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 skills add bcastelino/agent-skills-kit --skill hugging-face-jobsgit clone --depth 1 https://github.com/bcastelino/agent-skills-kitWrote 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/bcastelino/agent-skills-kit/hugging-face-jobs)<a href="https://agentmods.dev/skills/bcastelino/agent-skills-kit/hugging-face-jobs"><img src="https://agentmods.dev/badge/skills/bcastelino/agent-skills-kit/hugging-face-jobs/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.
<a href="https://agentmods.dev/skills/bcastelino/agent-skills-kit/hugging-face-jobs"><img src="https://agentmods.dev/badge/skills/bcastelino/agent-skills-kit/hugging-face-jobs.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00050 | $0.03034 |
| Opus 5 | $0.00025 | $0.01517 |
| Sonnet 5 | $0.00010 | $0.00607 |
| Haiku 4.5 | $0.00005 | $0.00303 |
Grade A, and why
hugging-face-jobs 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 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.
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 — 313 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Running Workloads on Hugging Face Jobs
Overview
Run any workload on fully managed Hugging Face infrastructure. No local setup required: jobs run on cloud CPUs, GPUs, or TPUs and can persist results to the Hub.
Common use cases: Data Processing, Batch Inference, Experiments & Benchmarks, Model Training (see model-trainer skill for TRL-specific), Synthetic Data Generation, Development & Testing, Scheduled Jobs.
When to Use This Skill
- Run Python workloads on cloud infrastructure
- Execute jobs without local GPU/TPU setup
- Process data at scale or run batch inference
- Schedule recurring tasks
- Persist results to the Hugging Face Hub
Key Directives
- Always use
hf_jobs()MCP tool:hf_jobs("uv", {...})orhf_jobs("run", {...}). Pass script content as a string; do NOT save to local files unless asked. - Always handle authentication: Hub operations require
HF_TOKENvia secrets. Seereferences/token_usage.md. - Provide job details after submission: job ID, monitoring URL, estimated time.
- Set appropriate timeouts: default 30 min may be insufficient.
Prerequisites
- HF Account with Pro, Team, or Enterprise plan
- Authenticated: verify with
hf_whoami() - For Hub operations:
secrets={"HF_TOKEN": "$HF_TOKEN"}(never hardcode tokens)
Full token guide:
references/token_usage.md
Quick Start
Approach 1: UV Scripts (Recommended)
UV scripts use PEP 723 inline dependencies for clean, self-contained workloads.
hf_jobs("uv", {
"script": """
# /// script
# dependencies = ["transformers", "torch"]
# ///
from transformers import pipeline
result = pipeline("sentiment-analysis")("I love Hugging Face!")
print(result)
""",
"flavor": "cpu-basic",
"timeout": "30m"
})
CLI: hf jobs uv run my_script.py --flavor cpu-basic --timeout 30m
Python API: run_uv_job("my_script.py", flavor="cpu-basic", timeout="30m")
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.
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.
- 12d ago First seen · 313 lines · 50 tokens per session scan A 9115ef60c4d7
hugging-face-jobs is a skill published in the GitHub repository bcastelino/agent-skills-kit (2 stars, last pushed 1mo ago), licensed MIT. It adds 50 tokens to every session and 3,034 once invoked, about $0.0003 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 2026-08-31.
Other skills, from other repositories
machine-learning-ops-ml-pipeline
Design and implement a complete ML pipeline for: $ARGUMENTS.
agy-prompting
Internal helper — how to tighten a user request into a sharp prompt for the Antigravity CLI (agy / Gemini 3.x with native web search and agentic tools).
companion-clis
Companion CLIs for Runpod workflows — HuggingFace, GitHub, Docker, and AWS.
agent-platform-deploy
Deploy open models or custom weights from Model Garden to Agent Platform endpoints, check deployment status, verify serving endpoints, or clean up resources by undeploying models and deleting endpoints. Use when asked to deploy models on Agent Platform, list available Model Garden models, check if a model is…
gemini-3-prompting
Guidance for writing effective prompts for Antigravity (agy) / Gemini 3 models.
managing-streamlit-apps
Create, deploy, and operate Streamlit apps in PostHog via the streamlit-apps MCP tools — create an app, set its source, start and stop its sandbox, poll status, list versions, delete, and share the app with humans via its PostHog URL. Use when asked to "create a streamlit app", "deploy a data app", "ship a dashboard…