deep-agents-orchestration - Orchestrate Deep Agents with planning and approvals
Delegate tasks to subagents, track multi-step plans with TodoList, and pause sensitive operations for human approval.
Tags
Updated: 2026-09-28Capabilities
Typical Inputs
Typical Outputs
What this skill does
- Delegate tasks to subagents
- Track multi-step tasks
- Require human approval
- Resume interrupted execution
- Configure specialized subagents
Inputs
- Task instructions
- Specialized tools
- Todo items
- Thread identifier
- Checkpointer
- Approval decisions
Outputs
- Subagent reports
- Todo list state
- Pending interrupt status
- Resumed execution results
Requirements
- Deep Agents environment
- create_deep_agent support
- Checkpointer for interrupts
- Thread identifier for todo persistence