本页还没有译文
本页 21 段还没译成Español,下面显示的是英文原文。Use subagents in Deep Agents Code
还没翻译译自英文(docs.langchain.com)本页 21 段都还没译
Define custom synchronous subagents as markdown files so Deep Agents Code can delegate specialized tasks to them.
Note
Async subagents are not available to end-users in Deep Agents Code at this time.
Each subagent lives in its own folder with an AGENTS.md file:
.deepagents/agents/{subagent-name}/AGENTS.md # Project-level
~/.deepagents/{agent}/agents/{subagent-name}/AGENTS.md # User-levelProject subagents override user subagents with the same name (see precedence rules).
Continue the parent conversation
The built-in general-purpose subagent inherits the parent agent's conversation and system prompt. This context lets delegated work continue without repeating the investigation, decisions, or other details already established in the parent conversation.
To run the built-in general-purpose subagent in isolated mode instead, set the following variable in your shell or global ~/.deepagents/.env:
export DEEPAGENTS_CODE_FORKED_SUBAGENTS=falseThe frontmatter requires name and description (same as the SubAgent dictionary spec). The markdown body becomes the subagent's system_prompt. In addition to the base spec, AGENTS.md files support an optional model frontmatter field that overrides the main agent's model for this subagent. Use the provider:model-name format (e.g., anthropic:claude-opus-4-8, openai:gpt-5.5). Omit it to inherit the main agent's model.
Note
Other SubAgent fields (tools, middleware, interrupt_on, skills) are currently not configurable via AGENTS.md frontmatter—custom subagents defined this way inherit the main agent's tools. Use the SDK directly for full control.
File format
Subagent AGENTS.md files use YAML frontmatter followed by a markdown body:
---
name: researcher
description: Research topics on the web before writing content
model: anthropic:claude-haiku-5-5
---
You are a research assistant with access to web search.
## Your Process
1. Search for relevant information
2. Summarize findings clearlyDynamic subagents
dcode ships with the code interpreter enabled, so dynamic subagents work out of the box.
To trigger dynamic subagents, ask for a "workflow". Instead of doing the work itself or managing fan-out through its native task tool, the agent writes an orchestration script that calls the built-in task() global and runs it in the code interpreter. For example: "Run a workflow to review every file in src/ for SQL injection."
As subagents spawn, dcode shows them live in the dynamic subagents panel, grouped into phases by dispatch.

You can also use dynamic subagents in the coding agent of your choice over ACP (for example, Zed).
Example: cost-efficient subagents
Use a cheaper, faster model for simple delegation tasks while keeping the main agent on a more capable model:
---
name: general-purpose
description: General-purpose agent for research and multi-step tasks
model: anthropic:claude-haiku-5-5
---
You are a general-purpose assistant. Complete the task efficiently and return a concise summary.This overrides the built-in general-purpose subagent, routing all delegated tasks to a cheaper model. See Override the general-purpose subagent for more.