INVOKE THIS SKILL when using subagents, task planning, or human approval in Deep Agents. Covers SubAgentMiddleware, TodoList for planning, and HITL interrupts.
This skill does not declare a tool allowlist. The agent host applies whatever default tools are available at runtime.
SKILL.md / Manifest
https://raw.githubusercontent.com/langchain-ai/langchain-skills/main/config/skills/deep-agents-orchestration/SKILL.mdRegistry
github (via claudemarketplaces.com)