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.
npx agentmods add rules/haohao-end/openagent/030-langchaingit clone --depth 1 https://github.com/Haohao-end/openagentWrote 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.
[](https://agentmods.dev/rules/haohao-end/openagent/030-langchain)<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>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.
| Model | Per session | Once 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 |
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.
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.
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.
- 4d ago First seen · 15 lines · 0 tokens per session scan A 6c5ff84da41d
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.
Other cursor rules, from other repositories
ai-coding
Cursor rule "ai-coding" from ly1836/spring-ai-rag-demo, covering ai 协作规则, 语言, commit 格式 and ai 行为约束.
spring-ai-rag-demo-module
Spring AI RAG Demo 项目专属架构与编码约束.
openspec-docs
OpenSpec 文档编写语言与结构约束.
frontend-features
How we build new full-stack features including frontend APIs, file structure, and components.
global
The most important domain objects are in observations.ts, traces.ts, scores.ts.
public-api
How to create new public api routes for Litefuse.