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-train-bevfusiongit 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-train-bevfusion)<a href="https://agentmods.dev/skills/nvidia-tao/tao-skill-bank/tao-train-bevfusion"><img src="https://agentmods.dev/badge/skills/nvidia-tao/tao-skill-bank/tao-train-bevfusion/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-train-bevfusion"><img src="https://agentmods.dev/badge/skills/nvidia-tao/tao-skill-bank/tao-train-bevfusion.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00103 | $0.03369 |
| Opus 5 | $0.00051 | $0.01684 |
| Sonnet 5 | $0.00021 | $0.00674 |
| Haiku 4.5 | $0.00010 | $0.00337 |
Grade A, and why
tao-train-bevfusion 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 13d 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 — 236 lines — stays where its author put it; the contents beside it link to each section on GitHub.
BEVFusion
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).
BEVFusion for multi-sensor 3D object detection. Fuses LiDAR point clouds and camera images in bird's-eye-view (BEV) space. Used in autonomous driving for robust 3D perception.
Set pretrained backbone paths for Swin image backbone.
BEVFusion requires the BEVFusion-specific TAO container
nvcr.io/nvidia/tao/tao-toolkit:5.5.0-pyt. Shared TAO PyTorch 7.x images do
not package mmdet3d and fail before any BEVFusion action can parse its
spec. The model-skill action is named dataset_convert, but the 5.5 container
CLI subtask is bevfusion convert -e <spec>.
Dataclass Schemas
Generated TAO Core schemas are packaged in schemas/<action>.schema.json, with schemas/manifest.json listing available actions. Each generated schema also emits references/spec_template_<action>.yaml from the schema top-level default field. AutoML enablement is declared at the model layer in references/skill_info.yaml via automl_enabled. Runnable AutoML for an action requires schemas/<action>.schema.json and references/spec_template_<action>.yaml to exist and parse. Use the packaged selected-action schema for automl_default_parameters, automl_disabled_parameters, defaults, min/max bounds, enums, option weights, math conditions, dependencies, and popular parameters. Do not expect ~/tao-core at runtime; maintainers regenerate schemas/templates before packaging the skill bank.
Train Action Policy
This model is AutoML-enabled at the model layer. Before handling any train-stage request, read references/skill_info.yaml and resolve the run override from either an explicit automl_policy value or the user's workflow request. Use automl_policy: on by default and only expose on / off in new launch prompts. Treat phrases like "turn off AutoML", "disable AutoML", "no HPO", or "plain training" as automl_policy: off for this run only. When automl_policy: on, automl_enabled: true, and both schemas/train.schema.json and references/spec_template_train.yaml are packaged, route the train action through tao-skill-bank:tao-run-automl by default with this model's skill_dir. Preserve workflow/application overrides for datasets, specs, output directories, GPU/platform settings, parent checkpoints, and automl_policy. Use direct model training only when automl_policy: off or the packaged train schema/template is missing; in the missing-schema case, report that AutoML is enabled but not runnable for this model until schemas are generated.
What ships with it
14 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 4.0 KB
- evals/evals.json 787 B
- references/skill_info.yaml 2.5 KB
- references/spec_template_dataset_convert.yaml 156 B
- references/spec_template_evaluate.yaml 6.8 KB
- references/spec_template_inference.yaml 6.8 KB
- references/spec_template_train.yaml 6.8 KB
- schemas/dataset_convert.schema.json 2.6 KB
- schemas/evaluate.schema.json 95 KB
- schemas/inference.schema.json 95 KB
- schemas/manifest.json 12 KB
- schemas/train.schema.json 95 KB
- skill-card.md 3.8 KB
- skill.oms.sig 6.9 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.
- 13d ago First seen · 236 lines · 103 tokens per session scan A c225202c2b7f
tao-train-bevfusion is a skill published in the GitHub repository NVIDIA-TAO/tao-skill-bank (88 stars, last pushed today), licensed Apache-2.0. It adds 103 tokens to every session and 3,369 once invoked, about $0.0005 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 2026-08-30.
Other skills, from other repositories
yolo-detection-2026-coral-tpu-macos
Google Coral Edge TPU — real-time object detection natively (macOS / Linux).
yolo-detection-2026-openvino
OpenVINO — real-time object detection via Docker (NCS2, Intel GPU, CPU).
ai-game-world-design
Complete mastery guide for designing and building AI-powered game worlds — procedural world generation, NPC behavior trees, LLM-driven dialogue systems, emergent storytelling, economy simulation, player modeling, and real-time difficulty adaptation. Covers the full stack from world-building fundamentals to integrating…
recommendation-algorithm-design
Complete mastery guide for designing social media recommendation algorithms — understanding candidate generation, ranking models, engagement prediction, content graph modeling, collaborative filtering, embedding spaces, real-time personalization, exploration vs exploitation tradeoffs, feedback loops, filter bubble…
lstm-price-prediction-guide
Guide to LSTM-based cryptocurrency price prediction. Covers data preprocessing, feature engineering, LSTM architecture, training, evaluation, and deployment. Includes TensorFlow/Keras implementation with technical indicators and sentiment features.
ai-agents-library-guide
Guide to the AI Agents Library — a curated collection of 300+ production-grade AI agent system prompts ready for import. Covers DeFi, crypto, trading, research, coding, writing, and more. Each prompt is optimized for GPT-4, Claude, Gemini, and other frontier models.