Agent Orchestrator

MANDATORY TRIGGERS: orchestrate, multi-agent, decompose task, spawn agents, sub-agents, parallel agents, agent coordination, task breakdown, meta-agent, agent factory, delegate tasks

Agent Orchestrator

Orchestrate complex tasks by decomposing them into subtasks, spawning autonomous sub-agents, and consolidating their work.

Core Workflow

Phase 1: Task Decomposition

Analyze the macro task and break it into independent, parallelizable subtasks:

1. Identify the end goal and success criteria
2. List all major components/deliverables required
3. Determine dependencies between components
4. Group independent work into parallel subtasks
5. Create a dependency graph for sequential work

Decomposition Principles:

Phase 2: Agent Generation

For each subtask, create a sub-agent workspace:

python3 scripts/create_agent.py  --workspace 

This creates:

//
├── SKILL.md          # Generated skill file for the agent
├── inbox/            # Receives input files and instructions
├── outbox/           # Delivers completed work
├── workspace/        # Agent's working area
└── status.json       # Agent state tracking

Generate SKILL.md dynamically with:

See references/sub-agent-templates.md for pre-built templates.

Phase 3: Agent Dispatch

Initialize each agent by:

1. Writing task instructions to inbox/instructions.md 2. Copying required input files to inbox/ 3. Setting status.json to {"state": "pending", "started": null} 4. Spawning the agent using the Task tool:

# Spawn agent with its generated skill
Task(
    description=f"{agent_name}: {brief_description}",
    prompt=f"""
    Read the skill at {agent_path}/SKILL.md and follow its instructions.
    Your workspace is {agent_path}/workspace/
    Read your task from {agent_path}/inbox/instructions.md
    Write all outputs to {agent_path}/outbox/
    Update {agent_path}/status.json when complete.
    """,
    subagent_type="general-purpose"
)

Phase 4: Monitoring (Checkpoint-based)

For fully autonomous agents, minimal monitoring is needed:

# Check agent completion
def check_agent_status(agent_path):
    status = read_json(f"{agent_path}/status.json")
    return status.get("state") == "completed"

Periodically check status.json for each agent. Agents update this file upon completion.

Phase 5: Consolidation

Once all agents complete:

1. Collect outputs from each agent's outbox/ 2. Validate deliverables against success criteria 3. Merge/integrate outputs as needed 4. Resolve conflicts if multiple agents touched shared concerns 5. Generate summary of all work completed

# Consolidation pattern
for agent in agents:
    outputs = glob(f"{agent.path}/outbox/*")
    validate_outputs(outputs, agent.success_criteria)
    consolidated_results.extend(outputs)

Phase 6: Dissolution & Summary

After consolidation:

1. Archive agent workspaces (optional) 2. Clean up temporary files 3. Generate final summary: - What was accomplished per agent - Any issues encountered - Final deliverables location - Time/resource metrics

python3 scripts/dissolve_agents.py --workspace  --archive

File-Based Communication Protocol

See references/communication-protocol.md for detailed specs.

Quick Reference:

Example: Research Report Task

Macro Task: "Create a comprehensive market analysis report"
Decomposition:
├── Agent: data-collector
│   └── Gather market data, competitor info, trends
├── Agent: analyst
│   └── Analyze collected data, identify patterns
├── Agent: writer
│   └── Draft report sections from analysis
└── Agent: reviewer
    └── Review, edit, and finalize report
Dependency: data-collector → analyst → writer → reviewer

Sub-Agent Templates

Pre-built templates for common agent types in references/sub-agent-templates.md:

Best Practices

1. Start small - Begin with 2-3 agents, scale as patterns emerge 2. Clear boundaries - Each agent owns specific deliverables 3. Explicit handoffs - Use structured files for agent communication 4. Fail gracefully - Agents report failures; orchestrator handles recovery 5. Log everything - Status files track progress for debugging

1. Start small - Begin with 2-3 agents, scale as patterns emerge 2. Clear boundaries - Each agent owns specific deliverables 3. Explicit handoffs - Use structured files for agent communication 4. Fail gracefully - Agents report failures; orchestrator handles recovery 5. Log everything - Status files track progress for debugging