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-setup-nvidia-gpu-hostgit 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-setup-nvidia-gpu-host)<a href="https://agentmods.dev/skills/nvidia-tao/tao-skill-bank/tao-setup-nvidia-gpu-host"><img src="https://agentmods.dev/badge/skills/nvidia-tao/tao-skill-bank/tao-setup-nvidia-gpu-host/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-setup-nvidia-gpu-host"><img src="https://agentmods.dev/badge/skills/nvidia-tao/tao-skill-bank/tao-setup-nvidia-gpu-host.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 4 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 77 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Privilege Escalation · line 169 Commands invoke sudo or root privileges. Verify this elevated access is necessary and justified.Fix: Avoid sudo/root unless strictly required. Prefer least-privilege patterns. If elevation is needed, document the justification and scope.
- medium MCP Rug Pull · line 169 Docker image references without a specific tag (:latest is implicit) or digest (@sha256:...) can be silently replaced by a malicious image.Fix: Pin the image: image:tag or image@sha256:abc123
- medium Privilege Escalation · line 256 Commands invoke sudo or root privileges. Verify this elevated access is necessary and justified.Fix: Avoid sudo/root unless strictly required. Prefer least-privilege patterns. If elevation is needed, document the justification and scope.
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 | $0.00177 | $0.03386 |
| Opus 5 | $0.00088 | $0.01693 |
| Sonnet 5 | $0.00035 | $0.00677 |
| Haiku 4.5 | $0.00018 | $0.00339 |
Grade B, and why
tao-setup-nvidia-gpu-host scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 7d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
sudo docker run --rm --runtime=nvidia --gpus all "$TAO_IMAGE" nvidia-smi -L How it starts
The opening of the file, as written. The whole thing — 262 lines — stays where its author put it; the contents beside it link to each section on GitHub.
NVIDIA GPU Host Setup
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).
Use this setup skill before TAO workflows run on the docker, local-docker,
or kubernetes backend. The TAO-wide default minimums are:
- NVIDIA driver
>=580(open kernel module preferred) - CUDA Toolkit
>=13.0 - NVIDIA Container Toolkit
>=1.19.0 - Docker engine — only installed for
docker/local-dockerbackends and only when Docker is missing. The package picked depends on the distro family (docker.ioon Debian-family by default,moby-engine/docker-cefromdownload.docker.comon RHEL-family,dockeron SUSE-family). Pass--skip-docker-installto opt out.
The check is safe and read-only by default — it works on any Linux
distribution because it only probes nvidia-smi, the CUDA toolkit path,
the installed container-toolkit package version (via dpkg/rpm/the
nvidia-ctk binary version), and the Docker daemon's NVIDIA runtime.
Installation must be explicitly authorized by the user and rerun with
--install. The install path is automated for these distro families:
| Family | Tested distros | Manager | Notes |
|---|---|---|---|
| debian | Ubuntu 22.04 / 24.04, Debian 12 (and derivatives Pop!_OS, Mint, Zorin, Raspbian, KDE Neon, etc. via UBUNTU_CODENAME / VERSION_CODENAME) |
apt-get |
Adds NVIDIA cuda-keyring + Container Toolkit .list. Docker via docker.io (override $DOCKER_PACKAGE_DEBIAN). |
| rhel | Fedora 39+, RHEL / Rocky / AlmaLinux 9 and 10 | dnf (or yum) |
Adds NVIDIA cuda-<distro>.repo + Container Toolkit .repo. Docker via Fedora moby-engine when available, otherwise docker-ce from download.docker.com. |
| suse | openSUSE Leap 15, SLES 15 | zypper |
Adds the same NVIDIA .repo files. Docker via the distribution docker package. |
| other (Arch, Alpine, Gentoo, NixOS, FreeBSD, …) | n/a | n/a | --install exits with a clear error listing the version targets and the NVIDIA install-guide URLs. Install manually, then rerun --check-only. |
What ships with it
6 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.
- 7d ago First seen · 262 lines · 177 tokens per session scan B bc3b2a18db46
tao-setup-nvidia-gpu-host is a skill published in the GitHub repository NVIDIA-TAO/tao-skill-bank (88 stars, last pushed today), licensed Apache-2.0. It adds 177 tokens to every session and 3,386 once invoked, about $0.0009 per session on Opus 5. A static security scan graded it B with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
securing-container-registry-with-harbor
Harbor is an open-source container registry that provides security features including vulnerability scanning (integrated Trivy), image signing (Notary/Cosign), RBAC, content trust policies, replicatio.
implementing-container-image-minimal-base-with-distroless
Reduce container attack surface by building application images on Google distroless base images that contain only the application runtime with no shell, package manager, or unnecessary OS utilities.
nvca-chart-release
Release NVCA Operator chart changes from the native monorepo source to the vendored Helm chart. Use when updating the vendored NVCA Operator chart, changing NVCA image refs, publishing helm-nvca-operator, or validating the chart against a self-managed control plane.
performing-container-security-scanning-with-trivy
Scan container images, filesystems, and Kubernetes manifests for vulnerabilities, misconfigurations, exposed secrets, and license compliance issues using Aqua Security Trivy with SBOM generation and CI/CD integration.
nvca-values-customization
Customize NVCA Operator Helm chart values in the native monorepo. Use when modifying vendored defaults, changing stack-derived install values, adding deployment-time overrides, or updating scripts under deploy/helm/nvca-operator.
nvca-self-managed-install
Install or validate the NVCA Operator chart against a self-managed NVCF control plane from the native monorepo. Use when the control plane comes from deploy/stacks/self-managed and NVCA must be installed with stack-derived image repository settings.