Skip to content
vibespell

.cursor/rules/project.mdc

Cursor rules for LangChain

Cursor rules are a markdown file with a short frontmatter header. Cursor attaches them to the agent so it stops guessing how this repo builds, tests, and styles code. This copy is written for a LangChain project. This repository builds LLM agents or chains. Model names and prompts are explicit. Tool calls validate their arguments. API keys stay in the environment.

The example uses a balanced, readable style, pragmatic tests, and comments only where the intent is not obvious. Open the generator to make the agent stricter, switch to test-first, quiet the comments, or pick a different file.

The example assumes a Python agent stack such as LangChain or a similar orchestrator already in the repo. It does not assume LangGraph versus a simple chain, or a hosted tracer. Use what the project already imports.

Customize in the generatorBrowse the library

Example file

Balanced strictness, readable style, pragmatic tests. Download name: project.mdc. Legacy path: .cursorrules

---
description: "Working rules for a LangChain repository"
globs: "**/*"
alwaysApply: true
---

# Project rules

Follow these rules on every task in this LangChain repository.
If the project still uses a root `.cursorrules` file, keep the same rules there.

## Stack

This repository builds LLM agents or chains. Model names and prompts are explicit. Tool calls validate their arguments. API keys stay in the environment.

## Layout

- Prompts and chain construction live in a module, not only in a notebook.
- Tools are small functions with a schema. They do not import the whole agent.
- Evals live next to the chain they score.

## Commands

- Tests: `pytest`
- Lint: `ruff check .`
- Eval: `Run the project's eval script if it has one`

Use the script the repo already defines when it differs from the command above.

## Conventions

- Name the model in code or config. Do not rely on an implicit default that can change under you.
- Validate tool arguments with the schema before side effects.
- Bound retries and timeouts on model and tool calls.
- Keep prompts in one place so a change is reviewable.
- Add or update an eval when you change a prompt that affects behavior.
- Secrets come from the environment. They are not default arguments.

## Testing

Add or update tests when behavior changes.

Test the tool with a fake model or a direct function call. Assert the side effect did not run on invalid input.

## Style

- Optimize for the next reader over the shortest diff.
- Comment only when the why is non-obvious.
- Name things the way neighboring files already do.
- Do not reformat code you did not change.

## Errors

- Fail at the boundary. Do not swallow errors.
- Return a structured tool error the model can read. Unexpected exceptions should fail the call, not invent an answer.

## Scope

- Do the requested task. Do not refactor unrelated code.
- Match the rigor already in the repo. Fix what you touch.
- Ask one clarifying question only when the task cannot be finished without it. Otherwise state the assumption and continue.

## Avoid

- Do not give a tool unrestricted shell or filesystem access.
- Do not log full prompts when they may contain user secrets.
- Do not catch a tool error and return a success string.
- Do not add a second orchestration library beside the one the repo uses.

## Done when

- The requested behavior works.
- `pytest` passes, including a test that a bad tool argument does not reach the side effect.
- The diff stays inside the task.
- You list anything you could not run.

Add it to the project

  1. 01

    Copy a starting file

    Copy the example Cursor rules on this page, or open the generator if you want different testing, strictness, or comment rules.

  2. 02

    Save it at .cursor/rules/project.mdc

    Save it at `.cursor/rules/project.mdc` in the LangChain repo and create the folders if they are missing. If the project still uses one root rules file, save the body as `.cursorrules`.

  3. 03

    Start a fresh agent session

    Rules files are read when a session starts. A chat that is already open may still be using the old instructions.

  4. 04

    Give it one small task

    Ask for one change a LangChain agent often gets wrong, such as a tool whose arguments are validated before it touches the filesystem or the network. If it ignores the file, confirm the path and start a new session.

Questions about this file

Where do I put Cursor rules in a LangChain repo?

Save it at `.cursor/rules/project.mdc` in the LangChain repo and create the folders if they are missing. If the project still uses one root rules file, save the body as `.cursorrules`.

Which tools read this Cursor rules?

Cursor reads `.cursor/rules/*.mdc` and, on older setups, a root `.cursorrules` file. Other tools ignore the frontmatter, so use AGENTS.md when more than one agent edits the repo.

What does the LangChain example assume?

The example assumes a Python agent stack such as LangChain or a similar orchestrator already in the repo. It does not assume LangGraph versus a simple chain, or a hosted tracer. Use what the project already imports.

Does VibeSpell upload my repository?

No. Recipe pages are static, and the generator builds the file in your browser from the options you pick. Your source code never leaves the machine.

Other files for LangChain

Cursor rules for other stacks