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/astrogirlnim/SkyFiMCPWrote 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/astrogirlnim/skyfimcp/python-development)<a href="https://agentmods.dev/rules/astrogirlnim/skyfimcp/python-development"><img src="https://agentmods.dev/badge/rules/astrogirlnim/skyfimcp/python-development/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/rules/astrogirlnim/skyfimcp/python-development"><img src="https://agentmods.dev/badge/rules/astrogirlnim/skyfimcp/python-development.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00000 | $0.01641 |
| Opus 5.5 | $0.00000 | $0.00656 |
| Sonnet 5.5 | $0.00000 | $0.00328 |
| Haiku 4.5 | $0.00000 | $0.00164 |
Grade A, and why
python-development 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 1mo 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 — 282 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Python Development
// Description: Modern Python development practices with type hints, testing, and AI-friendly patterns // Recommended Globs: **/*.py, **/pyproject.toml, **/requirements.txt, */.env
Project Structure
project_name/
├── src/
│ └── project_name/
│ ├── __init__.py
│ ├── models/
│ ├── services/
│ ├── controllers/
│ └── utils/
├── tests/
│ ├── __init__.py
│ ├── conftest.py
│ ├── unit/
│ └── integration/
├── docs/
├── .env
├── .env.example
├── .gitignore
├── pyproject.toml
├── README.md
└── requirements.txt
Type Annotations
Always use type hints for functions and classes:
from typing import Optional, List, Dict, Any, TypeVar, Generic
from typing_extensions import TypedDict # For Python <3.8
T = TypeVar('T')
class DataResponse(TypedDict):
success: bool
data: Dict[str, Any]
error: Optional[str]
class Repository(Generic[T]):
"""Generic repository pattern implementation.
Args:
model: The model class this repository handles
Attributes:
model_class: Stored model class reference
"""
def __init__(self, model: type[T]) -> None:
self.model_class = model
async def find_by_id(self, id: str) -> Optional[T]:
"""Retrieve an entity by its ID.
Args:
id: The unique identifier of the entity
Returns:
Optional[T]: The found entity or None
"""
# Implementation
...
Testing with Pytest
Use pytest fixtures and type annotations in tests:
from typing import TYPE_CHECKING, AsyncGenerator
import pytest
from httpx import AsyncClient
if TYPE_CHECKING:
from _pytest.capture import CaptureFixture
from _pytest.fixtures import FixtureRequest
from _pytest.logging import LogCaptureFixture
from _pytest.monkeypatch import MonkeyPatch
from pytest_mock.plugin import MockerFixture
@pytest.fixture
async def client() -> AsyncGenerator[AsyncClient, None]:
"""Create async test client.
Yields:
AsyncClient: The test client instance
"""
async with AsyncClient() as client:
yield client
@pytest.mark.asyncio
async def test_create_user(
client: AsyncClient,
mocker: MockerFixture,
caplog: LogCaptureFixture,
) -> None:
"""Test user creation endpoint.
Args:
client: The test client
mocker: Pytest mocker fixture
caplog: Pytest log capture fixture
"""
response = await client.post('/users', json={
'username': 'test_user',
'email': '[email protected]'
})
assert response.status_code == 201
assert 'User created successfully' in caplog.text
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.
- 1mo ago First seen · 282 lines · 1,641 tokens per session scan A 732594e674fa
python-development is a cursor rule published in the GitHub repository astrogirlnim/SkyFiMCP (1 stars, last pushed 1y ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,641 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 2026-08-31.
Other cursor rules, from other repositories
python_tests
We use the unit tests to cover internal behavior that can work without the web / backend counterpart. We aim for 95%+ unit test coverage of our Python code in lib/streamlit.
hypothesis
Definitive guidelines for writing robust, maintainable, and performant property-based tests using Hypothesis with Python and pytest.
pytest
This guide defines our team's definitive best practices for writing fast, reliable, and maintainable tests using pytest, ensuring consistency and high code quality across projects.
mypy
This guide provides definitive, actionable best practices for using mypy to ensure robust static type checking in Python projects, focusing on modern patterns and common pitfalls.
python-general-coding-standards
A set of general standards for Python projects, including type hints, input checking, code style, security, web requests, background work, and tests. It also covers FastAPI-specific tasks such as CORS and authentication.
style
Cursor rule "style" from Ayanami1314/swe-pruner, covering style guide, bad, good, test style and bad.