Every premium and members-only resource for $9.99/month, as a no-commitment subscription. See the plans

PalateKit

Menu

Request a resource

Describe the resource you are missing in one sentence. We will email you when it is published.

0 / 280

Unlock PalateKit

Unlock everything

Plan

Paying means accepting our terms of sale.

Secure payment by Stripe. Receipts and invoices sent by email.

Welcome back

Sign in to install, download or save this resource. A free account is enough for free resources.

LangGraph deep agent with planner and subagents v1.0.0

Use this resource to build a LangGraph agent with planning and subagents

New

  • 336 downloads
  • 177 likes
  • 180 saves

Free

Install with the CLI

In a terminal, from the folder you want:

npx --yes palatekit@latest install langgraph-deep-agent-architecture

With no option, the skill goes to ~/.agents/skills/; add --agent claude-code (or codex, cursor…) to target an agent.

First time: connect the CLI with

npx --yes palatekit@latest login

The agent assembles a planner, subagents with explicit instructions, a virtual file system with eviction and a bounded reflection loop. It checkpoints state only at user-visible boundaries. You get an architecture for long-running tasks.

Mostly picked by

Updated November 2, 2026

Card for the “LangGraph deep agent with planner and subagents” skill

Details

Generates with
Your agent's model
Licence
MIT

Similar resources

View all

What you get

  • SKILL.md: four-component architecture and build steps
  • references/virtual-filesystem-patterns.md: virtual file system with eviction

Good fit for

  • Your agent must plan and delegate long subtasks
  • Your agent state keeps growing and slowing each step

Not for

    Tags

    • langgraph
    • agents
    • subagents
    • planning

    About

    You say

    “Build a LangGraph agent that plans a market study and delegates data collection to subagents.”

    Card for the “LangGraph deep agent with planner and subagents” skill

    Skill published by Jeremy Longshore <jeremy@intentsolutions.io> under the MIT license, delivered in its original version.

    Show more

    How to use it

    1. Install the skill in your agent's skills folder
    2. Ask your agent to build a LangGraph agent with planning and subagents
    3. Review and adjust the result

    Content preview

    Files

    • LICENSE1.1 KB
    • NOTICE-PALATEKIT.md0.5 KB
    • references/architecture-blueprint.md8 KB
    • references/one-pager.md4 KB
    • references/reflection-loop.md7.2 KB
    • references/subagent-prompting.md6.8 KB
    • references/virtual-filesystem-patterns.md6.6 KB
    • SKILL.md19.4 KB

    Origin and licence

    Listed unmodified

    Author
    Jeremy Longshore <jeremy@intentsolutions.io>
    Source
    github.com/jeremylongshore/tons-of-skills-marketplace/tree/ab85a061f7bcc039dac13ee193de7a4cd4388571/skills/.curated/langchain-deep-agents
    Licence
    MIT

    Notice

    « langchain-deep-agents » (Jeremy Longshore <jeremy@intentsolutions.io>, MIT) livré dans sa version d'origine : fiche en français et en anglais par PalateKit.

    User reviews

    –

    No ratings yet

    Loading reviews…

    Delete your review?

    Your rating and comment will be removed from the page.