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 skills add AmariahAK/atlarix-skills --skill acr-linux-nvidia-cuda-python-cursorrules-prompt-filegit clone --depth 1 https://github.com/AmariahAK/atlarix-skillsWrote 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/skills/amariahak/atlarix-skills/acr-linux-nvidia-cuda-python-cursorrules-prompt-file)<a href="https://agentmods.dev/skills/amariahak/atlarix-skills/acr-linux-nvidia-cuda-python-cursorrules-prompt-file"><img src="https://agentmods.dev/badge/skills/amariahak/atlarix-skills/acr-linux-nvidia-cuda-python-cursorrules-prompt-file/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/skills/amariahak/atlarix-skills/acr-linux-nvidia-cuda-python-cursorrules-prompt-file"><img src="https://agentmods.dev/badge/skills/amariahak/atlarix-skills/acr-linux-nvidia-cuda-python-cursorrules-prompt-file.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 | $0.00011 | $0.00567 |
| Opus 5 | $0.00005 | $0.00283 |
| Sonnet 5 | $0.00002 | $0.00113 |
| Haiku 4.5 | $0.00001 | $0.00057 |
Grade A, and why
Cursor rules for Linux development with NVIDIA CUDA and Python integration 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 9d 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 — 44 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cursor rules for Linux development with NVIDIA CUDA and Python integration
When to use this skill
Cursor rules for Linux development with NVIDIA CUDA and Python integration.
Source
Synced from https://github.com/PatrickJS/awesome-cursorrules/tree/main/rules/linux-nvidia-cuda-python-cursorrules-prompt-file.mdc.
- Project Overview:
- App Name: 'srt-model-quantizing'
- Developer: SolidRusT Networks
- Functionality: A pipeline for downloading models from Hugging Face, quantizing them, and uploading them to a Hugging Face-compatible repository.
- Design Philosophy: Focused on simplicity—users should be able to clone the repository, install dependencies, and run the app using Python or Bash with minimal effort.
- Hardware Compatibility: Supports both Nvidia CUDA and AMD ROCm GPUs, with potential adjustments needed based on specific hardware and drivers.
- Platform: Intended to run on Linux servers only.
- Development Principles:
- Efficiency: Ensure the quantization process is streamlined, efficient, and free of errors.
- Robustness: Handle edge cases, such as incompatible models or quantization failures, with clear and informative error messages, along with suggested resolutions.
- Documentation: Keep all documentation up to date, including the README.md and any necessary instructions or examples.
- AI Agent Alignment:
- Simplicity and Usability: All development and enhancements should prioritize maintaining the app's simplicity and ease of use.
- Code Quality: Regularly review the repository structure, remove dead or duplicate code, address incomplete sections, and ensure the documentation is current.
- Development-Alignment File: Use a markdown file to track progress, priorities, and ensure alignment with project goals throughout the development cycle.
- Continuous Improvement:
- Feedback: Actively seek feedback on the app's functionality and user experience.
- Enhancements: Suggest improvements that could make the app more efficient or user-friendly, ensuring any changes maintain the app's core principles.
- Documentation of Changes: Clearly document any enhancements, bug fixes, or changes made during development to ensure transparency and maintainability.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 9d ago First seen · 44 lines · 11 tokens per session scan A 127e1b194e23
Cursor rules for Linux development with NVIDIA CUDA and Python integration is a skill published in the GitHub repository AmariahAK/atlarix-skills (2 stars, last pushed 5d ago), licensed Apache-2.0. It adds 11 tokens to every session and 567 once invoked, about $0.0001 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 2026-09-03.
Other skills, from other repositories
cursor-pytorch
Cursor IDE rules for pytorch.
pytorch-patterns
PyTorch deep learning patterns and best practices for building robust, efficient, and reproducible training pipelines, model architectures, and data loading.
synthetic-data-finetuning-expert
Expert guide for synthetic dataset generation, LLM-as-a-judge filtering, QLoRA fine-tuning (Unsloth), DPO alignment, and GGUF/Ollama export for local SLMs / Panduan ahli generasi data sintetis, fine-tuning QLoRA, DPO, dan ekspor GGUF/Ollama.
anthropic-python
Anthropic Python SDK for Claude API integration. Covers messages API, streaming, tool use, vision, error handling, and best practices. Use when building Python applications that call the Claude API. USE WHEN: user mentions "anthropic", "claude api", "anthropic sdk", "anthropic.Anthropic()", "client.messages.create"…
pydantic-ai-model-integration
Configure LLM providers, use fallback models, handle streaming, and manage model settings in PydanticAI. Use when selecting models, implementing resilience, or optimizing API calls.
pytorch-training
PyTorch model-building conventions and a neural-net training debug checklist. Use this skill whenever writing or reviewing PyTorch code that defines a model (nn.Linear, nn.Conv2d, BatchNorm) or trains one (training loop, optimizer, LR schedule), and ESPECIALLY when debugging training problems — loss not converging…