StepCOVNet: Skill for Claude Code

.cursor/skills/wsl-gpu-stepcovnet/SKILL.md

wsl-gpu-stepcovnet is a skill for Claude Code, Cursor from cpuguy96/StepCOVNet. It costs 58 tokens per session (1,417 once invoked), scanned A, original, Apache-2.0.

Windows development instructions for running StepCOVNet’s TensorFlow CUDA work through WSL, the Linux environment available inside Windows. CPU work stays in the Windows virtual environment, while GPU training and MERT feature extraction run in WSL.

In plain words
What is it for?
Use them when training, overfitting, or extracting MERT features with CUDA on Windows. They explain the dispatch scripts, environment overrides, repository path handling, and one-job-at-a-time rule.
Why use it?
They prevent GPU jobs from running in the wrong environment and avoid overlapping jobs on the single shared WSL GPU.

Skill for Claude CodeCursor

Written for Claude Code and Cursor: disable-model-invocation in frontmatter, but also installed under .cursor/.

This is cpuguy96/StepCOVNet's own configuration. It tells Claude Code and Cursor how to work on StepCOVNet itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything StepCOVNet configures →

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is bash scripts/wsl_ensure_env.sh.

Reuse

Borrowing it

Nothing to install: this file belongs to cpuguy96/StepCOVNet. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/cpuguy96/StepCOVNet/master/.cursor/skills/wsl-gpu-stepcovnet/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/cpuguy96/StepCOVNet

Made for: Claude Code, Cursor.

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 wsl-gpu-stepcovnet

README.md
[![agentmods](https://agentmods.dev/badge/skills/cpuguy96/stepcovnet/wsl-gpu-stepcovnet/github.svg)](https://agentmods.dev/skills/cpuguy96/stepcovnet/wsl-gpu-stepcovnet)
Your own site
<a href="https://agentmods.dev/skills/cpuguy96/stepcovnet/wsl-gpu-stepcovnet"><img src="https://agentmods.dev/badge/skills/cpuguy96/stepcovnet/wsl-gpu-stepcovnet/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.

agentmods 80×15 button for wsl-gpu-stepcovnet

Your own site · 80×15
<a href="https://agentmods.dev/skills/cpuguy96/stepcovnet/wsl-gpu-stepcovnet"><img src="https://agentmods.dev/badge/skills/cpuguy96/stepcovnet/wsl-gpu-stepcovnet.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 58 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,417 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 5.1 $0.00058 $0.01417
Opus 5 $0.00029 $0.00709
Sonnet 5 $0.00012 $0.00283
Haiku 4.5 $0.00006 $0.00142

Measured 10d ago against content hash de5f1ba8cb10, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

wsl-gpu-stepcovnet 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 10d 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.

.cursor/skills/wsl-gpu-stepcovnet/SKILL.md · 96 lines

How it starts

The opening of the file, as written. The whole thing — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.

WSL GPU (StepCOVNet)

Windows development model

On Windows, CPU work stays in the clone's Windows venv; CUDA work runs in WSL. The repo clone can live on any drive or folder — dispatch code derives WSL paths from the current checkout, not from a fixed username or /mnt/c/Users/... string.

Setting Default Override
WSL venv root $HOME/stepcovnet-venv-wsl WSL_VENV
WSL Python $WSL_VENV/bin/python STEPCOVNET_WSL_PYTHON
Repo root cwd / script location

Shell helpers share these via scripts/wsl_common.sh.

Rule

On native Windows, never run CUDA/GPU training in the Windows venv. From repo root (project venv activated):

python scripts/<script>.py <args>

when the script calls wsl_gpu.maybe_dispatch_for_training (or MERT --device=cuda dispatch).

Opt out: STEPCOVNET_NO_WSL=1.

GPU scheduling (one job at a time)

The WSL GPU is single-tenant for the agent:

Rule Detail
One training job Do not start a second WSL GPU training run while one is already active (train, overfit, MERT extract with --device=cuda).
No train + infer overlap Do not run GPU training and GPU inference (debug_*, --ar_decode, eval_dense_*, model.predict) in separate processes at the same time.
Before launching assert_wsl_gpu_free_for_training() checks nvidia-smi and logs/gpu_wsl.lock (stepcovnet.wsl_gpu_lock). Windows dispatch acquires the lock before wsl; a second parallel launch fails on O_EXCL. Override: STEPCOVNET_FORCE_GPU=1.
Manual check python -c "from stepcovnet import wsl_gpu; wsl_gpu.assert_wsl_gpu_free_for_training()"
After training Offline decode/eval on GPU is fine sequentially once training has exited.

CPU scripts (pytest, lint, config edits) may run while a GPU job is active — they do not use the WSL CUDA device.

Manual WSL (debugging or already inside WSL)

Read the full file on GitHub · 96 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. 10d ago First seen · 96 lines · 58 tokens per session scan A de5f1ba8cb10

Subscribe to this mod's changes

wsl-gpu-stepcovnet is a skill published in the GitHub repository cpuguy96/StepCOVNet (22 stars, last pushed 16d ago), licensed Apache-2.0. It adds 58 tokens to every session and 1,417 once invoked, about $0.0003 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 2026-08-30.

Related

Other skills, from other repositories

physicsnemo-discover

Official NVIDIA-authored guidance for navigating PhysicsNeMo — pick the model, datapipe, or example for a SciML/AI4Science task (surrogates, forecasting, downscaling, physics-informed, inverse, generative). Points at existing files via live repo search; never writes code. Do NOT use for installation or environment…

NVIDIA/physicsnemo · 124 tokens

lepton-cli

Operate NVIDIA DGX Cloud Lepton through the globally installed lep CLI. Use when the user asks to inspect or manage Lepton workspaces, endpoints/deployments, dev pods, batch jobs, fine-tuning jobs, Ray clusters, Slurm clusters, Dynamo endpoints, storage, secrets, nodes, ingress, templates, logs, authentication, or…

leptonai/leptonai · 122 tokens

depth-estimation

Real-time depth map privacy transforms using Depth Anything v2 (CoreML + PyTorch).

SharpAI/DeepCamera · 22 tokens

HomeSafe-Bench

VLM indoor safety hazard detection benchmark inspired by HomeSafeBench (arXiv 2509.23690).

SharpAI/DeepCamera · 28 tokens

ml-for-aec

Computer vision for buildings, image-to-floorplan, generative ML models, performance prediction, structural analysis ML, energy prediction, natural language to design, and point cloud ML for AEC computational design.

Abhinavbwj/Claude-skills-for-Computational-Designers · 39 tokens

ml-architecture-diagram

Create accurate, publication-ready, editable machine-learning and deep-learning architecture diagrams from model code, configuration files, model summaries, graph exports, or written specifications. Use for neural-network figures, architecture schematics, model block diagrams, training/inference diagrams, paper…

Ztsdut/ml-architecture-diagram-skill · 95 tokens