Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →jeremylongshore/langchain-langgraph-agents
Build a correct LangGraph 1.0 ReAct agent with `create_react_agent` — typed tools, error propagation, recursion caps, and stop conditions that actually stop.
Passed 21 of 21 test cases with the skill, and 14 of 21 without it.
and 5 more in the full report
7 fixed15 passed either way0 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 6 test cases the skill fixed. Same model, same prompt, with and without the skill.
When invoking a LangGraph ReAct agent created with create_react_agent, what is the required top-level dictionary key for sending conversation history or new user prompts?
| Checked | Without skill | With skill |
|---|---|---|
| The response specifies messages as the required input state key. | Passed | Passed |
| The response states that the messages value is a list. | Missed | Passed |
The instructions your model reads when the skill loads.
Two failure modes hit every team writing their first LangGraph 1.0 ReAct agent:
Loop-to-cap on vague prompts (P10). create_react_agent defaults to
recursion_limit=25. A prompt like "help me with my account" never converges —
the model calls a retrieval tool, gets irrelevant results, calls another tool,
and repeats until GraphRecursionError: Recursion limit of 25 reached without hitting a stop condition fires. Cost dashboards show the damage after the
fact: $5-$15 per runaway loop on Sonnet with a 3-tool agent, assuming no tool
is itself expensive.
Silent tool errors on legacy AgentExecutor (P09). The legacy executor
defaults handle_parsing_errors=True and catches tool exceptions, feeding the
error string back as the next observation. When the error serializes to empty
(e.g., a ValueError("") or an HTTP 500 with no body), the loop continues with
no signal. The agent says "I couldn't find the answer" — which was actually a
silent crash three tool calls ago.
This skill walks through defining typed tools with @tool + Pydantic; building
an agent with create_react_agent(model, tools, checkpointer=MemorySaver());
invoking with {"messages": [...]} and a thread-scoped config; setting
recursion_limit per expected agent depth (5-10 interactive, 20-30 planner);
adding middleware for a per-session token budget; and raise-by-default error
propagation. Pin: langgraph >= 1.0, < 2.0, langchain-core >= 1.0, < 2.0.
Pain-catalog anchors: P09, P10, P11, P32, P41, P42, P63.
langgraph >= 1.0, < 2.0 and langchain-core >= 1.0, < 2.0pip install langchain-anthropic or langchain-openailangchain-langgraph-basics (L25) — you already know StateGraph,
MessagesState, and checkpointersANTHROPIC_API_KEY or OPENAI_API_KEYtest cases passed, vs 14 / 21 without
Published skills whose descriptions closely match this one, with their headline benchmark lift.
More skills from the same source and nearby in the registry, with their headline benchmark lift.