skills.rest
orezek
orezekCOMMUNITY
Explore all skills by this author →
GitHub

deep-agents-orchestration

Configure subagent delegation, todo planning, and human approval interrupts in Deep Agents.

Updated Jan 10, 2026
Search Tags:#subagents#agent orchestration#LangGraph#task planning#human-in-the-loop#deep agents#interrupts
One-click install
npx skills add https://github.com/orezek/monorepo_template --skill deep-agents-orchestration-orezek
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: deep-agents-orchestration
Source: https://github.com/orezek/monorepo_template/tree/main/.agents/skills/deep-agents-orchestration
Command: npx skills add https://github.com/orezek/monorepo_template --skill deep-agents-orchestration-orezek

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Building agents that delegate work to subagents, plan multi-step tasks, or pause for human approval requires correctly wiring SubAgentMiddleware, TodoListMiddleware, and HumanInTheLoopMiddleware, where common mistakes like missing checkpointers or thread IDs silently break workflows. ## Core Features & Use Cases - Subagent Delegation: Create custom subagents with specialized tools and system prompts that the main agent invokes via the task tool. - TodoList Planning: Track multi-step task progress with the write_todos tool and read todo state from agent results. - Human-in-the-Loop Approval: Configure interrupt_on rules so sensitive tools like write_file or execute_sql pause for approve, reject, or edit decisions. - Use Case: You are building a deployment agent where a code-deployer subagent runs tests and deploys to production, but the deploy step must wait for a human to approve it before executing. ## Quick Start Ask the agent to create a Deep Agent with a custom subagent and human approval required before any file write operation.

Frequently Asked Questions about deep-agents-orchestration

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I create a custom subagent in Deep Agents?▼

Pass a subagents array to create_deep_agent with each subagent's name, description, system prompt, and tools. The main agent then delegates work using the task tool, and the subagent executes autonomously and returns a final report.

How do I add human approval before a tool runs in LangGraph agents?▼

Set interrupt_on in create_deep_agent with the tool names requiring approval, and provide a checkpointer like MemorySaver. When the tool is called, execution pauses and you resume with a Command containing an approve, reject, or edit decision.

Why is my Deep Agent interrupt not working?▼

Interrupts require a checkpointer such as MemorySaver passed to create_deep_agent, plus a consistent thread_id in the invoke config. Without both, the agent cannot pause execution or resume the interrupted workflow.

Do custom subagents inherit skills from the main agent?▼

No, custom subagents do not inherit skills from the main agent. You must provide skills explicitly in each subagent's configuration, though the default general-purpose subagent does inherit the main agent's skills.

Are Deep Agents subagents stateful across multiple task calls?▼

No, subagents are stateless and start fresh on every task call. Provide complete instructions in a single delegation call rather than relying on context from previous invocations.

Related Skills

Explore More Software Engineering Skills→
tyronerosstyroneross
1

building-with-deepagents

Provide structured guidelines for building and refactoring DeepAgents agents.

Community
Advanced
danmaraudadanmarauda

Convex Agents Human Agents

Integrate human agents into automated agent threads for approval workflows.

Community
Advanced
agenticgogolagenticgogol
1

axial-coding-new

Cluster open-coded failure notes into an approved taxonomy and ranked remediation backlog.

Community
Advanced
JosephRobles23JosephRobles23

langgraph-fundamentals

Teach LangGraph state management, nodes, edges, and conditional routing.

Community
Advanced