langchain-py-pack
LangChain 1.0 + LangGraph 1.0 skill pack for Python. Pain-first skills anchored to a 68-entry pain catalog covering content blocks, streaming token accounting, structured-output, vector stores, checkpointing, HITL, middleware, Deep Agents, and native OTEL. Includes 33 skills across four epics.
Installation
Open Claude Code and run this command:
/plugin install langchain-py-pack@claude-code-plugins-plus
Use --global to install for all projects, or --project for current project only.
What It Does
> Pain-first Claude Code skills for LangChain 1.0 and LangGraph 1.0 in Python. > Every skill opens with a specific production failure mode — not capability prose.
Skills (33) plugin-local skills
Wire LangChain 1.
Paste-match catalog of 14 real LangChain 1.
Works correctly with LangChain 1.
Compose LangChain 1.
Control LangChain 1.
Load and chunk documents for LangChain 1.
Produce a reproducible, sanitized diagnostic bundle for a LangChain / LangGraph incident — environment snapshot, version manifest, filtered astream_events(v2) transcript, propagating callback stack, LangSmith trace URL — so a debug colleague can reproduce the failure without a live terminal.
Build a LangGraph 1.
Deploy a LangChain 1.
Build and query vector stores with LangChain 1.
Enforce tenant isolation and role-based access across LangChain 1.
Build reproducible evaluation pipelines for LangChain 1.
Triage LangChain 1.
Build a correct LangGraph 1.
Build a correct LangGraph 1.
Persist LangGraph agent state correctly with MemorySaver and PostgresSaver — thread_id discipline, JSON-serializable state rules, time-travel, schema migration.
Build LangGraph 1.
Pick the correct LangGraph 1.
Compose LangGraph 1.
Build a fast, deterministic local test loop for LangChain 1.
Build composable middleware for LangChain 1.
Invoke Claude, GPT-4o, and Gemini through LangChain 1.
Build reliable dev / staging / prod isolation for LangChain 1.
Wire LangSmith tracing and custom metric callbacks into a LangChain 1.
Wire LangChain 1.
Tune LangChain 1.
Manage LangChain 1.
Rate-limit LangChain 1.
A reference layered architecture for production LangChain 1.
Compose LangChain 1.
Harden a LangChain 1.
Migrate a LangChain 0.
Dispatch LangChain 1.
How It Works
1. Install the pack
/plugin install langchain-py-pack@claude-code-plugins-plus
2. Install LangChain 1.0 + LangGraph 1.0
python -m venv .venv && source .venv/bin/activate
pip install "langchain>=1.0,<2.0" "langchain-core>=1.0,<2.0" \
"langchain-anthropic>=1.0,<2.0" \
"langgraph>=1.0,<2.0"
3. A minimal agent with memory
from langchain_anthropic import ChatAnthropic
from langgraph.prebuilt import create_react_agent
from langgraph.checkpoint.memory import MemorySaver
llm = ChatAnthropic(model="claude-sonnet-4-6", temperature=0)
def add(a: int, b: int) -> int:
"""Add two integers."""
return a + b
agent = create_react_agent(
model=llm,
tools=[add],
checkpointer=MemorySaver(),
)
config = {"configurable": {"thread_id": "demo-1"}}
result = agent.invoke(
{"messages": [("user", "What is 17 + 25?")]},
config=config,
)
print(result["messages"][-1].content)