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/robium-ai/robium/huggingfacenpx skills add robium-ai/robium --skill huggingfacegit clone --depth 1 https://github.com/robium-ai/robiumWrote 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/robium-ai/robium/huggingface)<a href="https://agentmods.dev/skills/robium-ai/robium/huggingface"><img src="https://agentmods.dev/badge/skills/robium-ai/robium/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 5.1 | $0.00129 | $0.02422 |
| Opus 5 | $0.00064 | $0.01211 |
| Sonnet 5 | $0.00026 | $0.00484 |
| Haiku 4.5 | $0.00013 | $0.00242 |
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 2d 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 — 245 lines — stays where its author put it; the contents beside it link to each section on GitHub.
huggingface
The lean, self-contained Hub layer for Robium. Use the installed CLI as the executable source of truth, keep robotics-specific artifact checks visible, and pause before publishing, paid compute, destructive operations, or handling credentials beyond the user's explicit authority.
When to use this skill
- Inspecting, downloading, creating, or uploading a robotics dataset or model repository on the Hugging Face Hub.
- Exploring a dataset before downloading it, including its subsets, rows, Parquet exports, size, or statistics through Dataset Viewer.
- Listing available Hub Jobs hardware or, after explicit authority, running, monitoring, inspecting, or cancelling a Job.
- Inspecting a Space's metadata, runtime, build logs, or run logs.
- Route LeRobotDataset structure, recording, policy training, checkpoint
semantics, and evaluation to
lerobot; route source-selection strategy todata; route whole-application choices toarchitect.
Key directives
- Delegation posture: embed + links. Embed the stable common path below;
consult live
hf <group> --helpand official documentation for flags and uncommon operations. The external Hugging Face skill catalog is optional, not a dependency. - Inspect before transfer. Check the repo card, file tree, revision, license, access status, and robotics embodiment/schema before downloading a large artifact or planning around it.
- Keep secrets out of prompts, commands, logs, and commits. Prefer the
browser/device flow from
hf auth loginor an already configuredHF_TOKEN. Never echo a token, place it directly on a command line, or print it throughhf auth tokenduring an agent session. - External mutations need authority. Creating a repo, uploading or changing visibility, starting paid compute, restarting a Space, cancelling another process, or deleting/moving content requires explicit user authorization for the concrete action. Inspection and public downloads are read-only.
- Do not copy a generated CLI inventory into Robium. Run
hf --helpand the relevant subgroup's help immediately before using a version-sensitive flag. The installed CLI and current official docs outrank examples here. - Never infer dataset/model facts from memory. Verify current contents, licensing, access, file sizes, and task/robot compatibility against the Hub.
What ships with it
2 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.
- 2d ago First seen · 245 lines · 129 tokens per session scan A 33db074e9c9e
huggingface is a skill published in the GitHub repository robium-ai/robium (9 stars, last pushed 8d ago), licensed MIT. It adds 129 tokens to every session and 2,422 once invoked, about $0.0006 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.
Other skills, from other repositories
spark-environment-setup
Set up a working ML training/inference environment on NVIDIA DGX Spark (GB10, aarch64, CUDA 13). Use when installing PyTorch/Unsloth/TRL/vLLM on DGX Spark, hitting libcudart or wheel-ABI errors on aarch64, or choosing between NGC containers and bare pip installs.
spark-memory-thermal-ops
Manage unified memory and thermals during long-running ML jobs on NVIDIA DGX Spark. Use when planning memory headroom for a training run on GB10, when a job OOMs on unified memory, or when monitoring temperature and power during multi-hour training.
spark-training-gotchas
Preflight and diagnose the ten known failure modes for ML training on NVIDIA DGX Spark. Use when a training run on DGX Spark fails to start, OOMs below the 128GB limit, slows down mid-run, or before any multi-hour training job on GB10.
solr-semantic-search
To build Solr phrase-tagging semantic search: concept tagging, taxonomy, graph paths.
coding-agents-prompt-authoring
To author, adapt, review, and validate prompts (skills, agents, workflows, rules, etc.) with brief, contracts, and a validation pack.
solr-query
To build and debug Solr queries: eDisMax, block join, JSON facets, kNN, explain.