cursorrules

A Cursor AI rules file that explains project coding conventions, but the older .cursorrules format is deprecated in favor of .cursor/rules/*.mdc files.

In plain words
What is it for?
Use it when maintaining a Cursor project or moving its rules into the newer MDC rule files.
Why use it?
It warns developers about the migration and gives agents guidance on structure, code quality, error handling, and tests.

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/jhl-labs/vibe-project/cursorrules
Clone the repo
git clone --depth 1 https://github.com/jhl-labs/vibe-project

Made for: Cursor.

Per session 495 This file is loaded in full into every session.
When invoked 495 The same file — it is already loaded in full.
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 $0.00495 $0.00495
Opus 5 $0.00247 $0.00247
Sonnet 5 $0.00099 $0.00099
Haiku 4.5 $0.00049 $0.00049

Measured 2d ago against content hash cf4a5e5102db, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

cursorrules 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 2d 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.

.cursorrules · 78 lines

How it starts

The opening of the file, as written. The whole thing — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Cursor AI Rules

⚠️ DEPRECATION NOTICE

─────────────────────────────────────────────────────────────

This .cursorrules file format is DEPRECATED.

Cursor will remove support for this format in a future release.

Please migrate to the new Project Rules system:

📁 .cursor/rules/*.mdc

This template includes both formats for compatibility:

- .cursor/rules/general.mdc (always applied)

- .cursor/rules/typescript.mdc (*.ts, *.tsx, *.js, *.jsx)

- .cursor/rules/python.mdc (*.py)

- .cursor/rules/architecture.mdc (domain, application, etc.)

Migration guide: https://docs.cursor.com/context/rules-for-ai

─────────────────────────────────────────────────────────────

You are an expert developer working on this project. Follow these rules strictly.

Project Context

  • Project:
  • Language:

Core Rules

  1. Follow existing code patterns and conventions
  2. Write clean, maintainable, well-documented code
  3. Keep functions small and focused (max 30 lines)
  4. Include proper error handling
  5. Write tests for new functionality

Architecture

Follow layered/clean architecture:

  • Domain: Pure business logic (no external dependencies)
  • Application: Use cases and orchestration
  • Infrastructure: External services, DB
  • Presentation: API/UI layer

Dependencies flow inward (Dependency Inversion).

Security (CRITICAL)

NEVER:

  • Hardcode secrets or credentials
  • Use eval() or dynamic code execution
  • Trust user input without validation
  • Expose sensitive data in logs

ALWAYS:

  • Validate and sanitize all inputs
  • Use parameterized queries
  • Use environment variables for configuration

Git

  • Conventional commits: type(scope): description
  • Atomic commits with clear messages

Response Format

When generating code:

  1. Explain approach briefly
  2. Provide complete implementation
  3. Include necessary imports
  4. Add comments for complex logic

Context Files

For detailed rules, see:

  • .cursor/rules/*.mdc - Project Rules (NEW, recommended)
  • CLAUDE.md - Full project instructions
  • .agent/context.md - Project context
  • .agent/conventions.md - Coding conventions

Read the full file on GitHub · 78 lines

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. 2d ago First seen · 78 lines · 495 tokens per session scan A cf4a5e5102db

Subscribe to this mod's changes

cursorrules is a cursor rule published in the GitHub repository jhl-labs/vibe-project (2 stars, last pushed 7mo ago), licensed MIT. It adds 495 tokens to every session, about $0.0025 per session on Opus 5. 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 2026-08-31.