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 G1Joshi/Agent-Skills --skill huggingfacegit clone --depth 1 https://github.com/G1Joshi/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/g1joshi/agent-skills/huggingface)<a href="https://agentmods.dev/skills/g1joshi/agent-skills/huggingface"><img src="https://agentmods.dev/badge/skills/g1joshi/agent-skills/huggingface.svg" alt="Measured on agentmods" 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 | $0.00018 | $0.00308 |
| Opus 5 | $0.00009 | $0.00154 |
| Sonnet 5 | $0.00004 | $0.00062 |
| Haiku 4.5 | $0.00002 | $0.00031 |
Grade A, and why
huggingface 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.
What it actually says
Hugging Face
Hugging Face is the GitHub of AI. It hosts 1M+ models. 2025 sees massive growth in Multimodal models and Robotics (LeRobot).
When to Use
- Model Discovery: Finding the SOTA open-source model for any task.
- Inference:
transformerslibrary is the standard way to run models in Python. - Datasets: Accessing standard datasets (
load_dataset('squad')).
Core Concepts
Transformers Library
The API to download and run models. pipeline('sentiment-analysis').
Hugging Face Hub (Hugging Face CLI)
Versioning, git-based storage for large model weights (git lfs).
Spaces
Hosting simple Gradio/Streamlit apps for model demos.
Best Practices (2025)
Do:
- Use
bitsandbytes: Load 70B models in 4-bit precision easily. - Use
accelerate: For multi-GPU training/inference distributed across devices. - Push to Hub: Share your fine-tunes.
Don't:
- Don't hardcode paths: Use
from_pretrained("repo/id")to auto-cache models.
References
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.
- 8d ago First seen · 45 lines · 18 tokens per session scan A a4dd9d2d1a6a
huggingface is a skill published in the GitHub repository G1Joshi/Agent-Skills (12 stars, last pushed 6mo ago), licensed MIT. It adds 18 tokens to every session and 308 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 2026-08-30.
Other skills, from other repositories
9router-stt
Speech-to-text via 9Router /v1/audio/transcriptions using OpenAI Whisper / Groq / Gemini / Deepgram / AssemblyAI / NVIDIA / HuggingFace models. Use when the user wants to transcribe audio, convert speech to text, or get subtitles from audio files.
9router
Entry point for 9Router — local/remote AI gateway with OpenAI-compatible REST for chat, image, TTS, embeddings, web search, web fetch. Use when the user mentions 9Router, NINEROUTERURL, or wants AI without writing provider boilerplate. This skill covers setup + indexes capability skills; fetch the relevant capability…
9router-chat
Chat / code generation via 9Router using OpenAI /v1/chat/completions or Anthropic /v1/messages format with streaming + auto-fallback combos. Use when the user wants to ask an LLM, generate code, summarize text, or run prompts through 9Router.
9router-embeddings
Generate vector embeddings via 9Router /v1/embeddings using OpenAI / Gemini / Mistral / Voyage / Nvidia / GitHub embedding models for RAG, semantic search, similarity. Use when the user wants embeddings, vectors, RAG, semantic search, or to embed text.
fixing-prompt
Prompt: Prompt Refinement and Optimization.
feature-engineering
When building training datasets, designing feature pipelines, or debugging training-serving skew.