swarm-init

swarm-init is a command for Claude Code from ruvnet/ruflo. It costs 0 tokens per session (482 once invoked), scanned A, original, MIT.

A command for initializing a Claude Flow swarm with a chosen connection layout, agent limit, and execution strategy. A swarm is a coordinated group of task-focused agents.

In plain words
What is it for?
Use it to configure mesh, hierarchical, ring, or star layouts; choose parallel, sequential, or balanced execution; and optionally enable automatic agents, persistent memory, or GitHub integration.
Why use it?
It sets the rules for how agents communicate and how work is scheduled before a complex task begins.

Command for Claude Code

Written for Claude Code: installed under .claude/. Also seen: mentions Claude Code.

Part of the claude-flow plugin — 134 skills, 52 commands, 11 agents, 4 hooks shipped together

About the project

Ruflo is an execution and coordination layer for Claude Code and Codex that equips AI coding agents with tools, memory, control loops, sandboxes, and collaboration mechanisms. Developers use it to organize specialized agents into swarms, coordinate workflows, retain knowledge across sessions, and communicate across machines. The catalogue entries are Ruflo’s skills, commands, agents, hooks, and plugin components.

ruvnet/ruflo · 70,498 stars · on GitHub · cognitum.one

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add commands/ruvnet/ruflo/swarm-init
Clone the repo
git clone --depth 1 https://github.com/ruvnet/ruflo

Made for: Claude Code.

Or install claude-flow, the plugin that ships this one along with the rest of its 134 skills, 52 commands, 11 agents, 4 hooks.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for swarm-init

README.md
[![agentmods](https://agentmods.dev/badge/commands/ruvnet/ruflo/swarm-init.svg)](https://agentmods.dev/commands/ruvnet/ruflo/swarm-init)
Your own site
<a href="https://agentmods.dev/commands/ruvnet/ruflo/swarm-init"><img src="https://agentmods.dev/badge/commands/ruvnet/ruflo/swarm-init.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 482 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00000 $0.00482
Opus 5 $0.00000 $0.00241
Sonnet 5 $0.00000 $0.00096
Haiku 4.5 $0.00000 $0.00048

Measured 2d ago against content hash adb339d92778, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

swarm-init scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

Origin

Copies of this mod

7 near-identical copies found in the catalogue:

.claude/commands/coordination/swarm-init.md · 86 lines

How it starts

The opening of the file, as written. The whole thing — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.

swarm init

Initialize a Claude Flow swarm with specified topology and configuration.

Usage

npx claude-flow swarm init [options]

Options

  • --topology, -t <type> - Swarm topology: mesh, hierarchical, ring, star (default: hierarchical)
  • --max-agents, -m <number> - Maximum number of agents (default: 8)
  • --strategy, -s <type> - Execution strategy: balanced, parallel, sequential (default: parallel)
  • --auto-spawn - Automatically spawn agents based on task complexity
  • --memory - Enable cross-session memory persistence
  • --github - Enable GitHub integration features

Examples

Basic initialization

npx claude-flow swarm init

Mesh topology for research

npx claude-flow swarm init --topology mesh --max-agents 5 --strategy balanced

Hierarchical for development

npx claude-flow swarm init --topology hierarchical --max-agents 10 --strategy parallel --auto-spawn

GitHub-focused swarm

npx claude-flow swarm init --topology star --github --memory

Topologies

Mesh

  • All agents connect to all others
  • Best for: Research, exploration, brainstorming
  • Communication: High overhead, maximum information sharing

Hierarchical

  • Tree structure with clear command chain
  • Best for: Development, structured tasks, large projects
  • Communication: Efficient, clear responsibilities

Ring

  • Agents connect in a circle
  • Best for: Pipeline processing, sequential workflows
  • Communication: Low overhead, ordered processing

Star

  • Central coordinator with satellite agents
  • Best for: Simple tasks, centralized control
  • Communication: Minimal overhead, clear coordination

Integration with Claude Code

Once initialized, use MCP tools in Claude Code:

mcp__claude-flow__swarm_init { topology: "hierarchical", maxAgents: 8 }

See Also

  • agent spawn - Create swarm agents
  • task orchestrate - Coordinate task execution
  • swarm status - Check swarm state
  • swarm monitor - Real-time monitoring

Read the full file on GitHub · 86 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2d ago First seen · 86 lines · 0 tokens per session scan A adb339d92778

Subscribe to this mod's changes

swarm-init is a command published in the GitHub repository ruvnet/ruflo (70,498 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 482 tokens. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.

Related

Other commands, from other repositories

launch

Preview the public launch — the file bundle, the secret/PII scan, and the release gates — in dry-run mode, cut a release by deriving its version and composing its changelog, and scaffold the changelog-driven release gate into a managed repo. The preview performs zero writes; ship writes the dated CHANGELOG heading and…

intentdriven/abcd · 85 tokens

archive

name: OpenSpec: Archive description: Archive a deployed OpenSpec change and update specs. category: OpenSpec tags: [openspec, archive].

spencermarx/orc · 0 tokens

release-update

(dev-only) release-update maintainer harness — Claude Code upstream change tracker (release-notes version-delta sweep + docs sync). NOT distributed to user projects.

modu-ai/moai-adk · 32 tokens

disembark

Pack a lifeboat from a repository into a destination directory — read-only over the source, behind a destination safety gate, secret-scanned before any write. Point it at any repo (including a dead or archived one) and write the lifeboat elsewhere.

intentdriven/abcd · 57 tokens

briefing

Structured pre-execution briefing session -- collects case context through specialist panel, builds execution plan, supports resume and depth control.

fedec65/bettercallclaude · 23 tokens

legal-goal

Define a checkable legal success condition for /legal-loop. Accepts a named profile (citations-clean, draft-passes-gate, adversarial-converge, nda-batch-clean, reg-watch, timeline-sourced) or free-text objective. Produces a persisted Goal Record — never starts work itself.

fedec65/bettercallclaude · 63 tokens