NVIDIA/skills is a catalogue of portable instruction sets that teach coding agents how to use NVIDIA software for robotics, simulation, CUDA, retrieval-augmented generation, and related workflows. Developers install these skills in agents such as Claude Code or Codex, while the catalogue mirrors skills maintained in separate NVIDIA product repositories.
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/skills --skill jetson-customize-usbgit clone --depth 1 https://github.com/NVIDIA/skillsWrote 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/skills/jetson-customize-usb)<a href="https://agentmods.dev/skills/nvidia/skills/jetson-customize-usb"><img src="https://agentmods.dev/badge/skills/nvidia/skills/jetson-customize-usb.svg" alt="Measured on agentmods" height="20"></a>- Gen Agent Trust Hub pass
- Socket pass
- Snyk warn
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 | $0.00039 | $0.02379 |
| Opus 5 | $0.00019 | $0.01189 |
| Sonnet 5 | $0.00008 | $0.00476 |
| Haiku 4.5 | $0.00004 | $0.00238 |
Grade A, and why
jetson-customize-usb 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 3d 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 — 184 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Customize USB (per-port enable / disable / role)
Purpose
Enable, disable, or change the role of USB2 / USB3 SS ports on a
Jetson Thor (Tegra264) or Orin (Tegra234) custom carrier. Captures
per-port wiring (role, max speed, VBUS-EN / OC GPIOs, CC1/CC2 GPIOs
for Type-C, USB3 SS UPHY lane), resolves the SS to USB2 companion
graph from the in-tree DTB, then renders a self-contained kernel-DT
overlay that flips every port action in three places in lockstep
(lane status, port status, host xHCI phys + phy-names).
UPHY lane allocation belongs to jetson-customize-uphy. No ODMDATA
edit. Output is one commit to the composite custom overlay .dts in
the bsp_sources/ hardware repo.
Prerequisites
- Active profile with
reference_devkit:+custom_carrier:blocks. <source.root_path>/Linux_for_Tegra/.gitexists (/jetson-init-source)./jetson-derive-carrierhas run — carrier flash-conf fork in the overlay tracker./jetson-customize-uphyhas run when any enabled USB3 SS port needs a non-stock UPHY lane allocation. Its JSON sidecar at<workspace>/target-platform/<profile-stem>.jetson-customize-uphy.jsonis consulted for SS lane allocation.- Source-of-truth docs: Adaptation Guide §"Port the Universal Serial Bus", Module Design Guide §USB, SoC TRM (xusb block).
- When
custom_carrier:is present, bothdocuments.custom_carrier_schematicANDdocuments.custom_carrier_pinmux_xlsare REQUIRED. Refuse the run if either is missing — per-port routing (VBUS-EN / OC / CC GPIOs, SS lane wiring, hub fan-out) on a custom carrier cannot be guessed. Reference-devkit-only profiles skip this check. dtc,fdtoverlayon PATH.
Overview
USB on Tegra spans three IP surfaces: the xusb_padctl block (USB2
OTG + USB3 SS PHYs), the tegra-xusb xHCI host controller, and an
optional tegra-xudc device controller attached to the single
OTG-capable USB2 port (usb2-0).
A per-port flip MUST touch three kernel-DT places in lockstep.
Anything less crashes the host xHCI probe and leaves lsusb empty
on every port (collateral damage to stock-okay ports):
What ships with it
10 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.
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.
- 3d ago First seen · 184 lines · 39 tokens per session scan A 5c08383c04ad
jetson-customize-usb is a skill published in the GitHub repository NVIDIA/skills (3,211 stars, last pushed yesterday), licensed Apache-2.0. It adds 39 tokens to every session and 2,379 once invoked, about $0.0002 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 2026-09-03.
Other skills, from other repositories
spark-environment-setup
Set up a working ML training/inference environment on NVIDIA DGX Spark (GB10, aarch64, CUDA 13). Use when installing PyTorch/Unsloth/TRL/vLLM on DGX Spark, hitting libcudart or wheel-ABI errors on aarch64, or choosing between NGC containers and bare pip installs.
spark-training-gotchas
Preflight and diagnose the ten known failure modes for ML training on NVIDIA DGX Spark. Use when a training run on DGX Spark fails to start, OOMs below the 128GB limit, slows down mid-run, or before any multi-hour training job on GB10.
terraform-module-library
Build reusable Terraform modules for AWS, Azure, GCP, and OCI infrastructure following infrastructure-as-code best practices. Use when creating infrastructure modules, standardizing cloud provisioning, or implementing reusable IaC components.
hyperpod-version-checker
Check and compare software component versions on SageMaker HyperPod cluster nodes - NVIDIA drivers, CUDA toolkit, cuDNN, NCCL, EFA, AWS OFI NCCL, GDRCopy, MPI, Neuron SDK (Trainium/Inferentia), Python, and PyTorch. Use when checking component versions, verifying CUDA/driver compatibility, detecting version mismatches…
technical-troubleshooting
Provide setup, troubleshooting, and maintenance guidance. Use when the user reports a device that won't power on, connectivity issues, setup questions, overheating, or maintenance concerns.
gpu-optimizer
GPU optimization for consumer NVIDIA GPUs (8-24GB VRAM) covering mixed precision, gradient checkpointing, XGBoost GPU, CuPy/cuDF migration, and torch.compile. Triggers on: "optimize GPU training", "speed up CUDA", "reduce OOM", "migrate NumPy to CuPy", "manage GPU memory", "benchmark PyTorch".