메뉴
Use when editing a DeepAgents project — adding tools, sub-agents, modifying the system prompt, choosing a filesystem backend, or composing extra middlewares (retries, fallbacks, HITL) on top.
기본적으로 소스를 먼저 확인하는 Prompt가 선택됩니다. 직접 명령으로 전환하거나 로컬 사본을 다운로드할 수도 있습니다.
설치 여부를 결정하기 전에 SKILL.md와 SkillsMP에 표시된 보조 파일을 읽어 보세요.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
직접 명령은 검토 Prompt를 거치지 않습니다. 실행하기 전에 소스를 확인하세요.
npx skills add https://github.com/cwijayasundara/agent_cli_langchain --skill langchain-agents-deepagents-code명령은 한 줄로 유지됩니다. 복사하기 전에 가로로 스크롤해 전체 내용을 확인하세요.
로컬 사본을 원하시나요? SkillsMP에서 현재 제공할 수 있는 파일을 다운로드하세요.
SOC 직업 분류 기준
SKILL.md 표시 중
| name | langchain-agents-deepagents-code |
| description | Use when editing a DeepAgents project — adding tools, sub-agents, modifying the system prompt, choosing a filesystem backend, or composing extra middlewares (retries, fallbacks, HITL) on top. |
Targets deepagents>=0.5.3. For API reference (signatures, kwargs, full middleware list), use the mcpdoc MCP tools: fetch_docs("https://docs.langchain.com/oss/python/deepagents/..."). This skill is the opinions layer.
async def callables and run with await agent.ainvoke(...) end-to-end. Mix sync and async sub-agents in the same subagents=[...] list.model=None is deprecated in create_deep_agent (0.5.3). Always pass an explicit model, e.g. init_chat_model("anthropic:claude-sonnet-4-6").CompositeBackend; sandbox is now the default for execution. Permission paths must start with /; path-traversal raises ValueError.Findings object" patterns.subagents=[...] with the new SubAgent shape.create_deep_agent(...) is a thin wrapper over create_agent(...) that pre-installs three middlewares: FilesystemMiddleware (virtual FS + read_file/write_file/edit_file/ls/glob/grep), SubAgentMiddleware (the task tool with named sub-agents), and TodoListMiddleware (the write_todos planning tool). You can stack additional middlewares on top.
The implication: everything you know about agentic middleware applies. See langchain-agents-middleware for the production stack — DeepAgents projects benefit from it just like plain create_agent projects do.
The default FilesystemMiddleware uses an in-memory virtual FS that resets between invocations unless you pass a checkpointer. For production, choose a backend:
| Backend | Scope | When |
|---|---|---|
| Default (in-memory) | Single invocation | Dev, tests |
StateBackend | Single thread (with checkpointer) | Conversation memory only |
StoreBackend(namespace=(assistant_id, user_id)) | Per-user persistent | Production: each user gets isolated files |
CompositeBackend | Mix scopes | E.g. ephemeral scratch + persistent /memories/ |
StoreBackend namespaced by user is the production default. Don't ship a multi-user agent with the in-memory default — files would leak across users.
Filesystem permissions (0.5.2+) — on CompositeBackend you can scope read/write/exec permissions per route, with sandbox as the default. Permission paths must start with / (a leading ./ or path-traversal raises ValueError). Use this to make /memories/ read-only to a sub-agent that should only consume past notes, or to forbid writes outside /scratch/.
For tools that run real shell commands, use ShellToolMiddleware with a sandboxed execution policy (Daytona is the primary supported sandbox). Two lifecycle patterns:
Critical rule the docs only mention in passing: never pass raw API keys into a sandbox. The agent can read_file any file the sandbox can. Use the auth proxy to inject credentials at call time. Treat sandboxes as adversarial environments.
task tool fills in {description}. Keep prompts generic; the parent decides the specifics.instructions= is for the top-level agent, not for sub-agents. Each sub-agent has its own prompt field.researcher sub-agent rarely needs send_email. The per-subagent tools key narrows the surface and improves reliability.async def, drive the parent with await agent.ainvoke(...), and the runtime parallelises sibling sub-agent calls automatically. Don't make a sub-agent async if its body is pure CPU.response_format to a sub-agent and the parent's task tool returns a typed object — much more reliable than parsing free-text findings.# Async sub-agent with structured output
from pydantic import BaseModel
class Findings(BaseModel):
summary: str
sources: list[str]
async def research(state, runtime):
# ... do async I/O (web search, mcp calls) ...
return state
subagents = [
{
"name": "researcher",
"description": "Researches a topic and returns structured findings.",
"prompt": "Research {description} and return findings.",
"tools": [web_search],
"response_format": Findings,
"callable": research, # async def is supported
},
]
create_deep_agent accepts a middleware=[...] parameter that adds to (not replaces) the built-in three. For any production DeepAgent, layer the production stack on top:
from deepagents import create_deep_agent
from langchain.agents.middleware import (
ModelCallLimitMiddleware, ToolCallLimitMiddleware,
ModelRetryMiddleware, ToolRetryMiddleware,
ModelFallbackMiddleware, SummarizationMiddleware,
HumanInTheLoopMiddleware, PIIMiddleware,
)
agent = create_deep_agent(
model="claude-sonnet-4-6", # required as of 0.5.3 — `model=None` is deprecated
tools=TOOLS,
subagents=SUBAGENTS,
instructions=PROMPT,
middleware=[
ModelCallLimitMiddleware(run_limit=50),
ToolCallLimitMiddleware(run_limit=200),
ModelRetryMiddleware(max_retries=3),
ToolRetryMiddleware(max_retries=3),
ModelFallbackMiddleware("openai:gpt-4o-mini"),
SummarizationMiddleware(model="claude-haiku-4-5", trigger=("tokens", 8000), keep=("messages", 20)),
# HITL on irreversible tools — requires checkpointer
HumanInTheLoopMiddleware(interrupt_on={"send_email": {"allowed_decisions": ["approve","edit","reject"]}}),
PIIMiddleware("email", strategy="redact", apply_to_input=True),
],
)
agent.invoke(...) calls within a single LangGraph run, but resets between runs unless you pass a checkpointer with a stable thread_id.HumanInTheLoopMiddleware requires a checkpointer at compile time. create_deep_agent accepts a checkpointer= parameter for this.interrupt_on={...} set on the parent inherits to sub-agents (fixed in 0.5.0). If you want sub-agents to bypass HITL gates, override on the sub-agent definition.ainvoke/astream — calling agent.invoke(...) on an async sub-agent runs it in a sync wrapper and you lose the parallelism benefit.https://docs.langchain.com/oss/python/deepagents/index.md — overviewhttps://docs.langchain.com/oss/python/deepagents/going-to-production.md — backends, sandboxes, deploymenthttps://docs.langchain.com/oss/python/deepagents/memory.md — filesystem backends in depthhttps://docs.langchain.com/oss/python/deepagents/human-in-the-loop.md — HITL patterns