pytorch

pytorch is a cursor rule for coding agents from XingjianTao/Cursor-Rules-for-PyTorch-DeepLearning-Beginner. It costs 4,719 tokens per session, scanned A, original, MIT.

A set of coding rules for projects built with PyTorch, a library for creating and training machine-learning models. It covers code organization, performance, security, testing, and common mistakes.

In plain words
What is it for?
Organize folders for data, models, source code, notebooks, and tests; apply PyTorch development practices; and review projects for maintainability, efficiency, security, testing coverage, and likely errors.
Why use it?
Machine-learning projects can become difficult to maintain and check as data, models, and experiments grow. These guidelines give an agent clear conventions for structuring and reviewing the code.

Cursor rule

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/xingjiantao/cursor-rules-for-pytorch-deeplearning-beginner/pytorch
Clone the repo
git clone --depth 1 https://github.com/XingjianTao/Cursor-Rules-for-PyTorch-DeepLearning-Beginner

Wrote 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.

agentmods badge for pytorch

README.md
[![agentmods](https://agentmods.dev/badge/rules/xingjiantao/cursor-rules-for-pytorch-deeplearning-beginner/pytorch.svg)](https://agentmods.dev/rules/xingjiantao/cursor-rules-for-pytorch-deeplearning-beginner/pytorch)
Your own site
<a href="https://agentmods.dev/rules/xingjiantao/cursor-rules-for-pytorch-deeplearning-beginner/pytorch"><img src="https://agentmods.dev/badge/rules/xingjiantao/cursor-rules-for-pytorch-deeplearning-beginner/pytorch.svg" alt="Measured on agentmods" height="20"></a>
Per session 4,719 This file is loaded in full into every session.
When invoked 4,719 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 $0.04719 $0.04719
Opus 5 $0.02360 $0.02360
Sonnet 5 $0.00944 $0.00944
Haiku 4.5 $0.00472 $0.00472

Measured 5d ago against content hash 2b520e1ebecb, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

pytorch 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 5d 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.

Original/pytorch.mdc · 382 lines

How it starts

The opening of the file, as written. The whole thing — 382 lines — stays where its author put it; the contents beside it link to each section on GitHub.

PyTorch Best Practices and Coding Standards

This document provides comprehensive guidelines for developing PyTorch projects, encompassing code organization, performance optimization, security, testing methodologies, and common pitfalls. Adhering to these best practices will result in more readable, maintainable, and efficient PyTorch code.

Library Information:

  • Name: PyTorch
  • Category: ai_ml
  • Subcategory: machine_learning

1. Code Organization and Structure

1.1 Directory Structure Best Practices

A well-organized directory structure enhances code maintainability and collaboration. Here's a recommended structure for PyTorch projects:

project_root/ ├── data/ │ ├── raw/ │ ├── processed/ │ └── ... ├── models/ │ ├── layers.py │ ├── networks.py │ ├── losses.py │ ├── ops.py │ └── model_name.py ├── src/ │ ├── data/ │ │ ├── datasets.py │ │ ├── dataloaders.py │ │ └── transforms.py │ ├── models/ │ │ └── ... (model-related code) │ ├── utils/ │ │ └── ... (utility functions) │ └── visualization/ │ └── ... ├── notebooks/ │ └── ... (Jupyter notebooks for experimentation) ├── tests/ │ ├── unit/ │ ├── integration/ │ └── ... ├── scripts/ │ └── train.py │ └── eval.py ├── configs/ │ └── ... (Configuration files, e.g., YAML) ├── README.md ├── requirements.txt ├── .gitignore └── ...

  • data/: Stores raw and processed datasets.
  • models/: Contains PyTorch model definitions, layers, and custom loss functions. Separate network architectures, individual layers/blocks, and operations into different files.
  • src/: Holds the main source code, including data loading, model definitions, utility functions, and visualization tools. It's common to split the src/ folder further based on responsibilities.
  • notebooks/: Jupyter notebooks for experimentation and exploration. Use notebooks for initial exploration and prototyping but transition finalized code to Python scripts.
  • tests/: Unit, integration, and end-to-end tests.
  • scripts/: Training, evaluation, and deployment scripts. The main training script should import model definitions.
  • configs/: Configuration files for hyperparameter settings and other parameters.

Read the full file on GitHub · 382 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. 5d ago First seen · 382 lines · 4,719 tokens per session scan A 2b520e1ebecb

Subscribe to this mod's changes

pytorch is a cursor rule published in the GitHub repository XingjianTao/Cursor-Rules-for-PyTorch-DeepLearning-Beginner (3 stars, last pushed 1y ago), licensed MIT. It adds 4,719 tokens to every session, about $0.0236 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 2026-08-31.