deep-agents-core

deep-agents-core29 wordsInspect firstinspect-then-install

Extended LangChain row with Deep Agents core/memory/orchestration, middleware/HITL, dependency pinning, and Managed Deep Agents ops. Confirm source-list slugs before apply.

Quick Start

Install:

npx skills add langchain-ai/langchain-skills --skill ecosystem-primer --skill langchain-fundamentals --skill langgraph-fundamentals --skill langgraph-human-in-the-loop --skill langgraph-persistence --skill langchain-rag --skill deep-agents-core --skill deep-agents-memory --skill deep-agents-orchestration --skill langchain-middleware --skill langchain-dependencies --skill managed-deep-agents -y -g -a antigravity claude-code codex crush cursor gemini-cli github-copilot grok opencode

Use: /deep-agents-core

Works with Claude Code, Gemini CLI, OpenCode, and other agentskills.io-compatible agents.

Curated external (hand-maintained)

Composed compose-external-wave-3 using authoring SSOT (docs/src/authoring/skills/deep-agents-core.mdx) + research. Do not run wagents docs generate on this file (HAND-MAINTAINED sentinel). Run external-skill-auditor before using in production or promoting.

What It Does

Part of official langchain-ai/langchain-skills (early dev). Agent architecture, harness setup, and SKILL.md format for Deep Agents. See README for LangChain/LangGraph/Deep Agents selection via primer.

Harness Coverage

Targets verified harnesses: antigravity, claude-code, codex, crush, cursor, gemini-cli, github-copilot, grok, opencode.

Portable multi-harness install command:

npx skills add langchain-ai/langchain-skills --skill ecosystem-primer --skill langchain-fundamentals --skill langgraph-fundamentals --skill langgraph-human-in-the-loop --skill langgraph-persistence --skill langchain-rag --skill deep-agents-core --skill deep-agents-memory --skill deep-agents-orchestration --skill langchain-middleware --skill langchain-dependencies --skill managed-deep-agents -y -g -a antigravity claude-code codex crush cursor gemini-cli github-copilot grok opencode

Trust / Audit

Trust tier: Inspect first (needs-inspection)

Curated status: inspect-then-install

Risk notes: Extended LangChain row with Deep Agents core/memory/orchestration, middleware/HITL, dependency pinning, and Managed Deep Agents ops. Confirm source-list slugs before apply.

Entry maintained via authoring + research for compose-external-wave-3; provenance and audit notes are authoritative there (research context is advisory).

Install Prerequisites

Group install via langchain-ai/langchain-skills npx … —skill deep-agents-* etc; status=inspect-then-install.

Public Metadata

Field	Value
Source Type	curated-external
Display Source	langchain-ai/langchain-skills
Source Kind	github
Installability	portable command
Review State	curated
Trust Tier	needs-inspection
Target Agents	antigravity, claude-code, codex, crush, cursor, gemini-cli, github-copilot, grok, opencode

General

Field	Value
Name	deep-agents-core

Curated catalog entry

docs/src/authoring/skills/deep-agents-core.mdx (full SSOT excerpt)

---
name: "deep-agents-core"
description: "Extended LangChain row with Deep Agents core/memory/orchestration, middleware/HITL, dependency pinning, and Managed Deep Agents ops. Confirm source-list slugs before apply."
title: "Deep Agents Core"
source_kind: "curated-external"
source: "langchain-ai/langchain-skills"
install_source: "langchain-ai/langchain-skills"
status: "inspect-then-install"
trust_tier: "needs-inspection"
provenance_status: "verified-install-command"
install_command: "npx skills add langchain-ai/langchain-skills --skill ecosystem-primer --skill langchain-fundamentals --skill langgraph-fundamentals --skill langgraph-human-in-the-loop --skill langgraph-persistence --skill langchain-rag --skill deep-agents-core --skill deep-agents-memory --skill deep-agents-orchestration --skill langchain-middleware --skill langchain-dependencies --skill managed-deep-agents -y -g -a antigravity claude-code codex crush cursor gemini-cli github-copilot grok opencode"
target_agents: [antigravity, claude-code, codex, crush, cursor, gemini-cli, github-copilot, grok, opencode]
source_url: "https://github.com/langchain-ai/langchain-skills"
notes: "Extended LangChain row with Deep Agents core/memory/orchestration, middleware/HITL, dependency pinning, and Managed Deep Agents ops. Confirm source-list slugs before apply."
risk_notes: "Extended LangChain row with Deep Agents core/memory/orchestration, middleware/HITL, dependency pinning, and Managed Deep Agents ops. Confirm source-list slugs before apply."
promotion_policy: "Inspect source, hooks, scripts, credentials, and dedupe before install."
provenance_evidence: "Curated `npx skills add` command with named `--skill` selectors under `inspect-then-install` in config/external-skills.md."
---

{/* GENERATED-AUTHORING: source=config/external-skills.md; entry=deep-agents-core; re-run migration to refresh */}

Extended LangChain row with Deep Agents core/memory/orchestration, middleware/HITL, dependency pinning, and Managed Deep Agents ops. Confirm source-list slugs before apply.

Install / provenance (from authoring frontmatter + research):

Field	Value
install_command	npx skills add langchain-ai/langchain-skills --skill ecosystem-primer --skill langchain-fundamentals --skill langgraph-fundamentals --skill langgraph-human-in-the-loop --skill langgraph-persistence --skill langchain-rag --skill deep-agents-core --skill deep-agents-memory --skill deep-agents-orchestration --skill langchain-middleware --skill langchain-dependencies --skill managed-deep-agents -y -g -a antigravity claude-code codex crush cursor gemini-cli github-copilot grok opencode
source	langchain-ai/langchain-skills
source_url	https://github.com/langchain-ai/langchain-skills
trust_tier	needs-inspection
curated_status	inspect-then-install
target_agents	antigravity, claude-code, codex, crush, cursor, gemini-cli, github-copilot, grok, opencode

Resources

Skill Catalog Browse custom and external skills.

CLI Reference Install and manage skills.