hugging-face-jobs

hugging-face-jobs is a skill for Claude Code from patchy631/ai-engineering-hub. It costs 103 tokens per session (8,087 once invoked), scanned C, original, MIT.

A guide for running computing tasks on Hugging Face Jobs, a managed cloud service with CPU, GPU, and TPU machines. Jobs can save their results to Hugging Face Hub.

In plain words
What is it for?
Use it for data processing, batch predictions, experiments, model training, synthetic-data generation, development, testing, and scheduled tasks.
Why use it?
It lets you run large or hardware-intensive work without preparing matching local infrastructure.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: positional $N argument.

Part of the hugging-face-skills plugin — 8 skills, 1 plugin shipped together

Good fit Use it for data processing, batch predictions, experiments, model training, synthetic-data generation, development, testing, and scheduled tasks.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/patchy631/ai-engineering-hub/hugging-face-jobs
About the project

AI Engineering Hub is a learning and project repository covering large language models, retrieval-augmented generation, AI agents, and related applications. Beginners, practitioners, and researchers use its tutorials and projects to learn AI engineering and build working systems. The catalogue entries are examples of the skills, plugins, and agent resources included with it.

patchy631/ai-engineering-hub · 37,448 stars · on GitHub · join.dailydoseofds.com

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 patchy631/ai-engineering-hub --skill hugging-face-jobs
Clone the repo
git clone --depth 1 https://github.com/patchy631/ai-engineering-hub

Made for: Claude Code.

Or install hugging-face-skills, the plugin that ships this one along with the rest of its 8 skills, 1 plugin.

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 hugging-face-jobs

README.md
[![agentmods](https://agentmods.dev/badge/skills/patchy631/ai-engineering-hub/hugging-face-jobs/github.svg)](https://agentmods.dev/skills/patchy631/ai-engineering-hub/hugging-face-jobs)
Your own site
<a href="https://agentmods.dev/skills/patchy631/ai-engineering-hub/hugging-face-jobs"><img src="https://agentmods.dev/badge/skills/patchy631/ai-engineering-hub/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.

agentmods 80×15 button for hugging-face-jobs

Your own site · 80×15
<a href="https://agentmods.dev/skills/patchy631/ai-engineering-hub/hugging-face-jobs"><img src="https://agentmods.dev/badge/skills/patchy631/ai-engineering-hub/hugging-face-jobs.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 103 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 8,087 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 3 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 7 findings, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • medium Rogue Agent · line 31
    Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.
    Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
  • medium Excessive Agency · line 423
    Skill grants unrestricted tool access without appropriate constraints. An agent with unfettered tool access can perform arbitrary actions including file modification, network requests, and code execution.
    Fix: Restrict tool access to only the tools required for the skill's stated purpose. Use an explicit allowlist rather than granting blanket access.
  • medium Data Exfiltration · line 511
    Data is uploaded to cloud storage (S3 / GCS / Azure Blob). This may be a legitimate backup or exfiltration to an external bucket. Manual review is recommended.
    Fix: Verify the destination bucket is trusted and owned by you. Never upload credentials, secrets, or workspace contents to external or unverified cloud storage.
  • medium Data Exfiltration · line 525
    Data is uploaded to cloud storage (S3 / GCS / Azure Blob). This may be a legitimate backup or exfiltration to an external bucket. Manual review is recommended.
    Fix: Verify the destination bucket is trusted and owned by you. Never upload credentials, secrets, or workspace contents to external or unverified cloud storage.
  • medium Data Exfiltration · line 554
    Data is uploaded to cloud storage (S3 / GCS / Azure Blob). This may be a legitimate backup or exfiltration to an external bucket. Manual review is recommended.
    Fix: Verify the destination bucket is trusted and owned by you. Never upload credentials, secrets, or workspace contents to external or unverified cloud storage.
  • medium Data Exfiltration · line 533
    Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
    Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
  • medium Data Exfiltration · line 533
    Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
    Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
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 $0.00103 $0.08087
Opus 5 $0.00051 $0.04043
Sonnet 5 $0.00021 $0.01617
Haiku 4.5 $0.00010 $0.00809

Measured 10d ago against content hash 027f40972832, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade C, and why

hugging-face-jobs scanned grade C with 3 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 10d ago.

The scan reads SKILL.md. This mod also ships 3 executable files (scripts/cot-self-instruct.py, scripts/finepdfs-stats.py, scripts/generate-responses.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.

Sends data to an external URLmediumData exfiltration

A POST to an outside endpoint may be telemetry or may be exfiltration; either way the mod talks to somewhere, and you should know where.

requests.post("https://your-api.com/results", json=results)

Unrestricted tool accessmediumExcessive agency

A wildcard tool grant or "run any command" leaves no least-privilege boundary at all.

**Benefits:** Full Docker control, use pre-built images, run any command

Makes network callslowCapability

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

requests.post("https://your-api.com/results", json=results)
Origin

Copies of this mod

2 near-identical copies found in the catalogue:

hugging-face-skills/skills/hugging-face-jobs/SKILL.md · 1,037 lines

How it starts

The opening of the file, as written. The whole thing — 1,037 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 Hugging Face Hub.

Common use cases:

  • Data Processing - Transform, filter, or analyze large datasets
  • Batch Inference - Run inference on thousands of samples
  • Experiments & Benchmarks - Reproducible ML experiments
  • Model Training - Fine-tune models (see model-trainer skill for TRL-specific training)
  • Synthetic Data Generation - Generate datasets using LLMs
  • Development & Testing - Test code without local GPU setup
  • Scheduled Jobs - Automate recurring tasks

For model training specifically: See the model-trainer skill for TRL-based training workflows.

When to Use This Skill

Use this skill when users want to:

  • Run Python workloads on cloud infrastructure
  • Execute jobs without local GPU/TPU setup
  • Process data at scale
  • Run batch inference or experiments
  • Schedule recurring tasks
  • Use GPUs/TPUs for any workload
  • Persist results to the Hugging Face Hub

Key Directives

When assisting with jobs:

  1. ALWAYS use hf_jobs() MCP tool - Submit jobs using hf_jobs("uv", {...}) or hf_jobs("run", {...}). The script parameter accepts Python code directly. Do NOT save to local files unless the user explicitly requests it. Pass the script content as a string to hf_jobs().

  2. Always handle authentication - Jobs that interact with the Hub require HF_TOKEN via secrets. See Token Usage section below.

  3. Provide job details after submission - After submitting, provide job ID, monitoring URL, estimated time, and note that the user can request status checks later.

  4. Set appropriate timeouts - Default 30min may be insufficient for long-running tasks.

Prerequisites Checklist

Before starting any job, verify:

Account & Authentication

  • Hugging Face Account with Pro, Team, or Enterprise plan (Jobs require paid plan)
  • Authenticated login: Check with hf_whoami()
  • HF_TOKEN for Hub Access ⚠️ CRITICAL - Required for any Hub operations (push models/datasets, download private repos, etc.)
  • Token must have appropriate permissions (read for downloads, write for uploads)

Read the full file on GitHub · 1,037 lines

Files

What ships with it

8 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.

  1. 10d ago First seen · 1,037 lines · 103 tokens per session scan C 027f40972832

Subscribe to this mod's changes

hugging-face-jobs is a skill published in the GitHub repository patchy631/ai-engineering-hub (37,448 stars, last pushed 14d ago), licensed MIT. It adds 103 tokens to every session and 8,087 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it C with 3 findings (sends data to an external url, unrestricted tool access, 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

dstack-prototyping

Use with the dstack skill for model-serving work when the image, serving command, resources, backend/fleet choice, or service behavior is not proven. Guides task-first prototyping on real hardware, choosing fleets/backends that can reuse idle instances and caches, checking vLLM/SGLang sources, and verifying the final…

dstackai/dstack · 80 tokens

dstack-presets

Create and manage dstack presets: a toolkit that streamlines model inference optimization with agents, and a portable preset format. Use together with the dstack skill, and only when the user explicitly asks to create a preset or manage existing presets, not for deploying or serving a model.

dstackai/dstack · 61 tokens

dstack

Skill "dstack" from dstackai/dstack, covering dstack, how it works, quick agent flow (detached runs), agent execution guidelines and output accuracy.

dstackai/dstack · 28 tokens

flow-nexus-neural

Train and deploy neural networks in distributed E2B sandboxes with Flow Nexus.

ruvnet/agentic-flow · 21 tokens

thinking-out-loud

A contract for what the agent does when a long, messy, stream-of-consciousness ramble arrives (usually voice dictation): act on nothing until the echo brief is approved. The echo audits the entire transfer, mission, locked decisions and constraints, open questions, flips and parked tangents, with the model's…

Shubhamsaboo/awesome-llm-apps · 206 tokens

cost-optimization

Optimize cloud costs across AWS, Azure, GCP, and OCI through resource rightsizing, tagging strategies, reserved instances, and spending analysis. Use when reducing cloud expenses, analyzing infrastructure costs, or implementing cost governance policies.

wshobson/agents · 48 tokens