UNPKG

claude-flow

Version:

Enterprise-grade AI agent orchestration with ruv-swarm integration (Alpha Release)

80 lines (67 loc) 2.26 kB
# SPARC Orchestrator Mode ## Description Multi-agent task orchestration and coordination ## Command Prompt SPARC: orchestrator You are an AI orchestrator that coordinates multiple specialized agents to complete complex tasks efficiently. ## Available Tools - **TodoWrite**: Create and manage task coordination - **TodoRead**: Monitor task progress and status - **Task**: Spawn and manage specialized agents - **Memory**: Store and retrieve coordination data - **Bash**: Execute system commands ## Core Capabilities - Centralized coordination of up to 10 parallel agents - Batch-optimized operations for efficiency - Memory-based state management across agents - Real-time task progress monitoring ## Usage Examples ### Basic Usage ```bash ./claude-flow sparc orchestrator "Your task description here" ``` ### Advanced Usage with Coordination ```javascript // Use TodoWrite for task coordination TodoWrite([ { id: "orchestrator_task", content: "Execute orchestrator task with batch optimization", status: "pending", priority: "high", mode: "orchestrator", batchOptimized: true, coordinationMode: "centralized", maxParallelTasks: 10, tools: ["TodoWrite","TodoRead","Task","Memory","Bash"] } ]); // Launch specialized agent Task("Orchestrator Agent", "Execute specialized orchestrator task", { mode: "orchestrator", batchOptimized: true, coordinationMode: "centralized", memoryIntegration: true }); ``` ## Best Practices - Use batch operations when working with multiple files - Store intermediate results in Memory for coordination - Enable parallel execution for independent tasks - Monitor resource usage during intensive operations - Leverage centralized coordination for team management ## Integration This mode integrates with: - Memory system for state persistence - TodoWrite/TodoRead for task coordination - Task tool for agent spawning - Batch file operations for efficiency - Real-time monitoring and metrics ## Troubleshooting - Ensure proper tool permissions are set - Check Memory keys for coordination data - Monitor resource usage during batch operations - Validate input parameters and constraints - Use verbose logging for debugging --- Generated by Claude-Flow SPARC Integration System