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/eliornl/rolemuleWrote 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/eliornl/rolemule/python-conventions)<a href="https://agentmods.dev/rules/eliornl/rolemule/python-conventions"><img src="https://agentmods.dev/badge/rules/eliornl/rolemule/python-conventions/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/eliornl/rolemule/python-conventions"><img src="https://agentmods.dev/badge/rules/eliornl/rolemule/python-conventions.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 | $0.01307 | $0.01307 |
| Opus 5.5 | $0.00523 | $0.00523 |
| Sonnet 5.5 | $0.00261 | $0.00261 |
| Haiku 4.5 | $0.00131 | $0.00131 |
Grade A, and why
python-conventions 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 — 179 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Python Conventions
Style Rules
- Type hints on all function parameters and return values
- Docstrings with Args / Returns / Raises sections on every public function
- Constants:
UPPERCASE_SNAKE_CASEat module level async/awaitfor all I/O — never mix sync blocking calls in async context- Imports: stdlib → third-party → local, blank line between groups
- Explicit annotations:
List[str],Dict[str, Any],Optional[T]
File Section Template
# =============================================================================
# CONSTANTS AND CONFIGURATION
# =============================================================================
# =============================================================================
# GLOBAL VARIABLES
# =============================================================================
# =============================================================================
# CLASSES/FUNCTIONS
# =============================================================================
FastAPI Endpoint Template
@router.post("/endpoint", response_model=ResponseModel)
async def endpoint_handler(
request_data: RequestModel,
current_user: Dict[str, Any] = Depends(get_current_user),
db: AsyncSession = Depends(get_database),
) -> ResponseModel:
"""
Short description.
Args:
request_data: Description
current_user: Authenticated user from JWT
db: PostgreSQL database session
Returns:
ResponseModel with result data
Raises:
APIError: 400/404/422/500 depending on failure type
"""
try:
# implementation
return ResponseModel(...)
except APIError:
raise # re-raise typed errors unchanged
except Exception as e:
logger.error(f"Operation failed: {e}", exc_info=True)
raise internal_error("Operation failed")
Key rules:
except APIError: raise— never catch and re-wrap typed errors- Use
raise internal_error(...)notraise HTTPException(500, ...) - Always log the exception before re-raising internal errors
- Check resource ownership before modifying it
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 · 179 lines · 1,307 tokens per session scan A 1b70e56009ec
python-conventions is a cursor rule published in the GitHub repository eliornl/rolemule (38 stars, last pushed yesterday), licensed MIT. It adds 1,307 tokens to every session, about $0.0052 per session on Opus 5.5. 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.
Other cursor rules, from other repositories
fastapi
FastAPI patterns and conventions for Python backend development.
skill-fastapi-api
Padrões DARE para APIs REST em Python + FastAPI + Pydantic v2 + SQLAlchemy 2.0 async + alembic. Routers, dependency injection, schemas Pydantic, OAuth2+JWT, slowapi rate limit, pytest+httpx, OpenAPI auto-gerado.
fastapi
Apply when building FastAPI endpoints, Pydantic models, or async APIs. Covers routing, dependency injection, error handling, testing, and OpenAPI hygiene.
best-practices
FastAPI Best Practices - enforces current best practices when working with FastAPI code.
backend-python
Python and FastAPI standards for the backend.
api-design-and-implementation
API Design and Implementation Rules for FastAPI Endpoints.