awesome-cursor-rules-mdc is a generator that creates Cursor MDC rule files from structured library information, using semantic search and language models to gather and organize guidance. Developers use it to produce reusable rules for libraries in Cursor, and the catalogue includes 200 of those rules.
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.
git clone --depth 1 https://github.com/sanjeed5/awesome-cursor-rules-mdcWrote 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/sanjeed5/awesome-cursor-rules-mdc/peewee)<a href="https://agentmods.dev/rules/sanjeed5/awesome-cursor-rules-mdc/peewee"><img src="https://agentmods.dev/badge/rules/sanjeed5/awesome-cursor-rules-mdc/peewee.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 5.1 | $0.02019 | $0.02019 |
| Opus 5 | $0.01009 | $0.01009 |
| Sonnet 5 | $0.00404 | $0.00404 |
| Haiku 4.5 | $0.00202 | $0.00202 |
Grade A, and why
peewee 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.
How it starts
The opening of the file, as written. The whole thing — 274 lines — stays where its author put it; the contents beside it link to each section on GitHub.
peewee Best Practices
Peewee is a lightweight, expressive ORM for Python. These guidelines ensure your Peewee code is clean, efficient, and aligns with modern best practices as of 2025.
1. Code Organization and Structure
Always establish a clear, DRY (Don't Repeat Yourself) structure for your Peewee models and database connection.
1.1 Define a BaseModel for Database Connection
Centralize your database instance within a BaseModel to avoid repetitive declarations and ensure all models use the same connection.
❌ BAD: Direct database assignment in every model
from peewee import *
db = SqliteDatabase('app.db')
class User(Model):
username = CharField()
class Meta:
database = db # Repeated for every model
✅ GOOD: Inherit from a BaseModel
from peewee import *
db = SqliteDatabase('app.db')
class BaseModel(Model):
class Meta:
database = db
class User(BaseModel):
username = CharField(unique=True)
1.2 Model Naming Convention
Name your model classes in the singular form. Peewee automatically pluralizes table names (e.g., User -> user).
❌ BAD: Plural model name
class Users(BaseModel): # Table might be 'userss' or 'users' depending on backend
name = CharField()
✅ GOOD: Singular model name
class User(BaseModel): # Table will be 'user'
name = CharField()
1.3 Explicit Imports for Model Definitions
For model definition files, use from peewee import * for convenience. This is a common and accepted pattern within the Peewee ecosystem. For other modules or specific utility functions, prefer explicit imports.
❌ BAD: Overly verbose imports for model definitions
from peewee import Model, CharField, IntegerField, SqliteDatabase, DateTimeField # ... and so on
✅ GOOD: Concise model definition imports
from peewee import * # For model definition files (e.g., models.py)
import datetime
# In other files (e.g., main.py, services.py), for specific functions/classes:
from peewee import SqliteDatabase, DoesNotExist
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 · 274 lines · 2,019 tokens per session scan A e7c2d6b061ad
peewee is a cursor rule published in the GitHub repository sanjeed5/awesome-cursor-rules-mdc (3,571 stars, last pushed 3mo ago), licensed CC0-1.0. It adds 2,019 tokens to every session, about $0.0101 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 2026-09-03.
Other cursor rules, from other repositories
database-algorithm-rules
Database algorithm rules guide Python applications that store and retrieve data, including containerized services. They cover schema design, indexes, query efficiency, transactions, connection pools, caching, retries, and migrations.
django-models
A small set of rules for Django models, the Python framework's definitions of database-backed data. It also guides how Django code should access and validate that data.
sqlmodel
Satisfying the type checker when working with SQLModel.
alembic
Alembic migration patterns and conventions for Python SQLAlchemy projects.
sqlalchemy
SQLAlchemy database patterns and conventions.
sqlalchemy-patterns
SQLAlchemy models, queries, relationships.