Huggingface

What it does

When your agent uses it

• Running open models
• Working on the Hugging Face platform — the Inference Providers router
• InferenceClient
• Hub repos via the hf CLI

Example prompts

• “/huggingface”

Requirements

• Python 3
• A Bash shell
• Docker

Workflow steps

3 steps, taken from the first numbered list in SKILL.md.

1. 1The Hub — versioned git repos for models, datasets, and Spaces. You search it, you
2. 2Inference — three ways to actually run a model: the Inference Providers router
3. 3The catalog — 1M+ open models you choose from by task, license, and size.

What it can do on your machine

Read from SKILL.md and the folder at commit 92fde8f. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  Ships 1 file in scripts/ (Shell), which the agent can run.

  Shell commands in SKILL.md call:

  • hf
  • pip
  • huggingface-cli

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  Hosts in commands or code, which the agent is likely to contact:

  • router.huggingface.co

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names these keys or tokens, usually read from environment variables:

  • HF_TOKEN

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Huggingface loads about 2.6k tokens when it runs, and up to ~5k if it reads all its reference files. Until then it costs about 137 tokens; SKILL.md has 1,014 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~137

When it runs · the whole SKILL.md, loaded when a task matches

~2.6k

With references · SKILL.md plus every file in references/, read only if the agent opens them

~5k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

The full file from ericrisco/rsc-harness at commit 92fde8f, republished under its MIT licence (© ericrisco). 1,014 words, ~2,560 tokens.

name

huggingface

description

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 serving locally on your own machine (that is `ollama`), NOT renting your own GPU box (that is `runpod`), NOT hosted creative image APIs (that is `replicate-images`), NOT fine-tuning with trl/peft (that is `finetuning`).

tags

huggingface, inference-providers, transformers, model-hub, inference-endpoints, spaces, ai-infra

recommends

ollama, runpod, modal, replicate, together-fireworks, fal, rag, embeddings-search, prompt-engineering, llm-pipeline, ai-media

origin

risco

pip install "huggingface_hub[inference]"   # 1.17.0; needs Python >=3.10
pip install transformers                    # 5.x line, PyTorch-first, optional/local
hf auth login                               # stores a token; or export HF_TOKEN=...

import os
from huggingface_hub import InferenceClient
client = InferenceClient(api_key=os.environ["HF_TOKEN"])   # never api_key="hf_xxx"

# Native client — task methods, NOT the removed .post()
from huggingface_hub import InferenceClient
client = InferenceClient(api_key=os.environ["HF_TOKEN"])
out = client.chat.completions.create(
    model="meta-llama/Llama-3.1-8B-Instruct",
    messages=[{"role": "user", "content": "One sentence on diffusion models."}],
    provider="together",          # name a partner; or omit for auto-routing
)
print(out.choices[0].message.content)

# OpenAI-compatible — same router, drop-in for existing OpenAI code
from openai import OpenAI
client = OpenAI(
    base_url="https://router.huggingface.co/v1",   # this exact host, nothing else
    api_key=os.environ["HF_TOKEN"],
)

hf download meta-llama/Llama-3.1-8B-Instruct --include "*.safetensors"
hf repo create my-org/my-model --repo-type model
hf upload my-org/my-model ./out --commit-message "v1 weights"

from huggingface_hub import snapshot_download
path = snapshot_download("BAAI/bge-small-en-v1.5")   # full repo, cached, resumable

import spaces
@spaces.GPU                       # GPU acquired for this call only
def generate(prompt: str) -> str:
    ...

from transformers import pipeline
pipe = pipeline("text-generation", model="meta-llama/Llama-3.1-8B-Instruct",
                device_map="auto", torch_dtype="auto")
print(pipe("Hello", max_new_tokens=64)[0]["generated_text"])

© ericrisco, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 6 other files (scripts, references) in skills/huggingface of ericrisco/rsc-harness.

• SKILL.md
• evals/README.md
• evals/cases.yaml
• references/endpoints-and-spaces.md
• references/hub-and-cli.md
• references/inference-providers.md
• scripts/verify.sh

Open the folder on GitHubat commit 92fde8f