Multi Agent Patterns
Skill Verified ActiveDesign multi-agent architectures for complex tasks. Use when single-agent context limits are exceeded, when tasks decompose naturally into subtasks, or when specializing agents improves quality.
Design sophisticated multi-agent systems to overcome single-agent limitations, improve task decomposition, and enhance agent specialization for complex problems.
Features
- Design multi-agent architectures
- Implement supervisor, peer-to-peer, and hierarchical patterns
- Focus on context isolation for agent subtasks
- Detail consensus and coordination mechanisms
- Address failure modes and mitigation strategies
Use Cases
- When single-agent context limits are exceeded
- When tasks naturally decompose into subtasks
- When specializing agents improves quality
- Designing complex LLM-driven workflows
Non-Goals
- Replacing the need for a central AI agent
- Providing a framework for agent development itself (focus is on design patterns)
- Defining specific agent roles anthropomorphically
Workflow
- Analyze user request and decompose into subtasks
- Dispatch to appropriate specialist agents using Task tool
- Collect and synthesize results from subagents
- Return unified response to user
Practices
- Multi-agent system design
- Context isolation
- Coordination protocols
- Failure mode analysis
Installation
First, add the marketplace
/plugin marketplace add NeoLabHQ/context-engineering-kit/plugin install sadd@context-engineering-kitQuality Score
VerifiedTrust Signals
Similar Extensions
API Design Patterns
100Comprehensive API design patterns covering REST, GraphQL, gRPC, versioning, authentication, and modern API best practices
Swarm Orchestration
100Orchestrate multi-agent swarms with agentic-flow for parallel task execution, dynamic topology, and intelligent coordination. Use when scaling beyond single agents, implementing complex workflows, or building distributed AI systems.
System Design
99Design scalable distributed systems using structured approaches for load balancing, caching, database scaling, and message queues. Use when the user mentions "system design", "scale this", "high availability", "rate limiter", "design a URL shortener", "system design interview", "capacity planning", or "distributed architecture". Also trigger when estimating infrastructure requirements, choosing between microservices and monoliths, or designing for millions of concurrent users. Covers common system designs and back-of-the-envelope estimation. For data fundamentals, see ddia-systems. For resilience, see release-it.
Ccg
99Claude-Codex-Gemini tri-model orchestration via /ask codex + /ask gemini, then Claude synthesizes results
V3 Ddd Architecture
100Domain-Driven Design architecture for claude-flow v3. Implements modular, bounded context architecture with clean separation of concerns and microkernel pattern.
Pathfinder
100Map a codebase into feature-grouped flowcharts, identify duplicated concerns across features, and propose a unified architecture. Use when asked to "find the ideal path," unify duplicated systems, or audit architecture before a refactor. Emits a proposed unified flowchart plus per-system /make-plan prompts.