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 NVIDIA-TAO/tao-skill-bank --skill tao-finetune-anomalygennextgit clone --depth 1 https://github.com/NVIDIA-TAO/tao-skill-bankWrote 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/nvidia-tao/tao-skill-bank/tao-finetune-anomalygennext)<a href="https://agentmods.dev/skills/nvidia-tao/tao-skill-bank/tao-finetune-anomalygennext"><img src="https://agentmods.dev/badge/skills/nvidia-tao/tao-skill-bank/tao-finetune-anomalygennext/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/nvidia-tao/tao-skill-bank/tao-finetune-anomalygennext"><img src="https://agentmods.dev/badge/skills/nvidia-tao/tao-skill-bank/tao-finetune-anomalygennext.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 | $0.00058 | $0.01234 |
| Opus 5.5 | $0.00023 | $0.00494 |
| Sonnet 5.5 | $0.00012 | $0.00247 |
| Haiku 4.5 | $0.00006 | $0.00123 |
Grade A, and why
tao-finetune-anomalygennext 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 21d 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 — 124 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Fine-tune AnomalyGenNext
This leaf prepares a user-owned dataset and optional recipe for task-specific
AnomalyGenNext LoRA training. The pinned image is declared in
references/skill_info.yaml; do not replace it with the older 1.0 release.
Read references/input-contract.md when validating a dataset or adapting a
recipe, and references/container-runtime.md before submission.
Inputs
DATASET/
defect_spec.jsonl
TEXTURE/
clean_image/*
anomaly_image/DEFECT/*
mask/DEFECT/*
VALIDATION/testcase.jsonl
Also supply a DCP-format Cosmos3-Nano base checkpoint directory containing
checkpoint.json, model/.metadata, and at least one model/*.distcp shard,
Wan2.2_VAE.pth, and
a complete checkpoint root containing the required Qwen tokenizer model assets
under hf/ plus facebook/dinov2-large/ for validation. The hf/ directory
name is part of the upstream image's fixed checkpoint layout. The validation
JSONL must contain image_filename, mask_filename, and anomaly_type; each trained
TEXTURE+DEFECT needs at least three rows. A separately stored defect spec is
accepted with --defect-spec.
If the official Cosmos3-Nano checkpoint is not already staged in DCP format, run the converter shipped in the pinned AnomalyGenNext image and write its output to a mounted, persistent directory:
python -m cosmos_framework.scripts.convert_model_to_dcp \
-o /models/Cosmos3-Nano-dcp \
--checkpoint-path Cosmos3-Nano
The registered Cosmos3-Nano name resolves the official checkpoint. To
convert an already-staged Hugging Face checkpoint instead, replace it with
that directory's absolute container path. Use the converter output as
--base-checkpoint; preparation verifies checkpoint.json,
model/.metadata, and the generated model/*.distcp shards before GPU work.
Dataset and validation images and masks must use .jpg, .jpeg, or .png,
matching the extensions supported by the AnomalyGenNext 1.1 runtime loader.
Every mask pixel must be binary 0 or 255; palette or grayscale masks with
intermediate values are rejected before training. Each mask must contain both
values, so empty/all-zero and full/all-255 masks are also rejected.
What ships with it
11 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.
- assets/default_recipe.yaml 593 B
- evals/evals.json 1.0 KB
- references/container-runtime.md 2.3 KB
- references/input-contract.md 2.8 KB
- references/nn-score-contract.md 837 B
- references/skill_info.yaml 2.5 KB
- scripts/finetune_anomalygennext.sh 3.4 KB runs code
- scripts/prepare_finetune_recipe.py 13 KB runs code
- scripts/tests/test_nn_improvement.py 3.1 KB runs code
- scripts/tests/test_prepare_finetune_recipe.py 8.9 KB runs code
- scripts/validate_nn_improvement.py 6.4 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.
- 21d ago Changed · +19 lines dad884f08c93
- 22d ago Changed · +7 lines d5983c8945c8
- 24d ago Changed · +5 lines b0cc3144586c
- 1mo ago First seen · 93 lines · 58 tokens per session scan A a90785dc1529
tao-finetune-anomalygennext is a skill published in the GitHub repository NVIDIA-TAO/tao-skill-bank (97 stars, last pushed 5d ago), licensed Apache-2.0. It adds 58 tokens to every session and 1,234 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-09-10.
Other skills, from other repositories
huawei-cloud-cloudrobo-train
Manage CloudRobo model training tasks and simulation reinforcement learning (SimRL) tasks — create pretrain (TRAINFROMSCRATCH) and finetune (MODELTUNING) tasks with FFT/SFT/LORA/QLORA/DEEPSPEED methods; manage the full task lifecycle (create/read/update/delete/stop/restart/resume/draft); save and resubmit draft…
tinker-research
Pi overlay for Tinker post-training. Use when the user wants to plan SFT/RL/DPO/distillation, pick a model, or run experiments from Pi. Canonical methodology lives in Tinker Cookbook — do not reinvent it here.
huggingface-transformers
Use Hugging Face Transformers pipelines, tokenizers, and AutoModel interfaces for inference and fine-tuning workflows.
Data Validation
Data quality checks to run before modeling — distribution summaries, leakage detection, class balance.
zero_shot_mutation_workflow
Zero-shot mutation engineering with VenusFactory PLMs. Use when the user wants beneficial mutations, directed evolution candidates, or stability/fitness ranking from a FASTA sequence or PDB structure. Do NOT use for ProteinMPNN inverse folding (proteinmpnndesignworkflow), sequence homology search…
venus_finetune_workflow
Fine-tune and run custom protein models on VenusFactory (CSV/HF → config → train → predict). Use when the user brings labeled sequences, wants adapter training (ProtT5/ESM2/Ankh/QLoRA notes), or batch inference with a trained config. Do NOT use for zero-shot mutation without labels (zeroshotmutationworkflow) or…