Deep Agents Orchestration

Official

Orchestrate subagents, plans, and approvals.

Authorlangchain-ai
Version1.0.0
Installs0

System Documentation

What problem does it solve?

This Skill streamlines complex agent workflows by providing robust mechanisms for task delegation to specialized subagents, intelligent task planning, and crucial human-in-the-loop approval for sensitive operations.

Core Features & Use Cases

  • SubAgentMiddleware: Delegate tasks to specialized agents for focused execution.
  • TodoListMiddleware: Automatically generate and track multi-step task plans.
  • HumanInTheLoopMiddleware: Implement approval gates for critical actions.
  • Use Case: An agent needs to deploy code. It can use a "code-deployer" subagent with HITL approval for the deploy_to_prod tool, ensuring safety before execution.

Quick Start

Use the Deep Agents Orchestration skill to delegate a research task to a specialized 'researcher' subagent.

Dependency Matrix

Required Modules

None required

Components

references

💻 Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: Deep Agents Orchestration
Download link: https://github.com/langchain-ai/langchain-skills/archive/main.zip#deep-agents-orchestration

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 471,000+ vetted skills library on demand.