orchestrating-swarms

Coordinate multi-agent workflows and task queues using Claude's TeammateTool and Task system.

5|Updated Feb 12, 2026
One-click install
npx skills add https://github.com/agusmdev/fullstack-ai-template --skill orchestrating-swarms-agusmdev
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: orchestrating-swarms
Source: https://github.com/agusmdev/fullstack-ai-template/tree/main/.claude/skills/swarm-orchestration
Command: npx skills add https://github.com/agusmdev/fullstack-ai-template --skill orchestrating-swarms-agusmdev

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Coordinating multiple Claude Code agents across a team enables parallel work, faster insight, and scalable automation by distributing tasks, messages, and workflows.

Core Features & Use Cases

  • Multi-agent team orchestration using TeammateTool and Task system for lead/teammate roles, message-based collaboration, and dependency-driven pipelines.
  • Supports parallel reviews, pipeline workflows with dependencies, and self-organizing task queues for scalable development and review processes.
  • Real-world scenario: orchestrate a feature rollout by coordinating code analysis, testing, and documentation tasks across several agents with auto-unblocking and shutdown sequences.

Quick Start

Launch a multi-agent swarm by creating a team and spawning teammates to start parallel tasks.

Frequently Asked Questions about orchestrating-swarms

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I coordinate multi-agent workflows across parallel tasks in Claude?

Multi-agent workflows are coordinated by defining Leader and Teammate roles, a shared Task List with dependencies, and an Inbox-based messaging model to distribute and track parallel work across agents.

Can I run pipeline orchestration with dependencies using Claude's Task system?

Pipeline orchestration with dependencies is supported by defining a shared Task List where agents execute sequential stages, auto-unblock downstream tasks, and trigger shutdown sequences upon completion.

What is the best way to orchestrate parallel code reviews with multiple AI agents?

Parallel code reviews are orchestrated by spawning multiple Teammate agents to analyze different code segments simultaneously, coordinating results back to a Leader agent via Inbox-based messaging for consolidated feedback.

Does multi-agent orchestration support tmux and iTerm2 backend spawn options?

Multi-agent orchestration supports in-process, tmux, and iTerm2 backend spawn options, allowing you to launch and manage distributed agent swarms across different terminal environments for scalable task execution.

How does Inbox-based messaging work for self-organizing task queues?

Inbox-based messaging enables self-organizing task queues by allowing Leader and Teammate agents to send messages, auto-unblock dependent tasks, and coordinate execution sequences without manual intervention.

When should I not use a multi-agent swarm for task execution?

A multi-agent swarm should not be used for simple, linear tasks lacking dependencies or parallelizable components, as the overhead of coordinating Leader, Teammate roles, and message passing outweighs the automation benefits.