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 agentmods add skills/nvidia/skills/doca-container-deploymentnpx skills add NVIDIA/skills --skill doca-container-deploymentgit 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/doca-container-deployment)<a href="https://agentmods.dev/skills/nvidia/skills/doca-container-deployment"><img src="https://agentmods.dev/badge/skills/nvidia/skills/doca-container-deployment.svg" alt="Measured on agentmods" 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 | $0.00234 | $0.02420 |
| Opus 5 | $0.00117 | $0.01210 |
| Sonnet 5 | $0.00047 | $0.00484 |
| Haiku 4.5 | $0.00023 | $0.00242 |
Grade A, and why
doca-container-deployment 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 5d 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 — 195 lines — stays where its author put it; the contents beside it link to each section on GitHub.
DOCA container deployment
Where to start: This skill is for operating the cross-cutting DOCA container-deployment runtime — the shared pattern every DOCA service on the BlueField uses to come up (kubelet standalone agent on the BlueField Arm watching a static-pod manifests directory; the operator drops a YAML pod spec into that directory; kubelet schedules the pod and runs the container).
If the developer has NOT yet decided container vs. bare-metal
("I just got a BlueField, what now?", "my code is built, how do I
run it?", "how do I deploy this?"), route them BACK to
doca-setup ## recognize first.
That is the front-door routing decision. The wrong failure mode is
to silently push every developer onto the container path because the
agent loaded this skill first. ## recognize detects the system
shape, asks the minimum residual question, and lands the developer on
either this skill (when the workload is a packaged DOCA service to
drop on a BlueField) or the bare-metal-path sibling
doca-bare-metal-deployment
(when the workload is a DOCA-linked application binary the developer
launches directly).
If the developer is already on the container path, open
TASKS.md and start at
## configure. If the question is what shape
of runtime is this and what does the deployment contract look like,
start at CAPABILITIES.md. For per-service
overlays, follow the per-service skill under skills/services/ that
layers on top of this one — the supported overlays are Argus, DMS,
Firefly, and UROM service. Flow-Inspector and OS-Inspector are
policy-excluded from this public bundle; route them through
doca-public-knowledge-map
instead of applying this runtime overlay. Externally-productized
NVIDIA services (BlueMan, HBN, SNAP, Virtio-net, DOCA Telemetry
Service as productized, …) are also out of scope and route through
that map. If DOCA is
not installed on the BlueField target yet, route to
doca-setup first.
What ships with it
7 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.
- 5d ago First seen · 195 lines · 234 tokens per session scan A 20274f090dce
doca-container-deployment is a skill published in the GitHub repository NVIDIA/skills (3,192 stars, last pushed today), licensed Apache-2.0. It adds 234 tokens to every session and 2,420 once invoked, about $0.0012 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
docker-optimization
Docker image optimization patterns including multi-stage builds, layer caching, security hardening, and size reduction techniques. Use when building Docker images, optimizing container size, improving build performance, or implementing Docker security best practices. Reduces image sizes by 70-90% and build times by…
test-integration-docker
Run comprehensive integration tests using real skills (Vercel, Anthropic, Expo) in a Docker container. Managed via Makefile for standard lifecycle control.
cli
Bento packages AI agent workspace state into portable, layered OCI artifacts — everything git doesn't track: agent memory, dependencies, build caches, conversation history, session state. Checkpoints are standard OCI images pushable to any container registry.
fp-live-system
Remote, stateful, or embedded system operations. Use when working with routers, OpenWrt, embedded Linux, VMs, containers, remote servers, or any target where a restart or 'ready' label is not proof of function. Provides management path preservation and verification protocols.
ci-debug-workflow
Debug failing CI pipelines, containers, and reproduce bugs locally. Use when CI is red, containers won't start, or need to reproduce bugs.
containerization-plan
Plan containerization for apps, services, jobs, and development environments. Use when Codex is asked to create or review Dockerfiles, container images, compose files, runtime users, build layers, healthchecks, ports, volumes, or container security.