hf-model-card-research

hf-model-card-research is a skill for Claude Code, Codex from AtlasOmnia/donna-starter. It costs 35 tokens per session (2,585 once invoked), scanned A, original, MIT.

A research workflow for reading Hugging Face model cards, which are pages where model authors describe their AI models and results.

In plain words
What is it for?
Use it to collect downloads, likes, file sizes, benchmark claims, and author statements for comparing model variants.
Why use it?
It gathers comparable information from scattered model pages and separates authors’ benchmark claims from other evidence.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions subagents.

Good fit Use it to collect downloads, likes, file sizes, benchmark claims, and author statements for comparing model variants.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/atlasomnia/donna-starter/hf-model-card-research
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 AtlasOmnia/donna-starter --skill hf-model-card-research
Clone the repo
git clone --depth 1 https://github.com/AtlasOmnia/donna-starter

Made for: Claude Code, Codex.

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.

agentmods badge for hf-model-card-research

README.md
[![agentmods](https://agentmods.dev/badge/skills/atlasomnia/donna-starter/hf-model-card-research/github.svg)](https://agentmods.dev/skills/atlasomnia/donna-starter/hf-model-card-research)
Your own site
<a href="https://agentmods.dev/skills/atlasomnia/donna-starter/hf-model-card-research"><img src="https://agentmods.dev/badge/skills/atlasomnia/donna-starter/hf-model-card-research/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.

agentmods 80×15 button for hf-model-card-research

Your own site · 80×15
<a href="https://agentmods.dev/skills/atlasomnia/donna-starter/hf-model-card-research"><img src="https://agentmods.dev/badge/skills/atlasomnia/donna-starter/hf-model-card-research.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 35 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,585 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00035 $0.02585
Opus 5 $0.00017 $0.01293
Sonnet 5 $0.00007 $0.00517
Haiku 4.5 $0.00003 $0.00259

Measured 12d ago against content hash e401d4224929, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

hf-model-card-research scanned grade A 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 12d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

**Pitfall — delegated subagents hit terminal guardrails on HF pulls.** Three dispatched subagents (each on different HF research tasks, all variants) hit `same_tool_failure_halt` after 4 repeated terminal retries on fail
Origin

Copies of this mod

1 near-identical copy found in the catalogue:

skills/research/hf-model-card-research/SKILL.md · 187 lines

How it starts

The opening of the file, as written. The whole thing — 187 lines — stays where its author put it; the contents beside it link to each section on GitHub.

HF Model Card Research

Extract structured metadata — downloads, likes, benchmark claims, file sizes, author statements — from HuggingFace model cards. Used when the user asks you to "check these models on HF", "pull benchmarks for these variants", or "compare what authors claim."

When to Use

  • User provides a list of authors and model families (e.g. "pull metadata for these Qwen3.6 variants")
  • You need to compare benchmark claims across multiple fine-tunes of the same base model
  • You need up-to-date download counts, likes, or file sizes for model variants
  • Verifying what a model card claims vs what other sources say
  • Surveying the ecosystem around a new base model release

Workflow

1. Discover model repo names

Search HF for each author's models using site:huggingface.co queries:

site:huggingface.co <author> <model-family> <variant-keyword>

Try variant-specific keywords: the author's handle, the model name, key terms like "uncensored", "abliterated", "Opus", "NVFP4", "MTP", etc.

For community quantizers (mradermacher, unsloth, byteshape), search with: site:huggingface.co <author> Qwen3.6-27B.

If search results are sparse, try the author's HF profile page directly: https://huggingface.co/<author>/models — use web_extract on that.

2. Pull structured stats via HF API

The HF API endpoint returns the metadata you need. Pull JSON, don't scrape the web view for stats:

https://huggingface.co/api/models/{owner}/{repo}

Returns JSON with:

  • downloads — download count
  • likes — like count
  • pipeline_tag — model type (text-generation, image-text-to-text)
  • tags, cardData, config, gguf, safetensors, siblings (file list), createdAt/lastModified
  • spaces (linked HF Spaces)
  • model-index (evaluation results when present)

Pitfall — delegated subagents hit terminal guardrails on HF pulls. Three dispatched subagents (each on different HF research tasks, all variants) hit same_tool_failure_halt after 4 repeated terminal retries on failed HF calls. The failure mode is predictable: subagents loop on the same failing terminal (curl to HF API) because they think "retry the same call until it works." The per-turn tool guardrail halts them after 4 non-progressing attempts with zero data produced. This happened across three separate delegations in the same session.

Read the full file on GitHub · 187 lines

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.

  1. 12d ago First seen · 187 lines · 35 tokens per session scan A e401d4224929

Subscribe to this mod's changes

hf-model-card-research is a skill published in the GitHub repository AtlasOmnia/donna-starter (111 stars, last pushed 12d ago), licensed MIT. It adds 35 tokens to every session and 2,585 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

rag-local-lancedb

Build, query, and manage local vector embeddings and semantic search pipelines using LanceDB and HuggingFace/SentenceTransformers embeddings without cloud dependencies.

pedroiff0/awesome-skills · 35 tokens

hf-model-card-research

Extract structured metadata — downloads, likes, benchmark claims, file sizes, author statements — from HuggingFace model cards. Used when the user asks you to "check these models on HF", "pull benchmarks for these variants", or "compare what authors claim.".

AtlasOmnia/hermes-custom-pack · 35 tokens

mnemosyne-maintenance

Use when: upgrading Mnemosyne, diagnosing slow/hung consolidation (mnemosynesleep), fixing missing embeddings, or troubleshooting import/version mismatches.

AtlasOmnia/hermes-custom-pack · 40 tokens

evaluating-llms-harness

Evaluates LLMs across 60+ academic benchmarks (MMLU, HumanEval, GSM8K, TruthfulQA, HellaSwag). Use when benchmarking model quality, comparing models, reporting academic results, or tracking training progress. Industry standard used by EleutherAI, HuggingFace, and major labs. Supports HuggingFace, vLLM, APIs.

pedroiff0/awesome-skills · 29 tokens

serving-llms-vllm

Use when deploying production LLM APIs, optimizing inference latency/throughput, or serving models with limited GPU memory. Supports OpenAI-compatible endpoints, quantization (GPTQ/AWQ/FP8), and tensor parallelism.

pedroiff0/awesome-skills · 27 tokens

computer-use

Drive the user's desktop in the background — clicking, typing, scrolling, dragging — without stealing the cursor, keyboard focus, or switching virtual desktops / Spaces. Cross-platform: macOS, Windows, Linux. Works with any tool-capable model. Load this skill whenever the computeruse tool is available.

pedroiff0/awesome-skills · 68 tokens