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 agentmods add skills/diillson/chatcli/huggingfacenpx skills add diillson/chatcli --skill huggingfacegit clone --depth 1 https://github.com/diillson/chatcliWrote 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/diillson/chatcli/huggingface)<a href="https://agentmods.dev/skills/diillson/chatcli/huggingface"><img src="https://agentmods.dev/badge/skills/diillson/chatcli/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 | $0.00076 | $0.00523 |
| Opus 5 | $0.00038 | $0.00262 |
| Sonnet 5 | $0.00015 | $0.00105 |
| Haiku 4.5 | $0.00008 | $0.00052 |
Grade A, and why
huggingface 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 yesterday.
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.
curl -s "https://huggingface.co/api/models?search=whisper&sort=downloads&limit=10" What it actually says
Hugging Face Hub
Public Hub browsing is keyless (HTTP API); a token (HF_TOKEN) is only needed for private or
gated repos and uploads.
Search (keyless)
curl -s "https://huggingface.co/api/models?search=whisper&sort=downloads&limit=10"
curl -s "https://huggingface.co/api/datasets?search=sentiment&limit=10"
Read id, downloads, likes, pipeline_tag.
Model / dataset card
@webfetch https://huggingface.co/<org>/<model> # the card
curl -s "https://huggingface.co/api/models/<org>/<model>" # metadata JSON
Download (huggingface-cli)
pip install -U "huggingface_hub[cli]"
huggingface-cli download <org>/<model> --local-dir ./model
# gated/private:
HF_TOKEN=... huggingface-cli download <org>/<model>
For a single file: huggingface-cli download <org>/<model> config.json.
Upload (needs token)
huggingface-cli login # or set HF_TOKEN
huggingface-cli upload <org>/<repo> ./local-dir
Choosing a model
- Search by task (
pipeline_tag: text-generation, automatic-speech-recognition, etc.). - Sort by downloads/likes/recency; read the card for license, size, and intended use.
- Report id, license, size, and a one-line fit assessment before downloading large weights.
Rules
- Weights can be huge — confirm before downloading multi-GB repos; mention disk cost.
- Respect model licenses; surface the license from the card.
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.
- yesterday First seen · 64 lines · 76 tokens per session scan A 0c9cac4c8058
huggingface is a skill published in the GitHub repository diillson/chatcli (90 stars, last pushed today), licensed Apache-2.0. It adds 76 tokens to every session and 523 once invoked, about $0.0004 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 2026-09-03.
Other skills, from other repositories
vector-and-embedding-weaknesses
Hunt vector / embedding weaknesses (OWASP LLM08:2025) — adversarial inputs against the RAG / similarity layer that cause cross-tenant leak, embedding-inversion privacy loss, semantic confusion, and retriever-driven prompt injection.
llm-redteam-overview
LLM red team category — full AATMF v3 tactic coverage (T01–T15). Routing skill: read this first to identify which tactic applies, then load the matching sub-skill. Maps to MITRE ATLAS where overlap exists.
shap
Model interpretability and explainability using SHAP (SHapley Additive exPlanations). Use this skill when explaining machine learning model predictions, computing feature importance, generating SHAP plots (waterfall, beeswarm, bar, scatter, force, heatmap), debugging models, analyzing model bias or fairness, comparing…
glycobiology
Glycosylation site prediction and glycobiology analysis. N-glycosylation motif finding, O-glycosylation hotspot prediction, glycan structure resources. Lightweight, pure Python. For protein function queries use uniprot-database; for structure analysis use alphafold-database.
cellxgene-census
Query the CELLxGENE Census (61M+ cells) programmatically. Use when you need expression data across tissues, diseases, or cell types from the largest curated single-cell atlas. Best for population-scale queries, reference atlas comparisons. For analyzing your own data use scanpy or scvi-tools.
data_analysis
基于已确认数据执行可审计的数学计算和描述统计。.