Swarm Init
- 649 installs
- 67k repo stars
- Updated August 4, 2026
- ruvnet/ruflo
swarm-init is a Claude Flow skill that bootstraps a multi-agent swarm with anti-drift configuration, topology selection, and up to 8 specialized agents for developers tackling complex multi-file software tasks.
About
swarm-init is a RuFlo Claude Flow skill that initializes a multi-agent swarm with anti-drift configuration for coordinated work requiring three or more agents. It calls mcp__claude-flow__swarm_init with topology options hierarchical, mesh, hierarchical-mesh, ring, star, or adaptive, maxAgents 8, and strategy specialized—or uses npx @claude-flow/cli. Skip swarm-init for single-file edits or quick questions. Allowed tools include swarm_status, Task, and SendMessage for inter-agent coordination. Developers reach for swarm-init when implementing features across modules, running cross-module refactors, or conducting security audits that benefit from specialized agent roles. The skill sets anti-drift guardrails before dispatching parallel agent work in Claude Code sessions.
- Initializes a complete swarm workspace with agent roles and communication protocols
- Configures persistent memory layers and shared context between agents
- Establishes orchestration patterns for parallel task execution
- Generates configuration files ready for immediate agent deployment
- Supports both local and cloud-based swarm coordination
Swarm Init by the numbers
- 649 all-time installs (skills.sh)
- +10 installs in the week ending Jul 26, 2026 (Skillselion tracking)
- Ranked #1,488 of 16,546 AI & Agent Building skills by installs in the Skillselion catalog
- Data as of Aug 5, 2026 (Skillselion catalog sync)
npx skills add https://github.com/ruvnet/ruflo --skill swarm-initAdd your badge
Show developers this skill is listed on Skillselion. Paste this into your README.
| Installs | 649 |
|---|---|
| repo stars | ★ 67k |
| Last updated | August 4, 2026 |
| Repository | ruvnet/ruflo ↗ |
How do you initialize a multi-agent coding swarm?
Bootstrap a multi-agent swarm environment that coordinates specialized agents for complex software projects.
Who is it for?
Developers starting complex multi-file tasks—feature builds, cross-module refactors, or security audits—needing 3+ coordinated claude-flow agents.
Skip if: Developers making single-file edits, quick Q&A, or tasks that do not require three or more coordinated agents.
When should I use this skill?
A complex multi-file task needs 3+ coordinated agents with anti-drift swarm configuration and topology selection.
What you get
Initialized swarm environment, topology config, agent roster up to 8 agents, and anti-drift coordination setup.
- initialized swarm config
- agent coordination setup
By the numbers
- Initializes swarms with up to 8 agents (maxAgents: 8)
- Supports 6 topology modes: hierarchical, mesh, hierarchical-mesh, ring, star, adaptive
Files
Initialize a hierarchical swarm for coordinated multi-agent work.
Via MCP: mcp__claude-flow__swarm_init({ topology: "hierarchical", maxAgents: 8, strategy: "specialized" })
Or via CLI:
npx @claude-flow/cli@latest swarm init --topology hierarchical --max-agents 8 --strategy specializedThen spawn named agents in ONE message via Claude Code's Task tool with name: (for SendMessage addressability) and run_in_background: true (for parallel execution). Use EnterWorktree per agent for git-safe parallel work, and SendMessage for inter-agent coordination.
For larger teams (10+), use hierarchical-mesh topology:
npx @claude-flow/cli@latest swarm init --topology hierarchical-mesh --max-agents 15 --strategy specializedRelated skills
Setup Matt Pocock SkillsScaffold the per-repo configuration that Matt Pocock’s engineering agent skills rely on so they understand the issue tracker, triage labels, and domain documentation la495k196k
Lark AppsConnect Claude, Cursor or custom agents directly to Lark (Feishu) for messaging, document automation, approval workflows and enterprise data access.402k
CavemanSlash token usage by roughly 75% while keeping every technical detail intact when working with Claude Code, Cursor or similar agents.391k94.7k
Lark Skill MakerQuickly turn any Lark/Feishu OpenAPI call or multi-step workflow into a reusable agent skill with its own SKILL.md.386k16k
Running Claude Code Via Litellm CopilotRun Claude Code at a fraction of the cost by routing requests through LiteLLM to the GitHub Copilot Chat API.270k72
Codex PetGenerate a complete Codex Pet spritesheet and metadata from one reference image without needing an OpenAI key or Codex Pro.246k10How it compares
Choose swarm-init over single-agent sessions when multi-file work needs anti-drift topology and up to 8 specialized claude-flow agents.
FAQ
When should developers use swarm-init?
swarm-init fits complex multi-file work needing three or more coordinated agents—feature implementation, cross-module refactors, or security audits. Skip it for single-file edits or quick questions.
What swarm topologies does swarm-init support?
swarm-init accepts hierarchical, mesh, hierarchical-mesh, ring, star, or adaptive topologies via --topology. swarm_init defaults include maxAgents 8 and strategy specialized for role-based coordination.