jeremy-adk-orchestrator
Production ADK orchestrator for A2A protocol and multi-agent coordination on Vertex AI
Installation
Open Claude Code and run this command:
/plugin install jeremy-adk-orchestrator@claude-code-plugins-plus
Use --global to install for all projects, or --project for current project only.
What It Does
This plugin enables Claude Code to communicate with ADK agents deployed on Vertex AI Agent Engine using the standardized A2A (Agent-to-Agent) Protocol. It handles task submission, status checking, session management, and AgentCard discovery for building multi-agent systems.
Key Capabilities:
- AgentCard discovery and capability inspection
- Task submission with structured inputs
- Session management for Memory Bank persistence
- Status polling and result retrieval
- Streaming responses for long-running tasks
- Multi-agent orchestration with supervisory patterns
Features
✅ AgentCard Discovery: Automatic capability detection for ADK agents
✅ A2A Protocol Communication: Standardized task submission and retrieval
✅ Session Management: Persistent sessions with Memory Bank
✅ Status Polling: Real-time task status monitoring
✅ Streaming Responses: Handle long-running agent tasks
✅ Multi-Agent Orchestration: Supervisory agent patterns
✅ Error Handling: Retry logic and graceful degradation
✅ Observability: Integrated logging and tracing
Skills (1)
Deploy and orchestrate Vertex AI ADK agents using A2A protocol.
How It Works
Natural Language Activation
Simply mention what you need:
"Communicate with the ADK agent at [endpoint]"
"Send a task to the sentiment-analysis agent"
"Orchestrate multiple ADK agents for this workflow"
"Check status of task ID abc-123"
"Discover capabilities of the agent at [endpoint]"
The skill auto-activates and handles A2A protocol communication.
Use Cases
Single Agent Communication
"Communicate with the sentiment-analysis ADK agent at [endpoint]"
"Send customer reviews to the analysis agent"
Multi-Agent Workflows
"Orchestrate data extraction, analysis, and synthesis agents"
"Run a multi-step workflow across these ADK agents: [list]"
Session Management
"Continue the conversation with session ID abc-123"
"Create a new session with Memory Bank persistence"
Status Monitoring
"Check status of task ID xyz-456"
"Monitor the long-running analysis task"
Capability Discovery
"Discover capabilities of the agent at [endpoint]"
"What tools does this ADK agent support?"