# Langgraph Workflows

> LangGraph

- Skill: `comeonoliver/langgraph-workflows` (Agent Skill)
- Install (CLI): `npx skillmds@latest add comeonoliver/langgraph-workflows`
- Raw SKILL.md: https://api.skillmd.com/api/skills/comeonoliver/langgraph-workflows/raw
- Safety review: pending (external: skill-scanner PASS, skillspector PASS)
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: Coding & Dev Tools
- Author: ComeOnOliver (https://skillmd.com/u/comeonoliver)
- Updated: 2026-09-21
- Page: https://skillmd.com/skills/comeonoliver/langgraph-workflows

---

# LangGraph

## Basic Agent Graph
```python
from langgraph.graph import StateGraph, END
from typing import TypedDict

class AgentState(TypedDict):
    messages: list
    next_step: str

def call_model(state: AgentState) -> AgentState:
    response = llm.invoke(state["messages"])
    return {"messages": state["messages"] + [response]}

def should_continue(state: AgentState) -> str:
    if state["messages"][-1].tool_calls:
        return "tools"
    return END

graph = StateGraph(AgentState)
graph.add_node("agent", call_model)
graph.add_node("tools", tool_executor)
graph.add_conditional_edges("agent", should_continue, {"tools": "tools", END: END})
graph.add_edge("tools", "agent")
graph.set_entry_point("agent")

app = graph.compile()
result = app.invoke({"messages": [HumanMessage("What's the weather?")]})
```

## Checkpointing for persistence, human-in-the-loop, branching, subgraphs