill from Apra-Labs/apra-fleet.

    101 GitHub stars~5.4k tokensUpdated today
    Agent WorkflowsAuto-check passed

  • Rove

    Sma1lboy/rove

    A skill your agent uses when controlling Rove tasks, parallel coding attempts, hosted agent sessions, task lifecycle, or the daemon-owned issue tracker from a shell.

    160 GitHub stars~8.9k tokensUpdated today
    Agent WorkflowsAuto-check passed

  • Agent Deck

    asheshgoplani/agent-deck

    agent-deck, the terminal session manager for AI coding agents.

    1k GitHub stars~1.7k tokensUpdated 3 days ago
    Agent WorkflowsAuto-check passed

More from guaardvark/guaardvark

All 15 skills in this repo

  • Cast

    guaardvark/guaardvark

    Build consistent characters, environments and props in Guaardvark's Cast Library and train LoRAs for them locally (reference photos → vision bible → sample plan → approved samples → training).

    257 GitHub stars~673 tokensUpdated today
    Auto-check passed

  • Image

    guaardvark/guaardvark

    Generate or edit images on the user's own GPU through Guaardvark: single images, instruction edits, background cut-outs, inpaint and outpaint, consistent characters from the Cast Library, and batch…

    257 GitHub stars~1.8k tokensUpdated today
    Auto-check passed

  • Music

    guaardvark/guaardvark

    Generate full songs with vocals or instrumentals (ACE-Step) and sound effects or ambience (Stable Audio Open) on the user's GPU through Guaardvark's Audio Foundry.

    257 GitHub stars~710 tokensUpdated today
    Auto-check passed

  • Ops

    guaardvark/guaardvark

    Operate a running Guaardvark: GPU and VRAM state, plugin start/stop, logs, Celery tasks, the Interconnector sync to other machines, overnight RAG autoresearch, and infographics.

    257 GitHub stars~779 tokensUpdated today
    Auto-check passed

  • Setup

    guaardvark/guaardvark

    Connect this agent to a running Guaardvark (self-hosted AI studio) and check what it can do right now.

    257 GitHub stars~1.2k tokensUpdated today
    Auto-check passed

  • Upscale

    guaardvark/guaardvark

    Upscale images and video 2x to 4K/8K on the user's GPU through Guaardvark (Real-ESRGAN, HAT-L, SwinIR, two-pass).

    257 GitHub stars~493 tokensUpdated today
    Auto-check passed

Works with

Categories

Questions about Swarm

What does Swarm do?

Launch and watch Guaardvark's Swarm Orchestrator: parallel coding agents, each in its own git worktree, working a markdown plan and merging back deterministically. Swarm is an agent skill from guaardvark/guaardvark. Launch and watch Guaardvark's Swarm Orchestrator: parallel coding agents, each in its own git worktree, working a markdown plan and merging back deterministically.

When should I use Swarm?

Swarm fits situations like: the user wants several agents on one codebase at once; says swarm this; asks about a running swarm.

How do I install Swarm in Claude Code?

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

How do I install Swarm in Codex?

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

Can I use 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 guaardvark/guaardvark --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 Swarm need to run?

Going by SKILL.md and its folder, Swarm needs the command-line tools its instructions call (curl).

Does Swarm access the network?

SKILL.md contains no URLs. Its commands use curl, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is 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 Swarm use?

Swarm is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Swarm use?

About 746 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 Swarm?

Skills that share tags, products or a category with Swarm: Agtx Task Sweep (fynnfluegge/agtx, 1.7k stars), Devcontainer Dev (stacklok/toolhive-studio, 170 stars), Parallel Feature Managers (Cotal-AI/Cotal, 313 stars) and Pm (Apra-Labs/apra-fleet, 101 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Swarm?

guaardvark (a GitHub user) maintains it in guaardvark/guaardvark, which has 257 GitHub stars. The repository holds 15 skills in this directory. The repository was last updated on October 9, 2026.

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