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 ericrisco/rsc-harness --skill huggingfacegit clone --depth 1 https://github.com/ericrisco/rsc-harnessWrote 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/ericrisco/rsc-harness/huggingface)<a href="https://agentmods.dev/skills/ericrisco/rsc-harness/huggingface"><img src="https://agentmods.dev/badge/skills/ericrisco/rsc-harness/huggingface/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/ericrisco/rsc-harness/huggingface"><img src="https://agentmods.dev/badge/skills/ericrisco/rsc-harness/huggingface.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00131 | $0.02705 |
| Opus 5.5 | $0.00052 | $0.01082 |
| Sonnet 5.5 | $0.00026 | $0.00541 |
| Haiku 4.5 | $0.00013 | $0.00270 |
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 1mo 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 — 192 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Hugging Face: Hub, routed/hosted inference, and transformers
Hugging Face is three surfaces, and you should always know which one you are on:
- The Hub — versioned git repos for models, datasets, and Spaces. You search it, you
hf download/hf upload, you read and write model cards. - Inference — three ways to actually run a model: the Inference Providers router
(serverless, you own nothing), a dedicated Inference Endpoint (you own a deployment
that autoscales), or local
transformers(you own the machine). - The catalog — 1M+ open models you choose from by task, license, and size.
The whole skill is choosing the right surface for the job and proving it works: a 200 router
response, a live endpoint URL, a pushed repo commit. If the model is open and the workflow
lives on huggingface.co, you are in the right place. Operating the GPU box yourself is
../ollama/SKILL.md (your machine) or ../runpod/SKILL.md
(a rented box); training weights is ../finetuning/SKILL.md.
Decision: how should I run this model?
Pick the row before you write a line of code. The cheapest mistake is standing up infra you did not need.
| Situation | Use | Why |
|---|---|---|
| Try a model now, low/dev volume, own no infra | Inference Providers router (InferenceClient) |
Fastest path; monthly credits cover dev. |
| CPU task: embeddings, text-ranking, text-classification, small BERT/GPT-2 | provider="hf-inference" |
That is exactly its remaining niche as of July 2025. |
| Big LLM (8B, 70B, 405B) through HF | router with a partner provider (Together/Fireworks/Cerebras/DeepInfra…) | hf-inference does not serve big LLMs — it will 404 or stall. |
| Steady prod traffic, need fixed latency/SLA | dedicated Inference Endpoint + scale-to-zero | Predictable, autoscaling, billed per minute. |
| Interactive demo or shareable GPU app | Space (Gradio + ZeroGPU) | Free-ish, public URL, GPU only while a call runs. |
| One-off GPU job (eval, batch convert) | hf jobs run |
No standing infra; PRO feature. |
| Offline, data-private, or already on a GPU box | local transformers pipeline() |
No network, no per-call cost. |
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.
- 1mo ago First seen · 192 lines · 131 tokens per session scan A ffd0fa8d6cfc
huggingface is a skill published in the GitHub repository ericrisco/rsc-harness (314 stars, last pushed today), licensed MIT. It adds 131 tokens to every session and 2,705 once invoked, about $0.0005 per session on Opus 5.5. 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
huggingface-transformers
Use when running or fine-tuning Hugging Face Transformers models in Python — pipeline() inference for text classification and generation, loading weights with AutoModel/AutoTokenizer, devicemap and dtype memory management, tokenizer usage, Trainer fine-tuning, and BGE embeddings for Chinese RAG. Covers transformers…
huggingface-transformers
Use Hugging Face Transformers pipelines, tokenizers, and AutoModel interfaces for inference and fine-tuning workflows.
data-pipeline
ETL/ELT pipeline design. Trigger when the user wants to create data flows, transformations, or orchestration.
huggingface-spaces
Build, deploy, and maintain applications on Hugging Face Spaces — Gradio / Docker / Static SDKs, ZeroGPU and dedicated hardware, model loading, debugging, buckets, inference providers, community grants. Use whenever the user asks to create or host an app on Hugging Face, port code onto ZeroGPU, fix a Space that won't…
minimax-m3-multimodal-input
How to use MiniMax M3's native multimodal input (image, video) for grounded decisions in coding work. Covers reading attached images/frames, treating them as ground truth for visual claims, screenshot diffing, design parity from mockups, and routing visual evidence through reports and PRs. Load when the user attaches…
attach-receipts
Attaches sourcedoc/extractionrunid/schemaversion receipts to every edge at write time, and refuses to write any edge missing one of the three.