cursorrules

A set of project instructions for an AI coding assistant, describing the technologies, folder layout, and coding rules used by an Evo AI project. It covers a Python API built with FastAPI and related database, authentication, caching, and email tools.

In plain words
What is it for?
Use it when working on the project’s API routes, database models and migrations, authentication, agent and chat features, caching, or email notifications.
Why use it?
It gives the assistant the project’s structure and technical conventions, reducing guesses about where code belongs and how it should be written.

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/evolution-foundation/evo-ai/cursorrules
Clone the repo
git clone --depth 1 https://github.com/evolution-foundation/evo-ai

Made for: Cursor.

Per session 2,134 This file is loaded in full into every session.
When invoked 2,134 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 $0.02134 $0.02134
Opus 5 $0.01067 $0.01067
Sonnet 5 $0.00427 $0.00427
Haiku 4.5 $0.00213 $0.00213

Measured 2d ago against content hash a7f2e4172a59, 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 · 232 lines

How it starts

The opening of the file, as written. The whole thing — 232 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Evo AI - Project Rules and Structure

Main Technologies

  • FastAPI: Web framework for building the API
  • SQLAlchemy: ORM for database interaction
  • Alembic: Database migration system
  • PostgreSQL: Main database
  • Pydantic: Data validation and serialization
  • Uvicorn: ASGI server for application execution
  • Redis: Cache and session management
  • JWT: Secure token authentication
  • Bcrypt: Secure password hashing
  • SendGrid: Email service for notifications
  • Jinja2: Template engine for email rendering

Project Structure

src/
├── api/
│   ├── __init__.py        # Package initialization
│   ├── admin_routes.py    # Admin routes for management interface
│   ├── agent_routes.py    # Routes to manage agents
│   ├── auth_routes.py     # Authentication routes (login, registration)
│   ├── chat_routes.py     # Routes for chat interactions with agents
│   ├── client_routes.py   # Routes to manage clients
│   ├── mcp_server_routes.py # Routes to manage MCP servers
│   ├── session_routes.py  # Routes to manage chat sessions
│   └── tool_routes.py     # Routes to manage tools for agents
├── config/
│   ├── database.py        # Database configuration
│   └── settings.py        # General settings
├── core/
│   ├── middleware.py      # API Key middleware (legacy)
│   └── jwt_middleware.py  # JWT authentication middleware
├── models/
│   └── models.py          # SQLAlchemy models
├── schemas/
│   ├── schemas.py         # Main Pydantic schemas
│   ├── chat.py            # Chat schemas
│   ├── user.py            # User and authentication schemas
│   └── audit.py           # Audit logs schemas
├── services/
│   ├── agent_service.py   # Business logic for agents
│   ├── agent_runner.py    # Agent execution logic
│   ├── auth_service.py    # JWT authentication logic
│   ├── audit_service.py   # Audit logs logic
│   ├── client_service.py  # Business logic for clients
│   ├── email_service.py   # Email sending service
│   ├── mcp_server_service.py # Business logic for MCP servers
│   ├── session_service.py # Business logic for chat sessions
│   ├── tool_service.py    # Business logic for tools
│   └── user_service.py    # User management logic
├── templates/
│   ├── emails/
│   │   ├── base_email.html           # Base template with common structure and styles
│   │   ├── verification_email.html   # Email verification template
│   │   ├── password_reset.html       # Password reset template  
│   │   ├── welcome_email.html        # Welcome email after verification
│   │   └── account_locked.html       # Security alert for locked accounts
├── tests/
│   ├── __init__.py        # Package initialization
│   ├── api/
│   │   ├── __init__.py        # Package initialization
│   │   ├── test_auth_routes.py # Test for authentication routes
│   │   └── test_root.py       # Test for root endpoint
│   ├── models/
│   │   ├── __init__.py        # Package initialization
│   │   ├── test_models.py     # Test for models
│   ├── services/
│   │   ├── __init__.py        # Package initialization
│   │   ├── test_auth_service.py # Test for authentication service
│   │   └── test_user_service.py # Test for user service
└── utils/
    ├── logger.py          # Logger configuration
    └── security.py        # Security utilities (JWT, hash)

Read the full file on GitHub · 232 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 · 232 lines · 2,134 tokens per session scan A a7f2e4172a59

Subscribe to this mod's changes

cursorrules is a cursor rule published in the GitHub repository evolution-foundation/evo-ai (608 stars, last pushed 1y ago), licensed Apache-2.0. It adds 2,134 tokens to every session, about $0.0107 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 2026-08-30.