Ag2 Agent Builder
Plugin Verifiziert AktivBuild AG2 (AutoGen) multi-agent systems with slash commands: scaffold agents, wire workflows, create tools, and review code
Empower developers to efficiently build, configure, and manage complex AG2 multi-agent systems with structured commands and agents.
Funktionen
- Scaffold AG2 agents and A2A server structures
- Create complex multi-agent workflows (group chats, pipelines)
- Generate utility tools with proper error handling and auth
- Review agent code for best practices and contract adherence
- Provide patterns for common AG2 agent types and orchestration
Anwendungsfälle
- Designing and implementing a new AG2 agent for a specific task
- Setting up a multi-agent system with a sequential processing pipeline
- Creating a collaborative agent group chat for complex problem-solving
- Developing custom tools for agents to interact with external APIs
Nicht-Ziele
- Running AG2 agents directly within Claude Code (focus is on scaffold/definition)
- Providing pre-built agents for every possible task (focus is on framework)
- Managing the deployment lifecycle of AG2 agents beyond code generation
Installation
/plugin install ag2-agent-builder@davepoon-buildwithclaudeQualitätspunktzahl
VerifiziertVertrauenssignale
Ähnliche Erweiterungen
Oh My Claudecode
99Multi-agent orchestration system for Claude Code
Agent Triforce
99Multi-agent development system with three specialized agents (PM, Dev, QA) coordinated through checklist methodology based on The Checklist Manifesto and Boeing's checklist engineering
Agenthub
99Multi-agent collaboration plugin for Claude Code. Spawn N parallel subagents that compete on code optimization, content drafts, research approaches, or any problem that benefits from diverse solutions. Evaluate by metric or LLM judge, merge the winner. 7 slash commands, agent templates, git DAG orchestration, message board coordination.
Context Management
98Context persistence, restoration, and long-running conversation management
Error Debugging
98Error analysis, trace debugging, and multi-agent problem diagnosis