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.
npx agentmods add rules/savagelysubtle/big-brain-memory-bank/1002-python-type-hintinggit clone --depth 1 https://github.com/savagelysubtle/BIG-BRAIN-Memory-BankWrote 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/savagelysubtle/big-brain-memory-bank/1002-python-type-hinting)<a href="https://agentmods.dev/rules/savagelysubtle/big-brain-memory-bank/1002-python-type-hinting"><img src="https://agentmods.dev/badge/rules/savagelysubtle/big-brain-memory-bank/1002-python-type-hinting.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 | $0.00000 | $0.01326 |
| Opus 5 | $0.00000 | $0.00663 |
| Sonnet 5 | $0.00000 | $0.00265 |
| Haiku 4.5 | $0.00000 | $0.00133 |
Grade A, and why
1002-python-type-hinting 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 3d 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 — 203 lines — stays where its author put it; the contents beside it link to each section on GitHub.
description: WHEN writing Python code ALWAYS use type hints for functions, methods, and variables globs: src/the_aichemist_codex/**/*.py
Args:
{parameter_name} ({parameter_type}): {parameter_description}
Returns:
{return_type}: {return_description}
Raises:
{exception_type}: {exception_description}
"""
</template>
</function>
<class>
<template>
"""
{class_description}
Attributes:
{attribute_name} ({attribute_type}): {attribute_description}
"""
</template>
</class>
Args:
document (Document): The document to process
tags (Optional[List[str]]): Tags to apply to the document
max_length (int): Maximum length to process
Returns:
Dict[str, Any]: Processed document data with applied tags
Raises:
ValueError: If document is empty or invalid
"""
if not document.content:
raise ValueError("Document content cannot be empty")
result: Dict[str, Any] = {
"id": document.id,
"content": document.content[:max_length],
"processed_at": datetime.now()
}
if tags:
document.tags.update(tags)
result["tags"] = list(document.tags)
return result
</code>
</good-example>
<good-example>
<description>Class with typed attributes and methods</description>
<code>
class DocumentProcessor: """ Processes documents and applies transformations.
Attributes:
max_length (int): Maximum content length to process
supported_formats (Set[str]): Document formats supported by this processor
"""
def __init__(self, max_length: int = 1000) -> None:
"""
Initialize the document processor.
Args:
max_length (int): Maximum content length to process
"""
self.max_length: int = max_length
self.supported_formats: Set[str] = {"txt", "md", "pdf"}
def process(self, document: Document) -> ProcessedDocument:
"""
Process a document into a standardized format.
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.
- 3d ago First seen · 203 lines · 0 tokens per session scan A 2d41ec7db82a
1002-python-type-hinting is a cursor rule published in the GitHub repository savagelysubtle/BIG-BRAIN-Memory-Bank (5 stars, last pushed 1y ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,326 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
Deep-Learning-Developer
You are an expert in deep learning, transformers, diffusion models, and LLM development, with a focus on Python libraries such as PyTorch, Diffusers, Transformers, and Gradio.
Jupyter Data Analyst
You are an expert in data analysis, visualization, and Jupyter Notebook development, with a focus on Python libraries such as pandas, matplotlib, seaborn, and numpy.
virtual-environment
Rules for using Python virtual environments - check requirements.txt for installed libraries and use the existing virtual environment directory.
Python安全规范
Cursor rule "Python安全规范" from nongjun/feishu-cursor-claw, covering python 安全, 密钥管理, 安全扫描 and 参考.
cursorrules
You are building an AI/ML project with Python. The project uses PyTorch for model training, handles data pipelines with proper validation, tracks experiments systematically, and follows production ML engineering practices. Code is type-hinted, tested, and reproducible.
10-python-standards
General Python engineering standards.