claude-flow
Version:
Enterprise-grade AI agent orchestration with ruv-swarm integration (Alpha Release)
80 lines (67 loc) • 2.26 kB
Markdown
# 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