This is for when you need multiple Claude instances working together on something complex. You get four swarm topologies (mesh for research, hierarchical for dev workflows, star for testing, ring for pipelines) and can spawn specialized agents like researchers, coders, and QA engineers. The documentation walks through three real patterns: a research swarm that does parallel info gathering then synthesizes findings, a development swarm with a full team hierarchy, and presumably a testing pattern. It's built on claude-flow with both MCP tools and CLI fallbacks. Honestly feels like overkill for most projects, but if you're doing deep research synthesis or coordinating multi-stage development across different specializations, this gives you the primitives to orchestrate it without reinventing the coordination layer.

GitHub stars
240
last updated
Jun 11, 2026

Install

$ npx -y skills add spencermarx/open-code-review --skill swarm-advanced --agent claude-code

Installs into .claude/skills of the current project.

Files

Advanced Swarm Orchestration

Master advanced swarm patterns for distributed research, development, and testing workflows. This skill covers comprehensive orchestration strategies using both MCP tools and CLI commands.

Quick Start

Prerequisites

# Ensure Claude Flow is installed
npm install -g claude-flow@alpha

# Add MCP server (if using MCP tools)
claude mcp add claude-flow npx claude-flow@alpha mcp start

Basic Pattern

// 1. Initialize swarm topology
mcp__claude-flow__swarm_init({ topology: "mesh", maxAgents: 6 })

// 2. Spawn specialized agents
mcp__claude-flow__agent_spawn({ type: "researcher", name: "Agent 1" })

// 3. Orchestrate tasks
mcp__claude-flow__task_orchestrate({ task: "...", strategy: "parallel" })

Core Concepts

Swarm Topologies

Mesh Topology - Peer-to-peer communication, best for research and analysis

  • All agents communicate directly
  • High flexibility and resilience
  • Use for: Research, analysis, brainstorming

Hierarchical Topology - Coordinator with subordinates, best for development

  • Clear command structure
  • Sequential workflow support
  • Use for: Development, structured workflows

Sponsors

Details

Repository
github.com/spencermarx/open-code-review
Categories
Testing & QA, Git & Pull Requests, Code Review & Quality, Data Science & ML, Automation & Workflows
License
Apache-2.0
First seen
Jun 11, 2026

More from spencermarx/open-code-review

All 31
1Trevoke avatarwriting-skillsTrevoke/org-gtd.elThis is TDD for documentation.0skills.sh installs
2heygen-com avatarhyperframes-cliheygen-com/hyperframesUse the HyperFrames CLI development loop: init, add, catalog, capture, lint, check, snapshot, compare, grade-compare, preview, play, present, beats, keyframes, 1.5Mskills.sh installs
3microsoft avatarazure-validatemicrosoft/azure-skillsPre-deployment validation for Azure readiness. Run deep checks on configuration, infrastructure (Bicep or Terraform), RBAC role assignments, managed identity pe659.9Kskills.sh installs
4microsoft avatarazure-aigatewaymicrosoft/azure-skillsConfigure Azure API Management as an AI Gateway for AI models, MCP tools, and agents. WHEN: semantic caching, token limit, content safety, load balancing, AI mo657.6Kskills.sh installs
5microsoft avatarazure-computemicrosoft/azure-skillsAzure VM/VMSS router. WHEN: create / provision / deploy / spin-up VM, recommend VM size, compare VM pricing, VMSS, scale set, autoscale, burstable, lightweight 614.1Kskills.sh installs
6google avatargoogle-agents-cli-workflowgoogle/agents-cliThis skill should be used when the user wants to "develop an agent", "build an agent using ADK", "run the agent locally", "debug agent code", "test an agent", "558.9Kskills.sh installs