A Python utility for downloading individual files, folders, model weights, datasets, and cached assets from Hugging Face, a platform for sharing machine-learning files.

Use it to pull models, datasets, files, or folder snapshots into a local project.

It gives other tools one consistent way to fetch Hugging Face content and retries automatically when the service temporarily limits requests.

hf-download — Skill for Claude Code by richfrem

Install

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.

Any agent

npx skills add richfrem/agent-plugins-skills --skill hf-download

Clone the repo

git clone --depth 1 https://github.com/richfrem/agent-plugins-skills

Made for: Claude Code.

Or install dev-utils, the plugin that ships this one along with the rest of its 17 skills.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/richfrem/agent-plugins-skills/hf-download/github.svg)](https://agentmods.dev/skills/richfrem/agent-plugins-skills/hf-download)

Your own site

<a href="https://agentmods.dev/skills/richfrem/agent-plugins-skills/hf-download"><img src="https://agentmods.dev/badge/skills/richfrem/agent-plugins-skills/hf-download/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/richfrem/agent-plugins-skills/hf-download"><img src="https://agentmods.dev/badge/skills/richfrem/agent-plugins-skills/hf-download.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 45 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 612 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00045	$0.00612
Opus 5	$0.00023	$0.00306
Sonnet 5	$0.00009	$0.00122
Haiku 4.5	$0.00005	$0.00061

Measured 6d ago against content hash c4034c467210, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

hf-download 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 6d ago.

The scan reads SKILL.md. This mod also ships 2 executable files (scripts/hf_config.py, scripts/hf_download.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

plugins/dev-utils/skills/hf-download/SKILL.md · 82 lines

How it starts

The opening of the file, as written. The whole thing — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Dependencies

This skill requires Python 3.8+ and standard library only. No external packages needed.

To install this skill's dependencies:

pip-compile ./requirements.in
pip install -r ./requirements.txt

See ./requirements.txt for the dependency lockfile (currently empty — standard library only).

HuggingFace Download Primitives

Status: Active Author: Richard Fremmerlid Domain: HuggingFace Integration Depends on: hf-init (credentials must be configured first)

Purpose

Provides consolidated download operations for all HF-consuming plugins (Primary Agent, local-llm-bench, etc.) to fetch files, models, and snapshots. All downloads include exponential backoff for rate-limit handling.

Available Operations

Function	Description	Source Repo
`download_file()`	Download a single file	Custom or default repo
`download_folder()`	Download an entire folder snapshot	Custom or default repo

Usage

From Python (as a library)

from hf_download import download_file, download_folder
from pathlib import Path

# Download a single file from dataset repository to local directory
local_file_path = await download_file(
    filename="data/soul_traces.jsonl",
    local_dir=Path("./local_data")
)

# Download a model snapshot (e.g. GGUF weights)
model_dir = await download_folder(
    local_dir=Path("./models"),
    repo_id="unsloth/gemma-4-12b-it-GGUF",
    repo_type="model",
    allow_patterns=["*UD-Q4_K_XL.gguf"]
)

From CLI

# Download a single file
python ./hf_download.py --filename data/soul_traces.jsonl --local-dir ./local_data

# Download a specific model snapshot using glob patterns
python ./hf_download.py \
  --repo-id unsloth/gemma-4-12b-it-GGUF \
  --repo-type model \
  --allow-patterns "*UD-Q4_K_XL.gguf" \
  --local-dir ./models

Prerequisites

Run hf-init first to validate credentials and dataset structure.
Requires huggingface_hub installed (pip install huggingface_hub).
Environment variables: HUGGING_FACE_USERNAME, HUGGING_FACE_TOKEN.

Read the full file on GitHub · 82 lines

Files

What ships with it

7 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.

Changes

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.

6d ago First seen · 82 lines · 45 tokens per session scan A c4034c467210

Subscribe to this mod's changes

hf-download is a skill published in the GitHub repository richfrem/agent-plugins-skills (6 stars, last pushed today), licensed MIT. It adds 45 tokens to every session and 612 once invoked, about $0.0002 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 2026-09-03.

Data and AI agent-skills agentic-framework agentic-os claude-code-skill claude-plugins claude-skills

swarm-scripts

Bulk, repeat, fan-out, or data-heavy work: write and run swarm scripts (inline script-run, named script-upsert, durable launch-script-run). Covers the script-vs-tool rubric, the authoring contract (args first, ctx second), the seed catalog, connections and secrets, dbquery, and exposing a script as an API.

desplega-ai/agent-swarm · 82 tokens

prompt-decompiler

This skill should be used when the user says "decompile this prompt", "reverse engineer this prompt", "analyze this prompt", "break down this prompt", "what does this prompt do", "adapt this prompt for", "simplify this prompt", "split this prompt", "migrate this prompt", "why does this prompt work", "explain this…

RadOrigin-LLC/RAD-Claude-Skills · 153 tokens

model-cli-gemini

Use when invoking Google's Gemini directly through the shared Antigravity, Gemini CLI, or agent fallback chain.

tony/skills · 27 tokens

custom-model-training

Trains a custom Ideogram model on a folder of reference images, then generates a new image with that trained model to prove it works — a real end-to-end pipeline (createdataset, uploaddatasetassets, trainmodel, poll getmodel, generateimage with custommodeluri), not just an explanation of how training works. Use…

devkindhq/ideogram-ai-toolkit · 230 tokens

ideogram-prompt

Prompting technique guide for Ideogram image generation via the connected Ideogram MCP (generateimage, describeimage, remiximage, editimage). Use whenever the user wants to generate, remix, or edit an image with Ideogram — including moodboards, style-matching a reference image, extracting a visual "recipe" from…

devkindhq/ideogram-ai-toolkit · 128 tokens

seurat-skill

Comprehensive Seurat v5 (R) guide for single-cell RNA-seq and multimodal analysis. Covers installation, standard workflows (Normalize/SCTransform), clustering, integration (CCA/RPCA/Harmony), differential expression (FindMarkers/FindAllMarkers), visualization (DimPlot/FeaturePlot/VlnPlot/DoHeatmap), spatial…

Agents365-ai/seurat-skill · 167 tokens