030-langchain

030-langchain is a cursor rule for Cursor from Haohao-end/openagent. It costs 0 tokens per session (177 once invoked), scanned A, original, MIT.

Coding rules for building language-model agents and workflows with LangChain and LangGraph. LangChain connects application steps to language models, while LangGraph manages multi-step or stateful workflows.

In plain words
What is it for?
Use it when implementing agents, multi-step workflows, document retrieval, session memory, tool calls, structured responses, and mocked language-model tests.
Why use it?
It sets consistent choices for chains, memory, tools, structured data, retrieval from stored documents, provider access, and testing.

Cursor rule for Cursor

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add rules/haohao-end/openagent/030-langchain
Clone the repo
git clone --depth 1 https://github.com/Haohao-end/openagent

Made for: Cursor.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for 030-langchain

README.md
[![agentmods](https://agentmods.dev/badge/rules/haohao-end/openagent/030-langchain.svg)](https://agentmods.dev/rules/haohao-end/openagent/030-langchain)
Your own site
<a href="https://agentmods.dev/rules/haohao-end/openagent/030-langchain"><img src="https://agentmods.dev/badge/rules/haohao-end/openagent/030-langchain.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Nothing until a file matches its globs; then the whole rule loads.
When invoked 177 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00000 $0.00177
Opus 5 $0.00000 $0.00088
Sonnet 5 $0.00000 $0.00035
Haiku 4.5 $0.00000 $0.00018

Measured 4d ago against content hash 6c5ff84da41d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

030-langchain scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

api/.cursor/rules/030-langchain.mdc · 15 lines

What it actually says

LangChain/LangGraph Rules:

  • ALWAYS use LCEL (LangChain Expression Language) for simple chains.
  • Use LangGraph for ANY multi-step agent or stateful workflow.
  • NEVER call LLM providers directly — ALWAYS route through the unified provider system (see api/providers/).
  • Structured output: use Pydantic with .with_structured_output() whenever possible.
  • RAG: use configured vector stores (Weaviate) via config.
  • Memory: use Redis-based session or LangGraph checkpointer.
  • Tools: define with @tool decorator and bind to agents properly.
  • Testing: mock LLM calls with fake providers or langchain_core.runnables.
  • Prompt engineering: use PromptTemplate with input_variables explicitly.
Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 4d ago First seen · 15 lines · 0 tokens per session scan A 6c5ff84da41d

Subscribe to this mod's changes

030-langchain is a cursor rule published in the GitHub repository Haohao-end/openagent (807 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 177 tokens. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.