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 Orchestration

by ruvnet in ruvnet/ruflo

Coordinates a hierarchical swarm of specialized agents through the claude-flow CLI for work that spans several files or modules at once.

MITAuto-check passedAgent Workflows

Install Swarm Orchestration

skills CLI
$ npx skills add ruvnet/ruflo --skill swarm-orchestration -a claude-code

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

GitHub CLI
$ gh skill install ruvnet/ruflo swarm-orchestration --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/ruvnet/ruflo.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/swarm-orchestration .claude/skills/swarm-orchestration && 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-orchestration
GitHub stars
74k
Used in
2 other repos
Token cost
~779 tokens
SKILL.md length
191 words
Files
3 (incl. scripts)
Skills in repo
264
Repo updated
First seen
Licence
MIT

At a glance

Coordinates a hierarchical swarm of specialized agents through the claude-flow CLI for work that spans several files or modules at once.

  • Works in 4 steps: Check memory for existing patterns… → Use hierarchical topology for coordination → Store successful patterns after completion → …
  • Implementing a feature that changes three or more files
  • SKILL.md covers Purpose, When to Trigger, When to Skip and Commands, plus 3 more sections
  • Runs Shell scripts from its folder; calls npx

What it does

This skill is meant for changes that touch three or more files: new features, cross-module refactors, API changes with tests, security-related work, codebase-wide performance tuning and database schema changes. It should be skipped for single-file edits, one or two line fixes, documentation or configuration changes and quick exploration.

Everything runs through npx @claude-flow/cli. The commands initialize a swarm with a hierarchical topology, a maximum agent count and a specialized strategy, route a task to suitable agents, spawn an agent of a chosen type and name, check swarm status, orchestrate a task with an adaptive or parallel strategy and list active agents. Two scripts, swarm-start.sh and swarm-monitor.sh, handle default startup and monitoring. The notes advise checking memory for existing patterns first.

When your agent uses it

  • Implementing a feature that changes three or more files
  • Refactoring across modules while keeping tests passing
  • Making API or database schema changes that need coordinated work
  • Splitting a security-related change across specialized agents

Example prompts

  • “Start a hierarchical swarm to refactor the auth module with at most four agents.”
  • “Route the task add rate limiting to the public API to the right agents.”
  • “Show the status of the current swarm and list the active agents.”

Requirements

  • Node.js with npx to run the `@claude-flow/cli` package

Workflow steps

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

  1. Check memory for existing patterns before starting
  2. Use hierarchical topology for coordination
  3. Store successful patterns after completion
  4. Document any new learnings

What it can do on your machine

Read from SKILL.md and the folder at commit 58e0ae7. 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

    Ships 2 files in scripts/ (Shell), which the agent can run.

    Shell commands in SKILL.md call:

    • npx

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

  • Network

    No URLs in SKILL.md. Its commands use npx, 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 Orchestration loads about 779 tokens when it runs. Until then it costs about 131 tokens; SKILL.md has 191 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~131
When it runs · the whole SKILL.md, loaded when a task matches
~779

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); the scripts in this folder are not scanned.

SKILL.md

The full file from ruvnet/ruflo at commit 58e0ae7, republished under its MIT licence (© ruvnet). 191 words, ~779 tokens.

Download SKILL.mdSave it as .claude/skills/swarm-orchestration/SKILL.md (or your agent's skills folder). This skill also uses 2 other files; get the full folder from GitHub.
name
swarm-orchestration
description
Multi-agent swarm coordination for complex tasks. Uses hierarchical topology with specialized agents to break down and execute complex work across multiple files and modules. Use when: 3+ files need changes, new feature implementation, cross-module refactoring, API changes with tests, security-related changes, performance optimization across codebase, database schema changes. Skip when: single file edits, simple bug fixes (1-2 lines), documentation updates, configuration changes, quick exploration.

Swarm Orchestration Skill

Purpose

Multi-agent swarm coordination for complex tasks. Uses hierarchical topology with specialized agents to break down and execute complex work across multiple files and modules.

When to Trigger

  • 3+ files need changes
  • new feature implementation
  • cross-module refactoring
  • API changes with tests
  • security-related changes
  • performance optimization across codebase
  • database schema changes

When to Skip

  • single file edits
  • simple bug fixes (1-2 lines)
  • documentation updates
  • configuration changes
  • quick exploration

Commands

Initialize Swarm

Start a new swarm with hierarchical topology (anti-drift)

bash
npx @claude-flow/cli swarm init --topology hierarchical --max-agents 8 --strategy specialized

Example:

bash
npx @claude-flow/cli swarm init --topology hierarchical --max-agents 6 --strategy specialized
Route Task

Route a task to the appropriate agents based on task type

bash
npx @claude-flow/cli hooks route --task "[task description]"

Example:

bash
npx @claude-flow/cli hooks route --task "implement OAuth2 authentication flow"
Spawn Agent

Spawn a specific agent type

bash
npx @claude-flow/cli agent spawn --type [type] --name [name]

Example:

bash
npx @claude-flow/cli agent spawn --type coder --name impl-auth
Monitor Status

Check the current swarm status

bash
npx @claude-flow/cli swarm status --verbose
Orchestrate Task

Orchestrate a task across multiple agents

bash
npx @claude-flow/cli task orchestrate --task "[task]" --strategy adaptive

Example:

bash
npx @claude-flow/cli task orchestrate --task "refactor auth module" --strategy parallel --max-agents 4
List Agents

List all active agents

bash
npx @claude-flow/cli agent list --filter active

Scripts

ScriptPathDescription
swarm-start.agents/scripts/swarm-start.shInitialize swarm with default settings
swarm-monitor.agents/scripts/swarm-monitor.shReal-time swarm monitoring dashboard

References

DocumentPathDescription
Agent Typesdocs/agents.mdComplete list of agent types and capabilities
Topology Guidedocs/topology.mdSwarm topology configuration guide

Best Practices

  1. Check memory for existing patterns before starting
  2. Use hierarchical topology for coordination
  3. Store successful patterns after completion
  4. Document any new learnings

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

Files

SKILL.md and 2 other files (scripts) in .agents/skills/swarm-orchestration of ruvnet/ruflo.

  • SKILL.md
  • scripts/swarm-monitor.sh
  • scripts/swarm-start.sh

Open the folder on GitHubat commit 58e0ae7

Used in 2 other repositories

We found 2 copies of this SKILL.md (exact, near-identical or edited) in other folders, from 2 other GitHub owners. This page covers the copy in ruvnet/ruflo, which our catalogue first saw on October 7, 2026.

Compare with similar skills

Swarm Orchestration 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 Orchestration compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Swarm Orchestration this skillruvnet/ruflo74k2 repos~779Automated safety check: PassMIT
O2 Review Loopopenobserve/openobserve22k—~3.7kAutomated safety check: PassAGPL-3.0
Kimi Code DelegationCherryHQ/cherry-studio52k—~504Automated safety check: PassAGPL-3.0
Sub-Agent DelegationTokenRhythm/opensquilla7.1k—~3kAutomated safety check: PassApache-2.0
Subagent-Driven DevelopmentHoangNguyen0403/agent-skills-standard571—~1.3kAutomated safety check: PassMIT
Multi AgentWrongStack/WrongStack370—~3.6kAutomated safety check: PassMIT

Similar skills

  • 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 stars~504 tokensUpdated today
    Agent WorkflowsAuto-check passed

  • Sub-Agent Delegation

    TokenRhythm/opensquilla

    Hands a self-contained coding task to Codex, Claude Code, OpenCode or Pi as a non-interactive background process, using OpenSquilla's exec_command and process tools.

    7.1k GitHub stars~3k tokensUpdated today
    Agent WorkflowsAuto-check passed

  • Subagent-Driven Development

    HoangNguyen0403/agent-skills-standard

    Runs a multi-task implementation plan by sending each task to a fresh implementer subagent, reviewing it independently, then reviewing the whole branch.

    571 GitHub stars~1.3k tokensUpdated today
    Agent WorkflowsAuto-check passed

  • Multi Agent

    WrongStack/WrongStack

    A skill your agent uses whenever work can be split across multiple AI agents running in parallel, or when orchestrating leader/worker patterns in WrongStack.

    370 GitHub stars~3.6k tokensUpdated yesterday
    Agent WorkflowsAuto-check passed

  • Multi Agent PR Review

    bbartling/open-fdd

    A skill your agent uses for rigorous pull request, branch, patch, or diff review.

    173 GitHub stars~1.4k tokensUpdated yesterday
    Agent WorkflowsAuto-check passed

More from ruvnet/ruflo

All 264 skills in this repo

  • AgentDB Pattern Memory

    ruvnet/ruflo

    Stores, searches, and retrieves successful patterns with HNSW-indexed semantic search so agents can reuse past solutions instead of relearning them.

    74k GitHub starsUsed in 2 repos~830 tokens
    Auto-check passed

  • Security Audit Scanner

    ruvnet/ruflo

    Runs claude-flow CLI security scans for input validation, path traversal, SQL injection, XSS, hardcoded secrets and known CVEs, and writes an audit report.

    74k GitHub starsUsed in 2 repos~823 tokens
    Auto-check passed

  • SPARC Development Methodology

    ruvnet/ruflo

    Applies the SPARC method (specification, pseudocode, architecture, refinement, completion) with 17 specialized modes and multi-agent orchestration, from research to deployment.

    74k GitHub starsUsed in 2 repos~829 tokens
    Auto-check passed

  • Ruflo Multi-Agent Orchestration

    ruvnet/ruflo

    Sets up and drives Ruflo, an npm-installed orchestration layer for multi-agent swarms, persistent memory, routing, hooks and its MCP tool catalog.

    74k GitHub starsUsed in 1 repo~975 tokens
    Auto-check passed

  • Agent Coordination

    ruvnet/ruflo

    Reference for spawning, listing, monitoring and stopping agents with claude-flow commands, with agent type families, routing codes and coordination tips.

    74k GitHub starsUsed in 2 repos~519 tokens
    Auto-check passed

  • Claims

    ruvnet/ruflo

    Claims-based authorization for agents and operations. An agent skill from ruvnet/ruflo.

    74k GitHub starsUsed in 2 repos~1.1k tokens
    Auto-check passed

Categories

Questions about Swarm Orchestration

What does Swarm Orchestration do?

Coordinates a hierarchical swarm of specialized agents through the claude-flow CLI for work that spans several files or modules at once. This skill is meant for changes that touch three or more files: new features, cross-module refactors, API changes with tests, security-related work, codebase-wide performance tuning and database schema changes. It should be skipped for single-file edits, one or two line fixes, documentation or configuration changes and quick exploration.

When should I use Swarm Orchestration?

Swarm Orchestration fits situations like: implementing a feature that changes three or more files; refactoring across modules while keeping tests passing; making API or database schema changes that need coordinated work; splitting a security-related change across specialized agents.

How do I install Swarm Orchestration in Claude Code?

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

How do I install Swarm Orchestration in Codex?

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

Can I use Swarm Orchestration 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 ruvnet/ruflo --skill swarm-orchestration -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-orchestration, .gemini/skills/swarm-orchestration, .github/skills/swarm-orchestration and .opencode/skills/swarm-orchestration in your project.

What does Swarm Orchestration need to run?

Going by SKILL.md and its folder, Swarm Orchestration needs a shell for the scripts in its folder and the command-line tools its instructions call (npx). Our summary lists: Node.js with npx to run the `@claude-flow/cli` package.

Does Swarm Orchestration access the network?

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

Is Swarm Orchestration 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. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Swarm Orchestration use?

Swarm Orchestration 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 Orchestration use?

About 779 tokens (SKILL.md is roughly 3.1k 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 Orchestration?

Skills that share tags, products or a category with Swarm Orchestration: O2 Review Loop (openobserve/openobserve, 22k stars), Kimi Code Delegation (CherryHQ/cherry-studio, 52k stars), Sub-Agent Delegation (TokenRhythm/opensquilla, 7.1k stars) and Subagent-Driven Development (HoangNguyen0403/agent-skills-standard, 571 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Swarm Orchestration?

ruvnet (a GitHub user) maintains it in ruvnet/ruflo, which has 74,159 GitHub stars. The repository holds 264 skills in this directory. The repository was last updated on October 9, 2026.

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