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 fanfan-de/anybox --skill vision-trainergit clone --depth 1 https://github.com/fanfan-de/anyboxWrote 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/fanfan-de/anybox/vision-trainer)<a href="https://agentmods.dev/skills/fanfan-de/anybox/vision-trainer"><img src="https://agentmods.dev/badge/skills/fanfan-de/anybox/vision-trainer/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/fanfan-de/anybox/vision-trainer"><img src="https://agentmods.dev/badge/skills/fanfan-de/anybox/vision-trainer.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 | $0.00194 | $0.07600 |
| Opus 5.5 | $0.00078 | $0.03040 |
| Sonnet 5.5 | $0.00039 | $0.01520 |
| Haiku 4.5 | $0.00019 | $0.00760 |
Grade A, and why
huggingface-vision-trainer 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 1mo 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.
This is a copy
100% identical to huggingface-vision-trainer — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 594 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Vision Model Training on Hugging Face Jobs
Train object detection, image classification, and SAM/SAM2 segmentation models on managed cloud GPUs. No local GPU setup required—results are automatically saved to the Hugging Face Hub.
When to Use This Skill
Use this skill when users want to:
- Fine-tune object detection models (D-FINE, RT-DETR v2, DETR, YOLOS) on cloud GPUs or local
- Fine-tune image classification models (timm: MobileNetV3, MobileViT, ResNet, ViT/DINOv3, or any Transformers classifier) on cloud GPUs or local
- Fine-tune SAM or SAM2 models for segmentation / image matting using bbox or point prompts
- Train bounding-box detectors on custom datasets
- Train image classifiers on custom datasets
- Train segmentation models on custom mask datasets with prompts
- Run vision training jobs on Hugging Face Jobs infrastructure
- Ensure trained vision models are permanently saved to the Hub
Related Skills
hugging-face-jobs— General HF Jobs infrastructure: token authentication, hardware flavors, timeout management, cost estimation, secrets, environment variables, scheduled jobs, and result persistence. Refer to the Jobs skill for any non-training-specific Jobs questions (e.g., "how do secrets work?", "what hardware is available?", "how do I pass tokens?").hugging-face-model-trainer— TRL-based language model training (SFT, DPO, GRPO). Use that skill for text/language model fine-tuning.
Local Script Execution
Helper scripts use PEP 723 inline dependencies. Run them with uv run:
uv run scripts/dataset_inspector.py --dataset username/dataset-name --split train
uv run scripts/estimate_cost.py --help
Prerequisites Checklist
Before starting any training job, verify:
Account & Authentication
- Hugging Face Account with Pro, Team, or Enterprise plan (Jobs require paid plan)
- Authenticated login: Check with
hf_whoami()(tool) orhf auth whoami(terminal) - Token has write permissions
- MUST pass token in job secrets — see directive #3 below for syntax (MCP tool vs Python API)
What ships with it
12 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.
- agents/openai.yaml 122 B
- references/finetune_sam2_trainer.md 6.3 KB
- references/hub_saving.md 17 KB
- references/image_classification_training_notebook.md 11 KB
- references/object_detection_training_notebook.md 29 KB
- references/reliability_principles.md 9.3 KB
- references/timm_trainer.md 3.5 KB
- scripts/dataset_inspector.py 31 KB runs code
- scripts/estimate_cost.py 7.2 KB runs code
- scripts/image_classification_training.py 13 KB runs code
- scripts/object_detection_training.py 27 KB runs code
- scripts/sam_segmentation_training.py 14 KB runs code
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.
- 1mo ago First seen · 594 lines · 194 tokens per session scan A c7aba4de75fa
huggingface-vision-trainer is a skill published in the GitHub repository fanfan-de/anybox (55 stars, last pushed 21d ago), licensed MIT. It adds 194 tokens to every session and 7,600 once invoked, about $0.0008 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 100% identical to huggingface-vision-trainer, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
arboreto
Infers candidate gene regulatory networks from bulk or single-cell expression data using AertsLab Arboreto GRNBoost2 and GENIE3. Use for transcription factor-target association ranking, compatible Dask execution, sparse expression inputs, and network stability checks.
deepspot-m
Generates transcriptome-wide virtual spatial transcriptomics from H&E histology with DeepSpot-M. Used for predicted log1p-CPM expression from 224x224 tiles at about 20x, querying the released protein-coding gene panel by symbol, and whole-slide prediction after resolution-aware tiling with histolab.
torchdrug
Builds and troubleshoots TorchDrug 0.2.1 workflows for molecular graphs, property prediction, self-supervised pretraining, molecule generation, retrosynthesis, protein representation learning, and knowledge graph reasoning. Use when code imports torchdrug or needs its datasets, models, tasks, or Engine.
pyhealth
Builds and validates PyHealth clinical machine-learning pipelines for EHR, signals, imaging, and medical codes. Use for PyHealth dataset loading, MIMIC-III/IV, eICU or OMOP prediction tasks, patient-level evaluation, mortality/readmission/length-of-stay modeling, medication recommendation, sleep staging, Trainer…
ml-training-recipes
Battle-tested PyTorch training recipes for all domains — LLMs, vision, diffusion, medical imaging, protein/drug discovery, spatial omics, genomics. Covers training loops, optimizer selection (AdamW, Muon), LR scheduling, mixed precision, debugging, and systematic experimentation. Use when training or fine-tuning…
nemo-mbridge-perf-expert-parallel-overlap
Validate and use MoE expert-parallel communication overlap in Megatron-Bridge, including overlapmoeexpertparallelcomm, delaywgradcompute, and flex dispatcher backends such as DeepEP and HybridEP.