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-port-huggingface-modelgit 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-port-huggingface-model)<a href="https://agentmods.dev/skills/nvidia-tao/tao-skill-bank/tao-port-huggingface-model"><img src="https://agentmods.dev/badge/skills/nvidia-tao/tao-skill-bank/tao-port-huggingface-model/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-port-huggingface-model"><img src="https://agentmods.dev/badge/skills/nvidia-tao/tao-skill-bank/tao-port-huggingface-model.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 | $0.00210 | $0.04521 |
| Opus 5 | $0.00105 | $0.02261 |
| Sonnet 5 | $0.00042 | $0.00904 |
| Haiku 4.5 | $0.00021 | $0.00452 |
Grade C, and why
tao-port-huggingface-model scanned grade C with 1 finding 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.
Harvests environment variableshighData exfiltration
Enumerating or grepping the environment for keys collects credentials unrelated to what the mod says it does.
**Goal:** decide whether to proceed at all. Gather credentials, locate/clone the four TAO repos, create a consistent working branch, launch the `tao-hf-inspect` container (Context A), validate the HF model is CV with a s How it starts
The opening of the file, as written. The whole thing — 211 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Standalone install? If this session was not initialized by the TAO skill bank plugin, run the
tao-setupskill first (host preflight, credentials, cross-skill discovery).
TAO-HF Integration Skill
Integrate a HuggingFace (HF) Computer Vision model into the NVIDIA TAO Toolkit ecosystem. Work the phases iteratively — not purely linearly — via a build → test → debug → fix → retest loop at every step: when something fails, diagnose and fix before moving on; when it passes, move to the next step.
This SKILL.md is the workflow coordinator. Each phase has a dedicated references/phase-N-*.md with the full step-by-step content, code, docker invocations, and gates. Read the matching reference at the start of each phase — the summaries below are not sufficient.
Local-Only Rule
All work is strictly local. Do NOT push/commit/branch on any remote (GitLab, GitHub, HuggingFace), create merge/pull requests or issues, or upload/publish Docker images to any registry or artifact store. You may only read/clone from remotes — all edits, Docker builds, and test runs stay on the local machine.
Submodule Override Strategy
The user clones the four TAO repos (tao-core, tao-pytorch, tao-deploy, tao-dataservices) independently into one working directory. The tao-core/ submodule nested inside each repo points to the original unmodified commit; modifications only exist in the top-level tao-core/. Always install from the top-level tao-core/, never <repo>/tao-core/ — the nested submodule silently ignores all modifications. Override rules: (1) mount the working directory -v $(pwd):/workspace; (2) pip install /workspace/tao-core FIRST, before tao-pytorch/tao-deploy; (3) PYTHONPATH top-level tao-core first, e.g. -e PYTHONPATH=/workspace/tao-core:/workspace/tao-pytorch. See references/cross-cutting.md for the directory tree.
What ships with it
20 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.
- BENCHMARK.md 3.9 KB
- eval.config 3.2 KB
- evals/evals.json 809 B
- references/cross-cutting.md 10 KB
- references/docker-patterns.md 16 KB
- references/hf-inspection.md 6.2 KB
- references/phase-0-prereqs.md 9.9 KB
- references/phase-1-inspection.md 10 KB
- references/phase-2-codebase.md 7.3 KB
- references/phase-3-implementation.md 35 KB
- references/phase-4-deploy.md 13 KB
- references/phase-5-packaging.md 3.3 KB
- references/phase-6-container-tests.md 15 KB
- references/phase-7-optimization.md 7.8 KB
- references/repo-structure.md 11 KB
- references/tao-patterns.md 20 KB
- references/task-type-guide.md 16 KB
- references/workflow-consistency.md 27 KB
- skill-card.md 4.3 KB
- skill.oms.sig 8.1 KB
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 · 211 lines · 210 tokens per session scan C fd8cacf316e1
tao-port-huggingface-model is a skill published in the GitHub repository NVIDIA-TAO/tao-skill-bank (88 stars, last pushed today), licensed Apache-2.0. It adds 210 tokens to every session and 4,521 once invoked, about $0.0011 per session on Opus 5. A static security scan graded it C with 1 finding (harvests environment variables). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
quantizing-models-bitsandbytes
Quantizes LLMs to 8-bit or 4-bit for 50-75% memory reduction with minimal accuracy loss. Use when GPU memory is limited, need to fit larger models, or want faster inference. Supports INT8, NF4, FP4 formats, QLoRA training, and 8-bit optimizers. Works with HuggingFace Transformers.
llama-factory
Expert guidance for fine-tuning LLMs with LLaMA-Factory - WebUI no-code, 100+ models, 2/3/4/5/6/8-bit QLoRA, multimodal support.
mlflow
Track ML experiments, manage model registry with versioning, deploy models to production, and reproduce experiments with MLflow - framework-agnostic ML lifecycle platform.
huggingface-hub
HuggingFace hf CLI: search/download/upload models, datasets.
submit-github-bug-issue
Use when converting QA findings, black-box failures, red-team reports, regression evidence, or local bug notes into GitHub Issues for NVIDIA/TensorRT-Model-Connect. Standardizes checking issue templates, checking labels, de-duplicating existing issues, drafting a bug report, creating the issue on GitHub, applying the…
submit-github-pr
Use when publishing an existing TensorRT-Model-Connect change as a GitHub pull request. Verifies authenticated repository access, branch and diff scope, validation evidence, commit identity, reviewer-facing text, exact pushed head, and the created draft PR without merging it.