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 PracticalSwan/agent-skills --skill huggingface-zerogpugit clone --depth 1 https://github.com/PracticalSwan/agent-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/practicalswan/agent-skills/huggingface-zerogpu)<a href="https://agentmods.dev/skills/practicalswan/agent-skills/huggingface-zerogpu"><img src="https://agentmods.dev/badge/skills/practicalswan/agent-skills/huggingface-zerogpu/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/practicalswan/agent-skills/huggingface-zerogpu"><img src="https://agentmods.dev/badge/skills/practicalswan/agent-skills/huggingface-zerogpu.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 | $0.00205 | $0.04864 |
| Opus 5 | $0.00102 | $0.02432 |
| Sonnet 5 | $0.00041 | $0.00973 |
| Haiku 4.5 | $0.00020 | $0.00486 |
Grade A, and why
huggingface-zerogpu 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 yesterday.
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.
This is a copy
88% identical to huggingface-zerogpu — 55 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 341 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Hugging Face ZeroGPU
Rules and patterns for ML demos on Hugging Face Spaces with ZeroGPU hardware. Covers @spaces.GPU, duration and quota tuning, process isolation, the CUDA availability model, concurrency safety, and CUDA build constraints.
Scope
This skill is for Gradio SDK Spaces using ZeroGPU hardware. Docker and Static Spaces cannot schedule onto ZeroGPU, and Streamlit apps now run as Docker Spaces — so this skill applies only to Gradio. For general Gradio coding (components, layouts, event listeners), see the huggingface-gradio skill in this repo. The authoritative ZeroGPU docs live at https://huggingface.co/docs/hub/spaces-zerogpu — refer to them for the current backing GPU, runtime version lists, and tier thresholds, all of which change over time.
Reference Files
| Reference | When to read |
|---|---|
references/concurrency.md |
Always read alongside SKILL.md when writing ZeroGPU code — handlers run in parallel by default |
references/how-zerogpu-works.md |
When reasoning about cold-starts, worker reuse, why module-scope warmup does not carry to requests, or why returning CUDA tensors hangs |
references/how-quota-works.md |
When choosing duration values, debugging illegal duration vs quota exceeded errors, or explaining why default 60s blocks short tasks |
references/cuda-and-deps.md |
When installing CUDA-dependent packages (e.g. flash-attn), pinning torch side-cars, or reading wheel filename tags |
Hardware
ZeroGPU exposes two GPU sizes that map to a fraction of the backing card:
size |
Slice of backing GPU | Quota cost |
|---|---|---|
large (default) |
Half | 1x |
xlarge |
Full | 2x |
Default large gives half a physical GPU, so memory bandwidth and compute are significantly lower than the full card's specs. Use xlarge only when the workload genuinely needs the extra memory or compute.
Backing GPU changes without notice. ZeroGPU has already migrated across GPU generations several times; older write-ups may name A100 or H200, but those are outdated. For the current backing GPU and exact per-size VRAM, always check the ZeroGPU docs before sizing workloads.
What ships with it
6 files 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.
- yesterday Changed ae2411d301f7
- 3d ago Changed a28085f50439
- 5d ago First seen · 341 lines · 205 tokens per session scan A 0246f5f4dba7
huggingface-zerogpu is a skill published in the GitHub repository PracticalSwan/agent-skills (13 stars, last pushed yesterday), licensed MIT. It adds 205 tokens to every session and 4,864 once invoked, about $0.0010 per session on Opus 5. A static security scan graded it A with 0 findings. It is 88% identical to huggingface-zerogpu, differing in 55 lines, and is treated as a copy.
Other skills, from other repositories
quantizing-models-bitsandbytes
Quantizes LLMs to 8-bit or 4-bit for 50-75% memory reduction with minimal accuracy loss. Use when GPU memory is limited, need to fit larger models, or want faster inference. Supports INT8, NF4, FP4 formats, QLoRA training, and 8-bit optimizers. Works with HuggingFace Transformers.
llama-factory
Expert guidance for fine-tuning LLMs with LLaMA-Factory - WebUI no-code, 100+ models, 2/3/4/5/6/8-bit QLoRA, multimodal support.
mlflow
Track ML experiments, manage model registry with versioning, deploy models to production, and reproduce experiments with MLflow - framework-agnostic ML lifecycle platform.
transformers
This skill should be used when working with pre-trained transformer models for natural language processing, computer vision, audio, or multimodal tasks. Use for text generation, classification, question answering, translation, summarization, image classification, object detection, speech recognition, and fine-tuning…
huggingface-hub
HuggingFace hf CLI: search/download/upload models, datasets.
submit-github-bug-issue
Use when converting QA findings, black-box failures, red-team reports, regression evidence, or local bug notes into GitHub Issues for NVIDIA/TensorRT-Model-Connect. Standardizes checking issue templates, checking labels, de-duplicating existing issues, drafting a bug report, creating the issue on GitHub, applying the…