deep-agents-orchestration

Agent workflows

langchain-ai/langchain-skillsskills.sh ↗

Installs

12,833

deduplicated, at the last sync

Since we started

+1.4%

40 readings, about 2 hours apart. Not a live curve.

Our category

Agent workflows

ours

Last read

Sep 3, 2026

from the directory

Our brief

ours

This skill orchestrates complex agent workflows by providing three core capabilities: delegating specialized tasks to subagents, planning multi-step operations using a todo list, and requiring human approval for sensitive actions. It allows the main agent to manage complexity, isolate work, and ensure compliance before executing critical steps.

What it produces
  • final report from subagent
  • todo list of tasks with status
  • state indicating pending action or decision
What it needs
  • user message/instruction
  • subagents configuration (name, tools)
  • thread_id for state persistence
Paid services

not detected

The evidence does not provide information regarding paid plans or API costs.

Registration

not detected

The evidence does not mention any required registration process.

Limits and human review

The skill cannot make subagents stateful, meaning they are ephemeral and require complete instructions in a single call. It also cannot configure tool names (like `task` or `write_todos`) or the HITL protocol structure itself. Furthermore, it requires a checkpointer when using human-in-the-loop interrupts.

Evidenceconfig/skills/deep-agents-orchestration/SKILL.md:1-438
config/skills/deep-agents-orchestration/SKILL.md1–438 · excerpt truncated
---
name: deep-agents-orchestration
description: "INVOKE THIS SKILL when using subagents, task planning, or human approval in Deep Agents. Covers SubAgentMiddleware, TodoList for planning, and HITL interrupts."
---

<overview>
Deep Agents include three orchestration capabilities:

1. **SubAgentMiddleware**: Delegate work via `task` tool to specialized agents
2. **TodoListMiddleware**: Plan and track tasks via `write_todos` tool
3. **HumanInTheLoopMiddleware**: Require approval before sensitive operations

All three are automatically included in `create_deep_agent()`.
</overview>

---

## Subagents (Task Delegation)

<when-to-use-subagents>

| Use Subagents When | Use Main Agent When |
|-------------------|-------------------|
| Task needs specialized tools | General-purpose tools sufficient |
| Want to isolate complex work | Single-step operation |
| Need clean context for main agent | Context bloat acceptable |

</when-to-use-subagents>

<how-subagents-work>
Main agent has `task` tool -> creates fresh subagent -> subagent executes autonomously -> returns final report.

**Default subagent**: "general-purpose" - automatically available with same tools/config as main agent.
</how-sub

Read 1 of 1 text files in the skill.

Checked September 2026 · GemmaWritten from the skill's published files. Check the source before relying on access or cost details.

Installfrom the directory

npx skills add https://github.com/langchain-ai/langchain-skills

Installing happens there, not here. We are an index with an opinion, not a mirror.

What is inside itfrom the directory

SKILL.md

1 files — names only. The directory does not report sizes.

What the auditors foundfrom the directory

A skill is instructions your agent will follow and scripts it may run, so who checked it matters as much as how many people installed it.

Gen Agent Trust HubThis skill provides guidance on orchestrating agents using subagents, task planning, and human-in-the-loop (HITL) workflows. It utilizes the author's own libraries and emphasizes security best practices, such as requiring human approval for sensitive operations like SQL execution or production deployments. No security issues were detected.May 20, 2026 · SAFEpass
SocketNo alertsMay 20, 2026pass
SnykRisk: LOW · No issuesMay 20, 2026 · LOWpass
Runlayer1/1 file flaggedMar 4, 2026 · LOWpass
ZeroLeaksScore: 93/100 · 2 sections analyzedApr 16, 2026 · NONEpass

Installs, reading by readingours

12.7k
12.8k
Aug 31, 202640 readings over 4 days, drawn as the last reading of each day.Sep 3, 2026

Axis starts at 12.7k, not zero — the range is 12.7k to 12.8k.

Asked out loudspoken, not typed

The same skill in the words people use speaking to an assistant rather than typing into a box. Each one carries the situation it came from, and each answer says only what the skill's own files support.

understanding workflow optionsIf I need to delegate a complex task, should I use subagents?

Yes, you should use subagents when the task requires specialized tools or if you want to isolate complex work. This allows the main agent to delegate the job and receive a final report.

planning a large projectHow does this skill help me plan multi-step projects?

It includes TodoListMiddleware, which automatically creates a todo list for complex tasks. This helps track progress by setting items as pending, in_progress, or completed.

deploying code to productionDo I need to worry about human approval for sensitive actions?

The skill supports HumanInTheLoopMiddleware. You can configure specific tools to require human approval before they execute, which is useful for high-stakes operations like deployments.

Filed alongside itours