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-spacesgit 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-spaces)<a href="https://agentmods.dev/skills/practicalswan/agent-skills/huggingface-spaces"><img src="https://agentmods.dev/badge/skills/practicalswan/agent-skills/huggingface-spaces/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-spaces"><img src="https://agentmods.dev/badge/skills/practicalswan/agent-skills/huggingface-spaces.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 | $0.00106 | $0.05074 |
| Opus 5 | $0.00053 | $0.02537 |
| Sonnet 5 | $0.00021 | $0.01015 |
| Haiku 4.5 | $0.00011 | $0.00507 |
Grade B, and why
huggingface-spaces scanned grade B with 1 finding 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 3d 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.
Strips warnings and disclaimersmediumAnti-refusal
Omitting safety caveats hides risk from the user and is a common jailbreak preamble.
**B. Logs clean post-boot?** Read the run log to confirm startup finished without warnings or silent fallbacks: How it starts
The opening of the file, as written. The whole thing — 301 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Hugging Face Spaces
Hugging Face Spaces host machine-learning applications. There are 1M+ today; each Space is a git repo. This skill covers creating, building, debugging, and maintaining them.
0. Getting ready
Before anything else:
- Check whether the
hfCLI is installed (Get-Command hfon Windows orcommand -v hfon POSIX). If it is absent, use the official Python SDK or browser workflow; do not install a runtime implicitly. - Check the user is logged in:
hf auth whoami. If not, ask the user to runhf auth loginlocally and complete its browser/OAuth flow, or configure an approved secret manager. Never request or accept a token value in chat or pass a literal token in a command argument. - Note
whoami'scanPayandisProflags — they gate hardware choices below. A free (isPro=False) account can only host Static Spaces and up to 2 ZeroGPU Spaces.
The optional hf-cli skill teaches every hf command. Load it only when the
hf runtime is already installed and the user explicitly authorizes adding
that skill; this catalog omits it because the laptop has no hf command.
1. What a Space is
A Space is a git repo with three possible SDKs:
- Gradio — most Spaces. Python, fast iteration, supports ZeroGPU.
- Docker — arbitrary container. Use when you need a non-Python stack or a pre-built template (Streamlit, Argilla, Shiny, etc. — full list at https://huggingface.co/docs/hub/spaces-sdks-docker). Does not support ZeroGPU.
- Static — plain HTML, or a React/Svelte/Vue project built at deploy time. Use for in-browser ML (transformers.js / WebGPU / WebAssembly / onnxruntime-web), project pages, interactive reports, or Spaces that orchestrate other Spaces. No hardware needed.
Hardware tiers
Static Spaces are free for everyone and need no hardware. Gradio and Docker Spaces run on compute and require a paid plan to create — PRO for personal accounts, Team or Enterprise for organizations — with one exception: free personal accounts in good standing (verified email, account older than 30 days) can host up to 2 ZeroGPU Spaces.
What ships with it
16 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.
- CHANGELOG.md 3.2 KB
- LICENSE.txt 11 KB
- README.md 412 B
- references/3d-cuda-extensions.md 9.1 KB
- references/3d-generation.md 8.6 KB
- references/3d-gsplat.md 7.2 KB
- references/3d-models.md 20 KB
- references/3d-outputs.md 9.3 KB
- references/buckets.md 4.3 KB
- references/debugging.md 11 KB
- references/gradio.md 9.2 KB
- references/grants.md 3.2 KB
- references/inference-providers.md 3.8 KB
- references/known-errors.md 13 KB
- references/requirements.md 11 KB
- references/zerogpu.md 21 KB
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.
- 3d ago Changed 63f7690a7993
- 4d ago Changed 7271fe4984a9
- 7d ago First seen · 301 lines · 106 tokens per session scan B 9eacdb9403dc
huggingface-spaces is a skill published in the GitHub repository PracticalSwan/agent-skills (14 stars, last pushed 3d ago), licensed MIT. It adds 106 tokens to every session and 5,074 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it B with 1 finding (strips warnings and disclaimers). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
huggingface
Use when running open models or working on the Hugging Face platform — the Inference Providers router or InferenceClient, Hub repos via the hf CLI, a dedicated Inference Endpoint with scale-to-zero, a Gradio Space with ZeroGPU, picking an open model by task/license/size, or loading one locally with transformers. NOT…
hugging-face-model-trainer
This skill should be used when users want to train or fine-tune language models using TRL (Transformer Reinforcement Learning) on Hugging Face Jobs infrastructure. Covers SFT, DPO, GRPO and reward modeling training methods, plus GGUF conversion for local deployment. Includes guidance on the TRL Jobs package, UV…
tensorrt-llm
High-throughput LLM inference on NVIDIA GPUs.
google-cloud-solution-guided-gke-ai-migration
Guides the migration of existing AI workloads (Cloud Run, Gemini API, Gemini Enterprise Agent Platform) to self-hosted GKE inference using gcloud and kubectl. Use when the user has an existing AI inference workload (on Cloud Run, the Gemini API, Gemini Enterprise Agent Platform, or a custom VM) and wants to move it to…
agent-platform-tuning
Agent Platform Model Tuning. Use when you need to fine-tune open models or Gemini models using Agent Platform infrastructure. Don't use for model training outside Agent Platform, model deployment to endpoints (use agent-platform-deploy), or managing serving endpoints (use agent-platform-endpoint-management).
gke-inference
Deploys and optimizes AI/ML inference workloads on GKE, using GPUs, TPUs, and model servers. Use when deploying GKE inference servers, configuring GKE GPU resources for inference, or deploying LLMs on GKE. Don't use for generic batch jobs or HPC task queues (use gke-batch-hpc instead).