New to Claude Skills? Learn how to install them →

ruvnet on GitHub

Agent Coordination

Free

Manage and coordinate multiple AI agents seamlessly.

by ruvnet67.6k stars on ruvnet/ruflo
Updated Aug 10, 2026
Get this skill

Free · Opens the source repo

What Agent Coordination does

The Agent Coordination skill is designed for developers and teams who need to spawn, manage, and coordinate multiple AI agents for complex tasks. With support for over 60 specialized agent types, this skill allows you to effectively handle various roles such as coding, testing, security auditing, and performance engineering. By leveraging this skill, you can streamline workflows that involve multiple agents working together, thereby enhancing productivity and efficiency in your projects.

This skill provides a robust command-line interface for managing agent lifecycles. You can easily spawn agents, list their statuses, and monitor their performance metrics. The ability to manage agent pools allows for dynamic scaling based on task requirements. For instance, if you need to handle a bug fix, you can spawn a specific set of agents tailored to that task, ensuring that each agent has a defined role within the coordination framework.

The skill also includes predefined routing codes for common tasks, which can simplify the orchestration of agents. By utilizing hierarchical coordination and specialized agents, you can optimize the workflow for tasks such as feature development, refactoring, and security assessments. Best practices are provided to ensure that coordination remains tight and effective, particularly when managing a limited number of agents.

This skill is particularly useful for teams working on large-scale projects where multiple AI agents can be deployed to tackle different aspects of development simultaneously. It is ideal for environments where collaboration and coordination among agents can lead to faster and more reliable outcomes.

When to use it

Use this skill when you need to coordinate multi-agent workflows or manage agent pools for complex projects.

When not to use it

Avoid this skill for single-agent tasks or when no coordination among agents is required.

What you can build with it

Bug Fix Coordination

Spawn a team of agents including a coordinator, researcher, coder, and tester to efficiently resolve bugs.

Feature Development

Utilize a group of specialized agents to collaboratively design and implement new features.

Performance Optimization

Deploy performance engineers alongside other roles to analyze and enhance system performance.

How to install Agent Coordination

View source

1. Install with the skills CLI

npx skills add ruvnet/ruflo/agent-coordination --agent claude-code

2. Or install it manually

Download the skill folder and drop it into ~/.claude/skills/ for all projects, or .claude/skills/ to scope it to one repo. Restart Claude Code so it picks up the new skill.

Anthropic's agentic coding CLI, and the reference implementation of Agent Skills. Drop a skill folder into ~/.claude/skills and Claude Code loads it automatically whenever a task matches the skill's description. Claude Code docs

Inside SKILL.md

Written by ruvnet

Agent Coordination Skill

Purpose

Spawn and coordinate agents for complex multi-agent tasks.

Agent Types

Core Development

coder, reviewer, tester, planner, researcher

V3 Specialized

security-architect, security-auditor, memory-specialist, performance-engineer

Swarm Coordination

hierarchical-coordinator, mesh-coordinator, adaptive-coordinator, collective-intelligence-coordinator

Consensus

byzantine-coordinator, raft-manager, gossip-coordinator, consensus-builder

GitHub

pr-manager, code-review-swarm, issue-tracker, release-manager

SPARC

sparc-coord, sparc-coder, specification, pseudocode, architecture, refinement

Commands

Spawn Agent

npx claude-flow agent spawn --type coder --name my-coder

List Agents

npx claude-flow agent list --filter active

Agent Status

npx claude-flow agent status --id agent-123

Agent Metrics

npx claude-flow agent metrics --id agent-123

Stop Agent

npx claude-flow agent stop --id agent-123

Pool Management

npx claude-flow agent pool --size 5 --type coder

Routing Codes

CodeTaskAgents
1Bug Fixcoordinator, researcher, coder, tester
3Featurecoordinator, architect, coder, tester, reviewer
5Refactorcoordinator, architect, coder, reviewer
7Performancecoordinator, perf-engineer, coder
9Securitycoordinator, security-architect, auditor

Best Practices

  1. Use hierarchical topology for coordination
  2. Keep agent count under 8 for tight coordination
  3. Use specialized agents for specific tasks
  4. Coordinate via memory, not direct communication

Frequently asked questions about Agent Coordination

Similar skills