refactor:pytorch

refactor:pytorch is a skill for Claude Code from SnakeO/claude-debug-and-refactor-skills-plugin. It costs 104 tokens per session (5,637 once invoked), scanned A, original, no licence file.

A code-refactoring guide for PyTorch, a Python library used to build and train machine-learning models. It focuses on making code easier to maintain and applies stated PyTorch 2.x patterns, including compilation and mixed-precision training.

In plain words
What is it for?
Use it to restructure PyTorch projects, split code into clearer components, reduce duplication, and apply relevant PyTorch 2.x practices.
Why use it?
It helps clean up repeated code, oversized functions, deep nesting, and unclear responsibilities without changing the work into a different framework.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the debug-and-refactor plugin — 45 skills shipped together

Good fit Use it to restructure PyTorch projects, split code into clearer components, reduce duplication, and apply relevant PyTorch 2.x practices.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/snakeo/claude-debug-and-refactor-skills-plugin/refactor-pytorch
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.

Any agent
npx skills add SnakeO/claude-debug-and-refactor-skills-plugin --skill refactor-pytorch
Clone the repo
git clone --depth 1 https://github.com/SnakeO/claude-debug-and-refactor-skills-plugin

Made for: Claude Code.

Or install debug-and-refactor, the plugin that ships this one along with the rest of its 45 skills.

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 refactor:pytorch

README.md
[![agentmods](https://agentmods.dev/badge/skills/snakeo/claude-debug-and-refactor-skills-plugin/refactor-pytorch.svg)](https://agentmods.dev/skills/snakeo/claude-debug-and-refactor-skills-plugin/refactor-pytorch)
Your own site
<a href="https://agentmods.dev/skills/snakeo/claude-debug-and-refactor-skills-plugin/refactor-pytorch"><img src="https://agentmods.dev/badge/skills/snakeo/claude-debug-and-refactor-skills-plugin/refactor-pytorch.svg" alt="Measured on agentmods" height="20"></a>
Per session 104 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 5,637 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin unknown 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 5.1 $0.00104 $0.05637
Opus 5 $0.00052 $0.02818
Sonnet 5 $0.00021 $0.01127
Haiku 4.5 $0.00010 $0.00564

Measured 8d ago against content hash fcebb14b5a7e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

refactor: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 8d 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.

plugins/debug-and-refactor/skills/refactor-pytorch/SKILL.md · 824 lines

The source is not reproduced here

No licence file

A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.

Read it on GitHub

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. 8d ago First seen · 824 lines · 104 tokens per session scan A fcebb14b5a7e

Subscribe to this mod's changes

refactor:pytorch is a skill published in the GitHub repository SnakeO/claude-debug-and-refactor-skills-plugin (9 stars, last pushed 7mo ago), with no licence file. It adds 104 tokens to every session and 5,637 once invoked, about $0.0005 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.

Related

Other skills, from other repositories

huggingface-llm-trainer

Train or fine-tune language models with TRL or Unsloth on Hugging Face Jobs, including SFT, DPO, GRPO, reward models, and GGUF conversion. Use for cloud LLM training; use huggingface-vision-trainer for vision tasks.

waybarrios/opencode-power-pack · 65 tokens

huggingface-vision-trainer

Train object-detection, image-classification, or SAM segmentation models on Hugging Face Jobs. Use for vision fine-tuning and evaluation; use huggingface-llm-trainer for language models.

waybarrios/opencode-power-pack · 48 tokens

huggingface-best

Find and compare recommended Hugging Face models for a task using benchmarks, model size, and device constraints. Use for model selection questions; use huggingface-local-models for GGUF setup and hf-cli for Hub operations.

waybarrios/opencode-power-pack · 49 tokens

craft-goal

Compile or lint a persistent Mayor-style goal prompt that ratchets a bead graph through bounded RPI experiments toward one larger outcome. Triggers: "craft a goal prompt", "mayor goal", "goal-runner prompt", "lint this goal", "is this goal safe". (Shaping one experiment's intent routes to plan.).

boshu2/agentops · 71 tokens

submit-github-pr

Use when publishing an existing TensorRT-Model-Connect change as a GitHub pull request. Verifies authenticated repository access, branch and diff scope, validation evidence, commit identity, reviewer-facing text, exact pushed head, and the created draft PR without merging it.

NVIDIA/TensorRT-Model-Connect · 58 tokens

council-review

Multi-model validation council — auto-validate plans, architecture changes, and PRs via validate-plan/review before executing.

alinaqi/maggy · 28 tokens