multi-agent-patterns

Coordinate multiple agents by distributing work, isolating context, and synchronizing results.

Updated Aug 23, 2026

Search Tags:#multi-agent #consensus #swarm #coordination #handoff #orchestrator #context-isolation

Ready to run

npx skills add https://github.com/zjh08177/agent-harness --skill multi-agent-patterns-zjh08177

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: multi-agent-patterns
Source: https://github.com/zjh08177/agent-harness/tree/main/skills/multi-agent-patterns
Command: npx skills add https://github.com/zjh08177/agent-harness --skill multi-agent-patterns-zjh08177

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

Coordinate multiple agents to collaboratively complete complex tasks by distributing work, isolating context, and synchronizing results.

Core Features & Use Cases

Supervisor/Orchestrator pattern coordinates workers with stateful routing to deliver end-to-end outcomes.
Peer-to-peer swarm enables direct handoffs and parallel exploration without a central bottleneck.
Hierarchical pattern layers strategy, planning, and execution for scalable complex tasks.

Quick Start

Create a basic multi-agent workflow that decomposes a complex task and assigns subtasks to specialized agents.

Frequently Asked Questions about multi-agent-patterns

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

FAQPage Schema

How do I coordinate multiple agents to collaboratively complete complex tasks?▼

You coordinate multiple agents by distributing work, isolating context, and synchronizing results using supervisor, swarm, and hierarchical patterns. This approach enables parallel agents to handle research, planning, content creation, and data synthesis effectively.

What is the difference between supervisor, swarm, and hierarchical multi-agent patterns?▼

The supervisor pattern uses stateful routing to coordinate workers, the swarm pattern enables direct peer-to-peer handoffs without a central bottleneck, and the hierarchical pattern layers strategy, planning, and execution for scalable complex tasks.

When do I need context isolation in multi-agent systems?▼

You need context isolation when distributing work across parallel agents to prevent state interference and ensure clean synchronization. It ensures specialized agents handle subtasks independently before synchronizing their final results.

How do I set up a basic multi-agent workflow for parallel exploration?▼

You set up a basic multi-agent workflow by decomposing a complex task and assigning subtasks to specialized agents. The workflow uses handoff protocols and consensus mechanisms to enable direct peer-to-peer parallel exploration.

Can I use peer-to-peer swarm coordination without a central orchestrator bottleneck?▼

Yes, the peer-to-peer swarm pattern enables direct handoffs and parallel exploration without a central bottleneck. Agents coordinate autonomously, bypassing the stateful routing required by traditional supervisor or orchestrator architectures.

What are the limitations of hierarchical multi-agent coordination for complex tasks?▼

Hierarchical coordination layers strategy, planning, and execution to scale complex tasks, but requires careful synchronization of results across layers. If consensus mechanisms fail, context isolation between execution and strategy layers may break down.