A command-line tool for managing NVIDIA AI Workbench projects, which are Git-based development projects for GPU-accelerated artificial intelligence and machine learning. It can work with containers on your computer or on remote machines.

Use it to create or clone AI Workbench projects, build their container environments, and manage local or remote contexts, applications, and environment variables.

It provides one interface for creating, copying, building, and configuring these projects and the places where they run. This reduces the need to manage container environments manually.

How brevdev/workshop-build-an-agent configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to brevdev/workshop-build-an-agent. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/brevdev/workshop-build-an-agent/main/.agents/skills/nvwb/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/brevdev/workshop-build-an-agent

Made for: Claude Code.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/brevdev/workshop-build-an-agent/nvwb/github.svg)](https://agentmods.dev/skills/brevdev/workshop-build-an-agent/nvwb)

Your own site

<a href="https://agentmods.dev/skills/brevdev/workshop-build-an-agent/nvwb"><img src="https://agentmods.dev/badge/skills/brevdev/workshop-build-an-agent/nvwb/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/brevdev/workshop-build-an-agent/nvwb"><img src="https://agentmods.dev/badge/skills/brevdev/workshop-build-an-agent/nvwb.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 52 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,044 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits

NVIDIA SkillSpector pass 7 Sept 2026

How audits are shown

Origin original No closer match found in the catalogue.

Token cost

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	$0.00052	$0.01044
Opus 5.5	$0.00021	$0.00418
Sonnet 5.5	$0.00010	$0.00209
Haiku 4.5	$0.00005	$0.00104

Measured 1mo ago against content hash 84251a1067d9, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

nvwb 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 1mo 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.

.agents/skills/nvwb/SKILL.md · 91 lines

How it starts

The opening of the file, as written. The whole thing — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.

NVIDIA AI Workbench — Local Machine (Control Plane)

NVIDIA AI Workbench is a lightweight, containerized development platform for GPU-accelerated AI/ML workflows. Every project is a Git repo with a .project/spec.yaml that defines the container environment. It supports Docker and Podman as container runtimes.

The nvwb CLI always runs on the local machine — the user's laptop or desktop. From there it manages contexts, which may be local (container on the same machine) or remote (container on a server or cloud instance accessed via SSH). Codex using this skill is on the local machine.

The user wants help with: $ARGUMENTS

Core Concepts

Contexts — Locations/machines where projects run (local, remote SSH, Brev cloud)
Projects — Git repos with container configuration (.project/spec.yaml)
Applications — Services inside the container (JupyterLab, VS Code, custom webapps/processes)
Environment Variables — Runtime values set via CLI; sensitive ones (--is-sensitive) are masked in output. Values are never committed to Git. Projects may declare required secret variable names in spec.yaml under execution.secrets.

Current State Detection

Before taking action, check the current state:

nvwb list contexts        # What locations are configured?
nvwb status               # Is a project open? Is the container running?
nvwb list projects        # What projects exist in the active context?

Build vs Runtime Isolation

Build-time (changes require nvwb build):

apt.txt — system packages
requirements.txt — pip packages
preBuild.bash / postBuild.bash — custom build scripts
Package manager entries in spec.yaml

Runtime (changes require container restart: nvwb close + nvwb open):

variables.env — environment variables
Mount configuration changes
App definitions in spec.yaml

No action needed:

Code in layout directories (code/, data/, models/) — live-mounted at /project/

Key Environment Variables

Read the full file on GitHub · 91 lines

Files

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.

Changes

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.

1mo ago First seen · 91 lines · 52 tokens per session scan A 84251a1067d9

Subscribe to this mod's changes

nvwb is a skill published in the GitHub repository brevdev/workshop-build-an-agent (151 stars, last pushed 16d ago), licensed Apache-2.0. It adds 52 tokens to every session and 1,044 once invoked, about $0.0002 per session on Opus 5.5. 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.

Containers Data and AI DevOps and cloud

kermt-monitor

Check progress for a detached KERMT run (pretrain, finetune, or any kermtrundetached invocation). Reads run.json, queries docker for container state, tails the pretrain/finetune log, and parses progress lines (epoch, step, val loss).

NVIDIA/skills · 64 tokens

kermt-setup

Bootstrap the KERMT agent environment — verify host docker + nvidia-container-toolkit, build the kermt:latest image from the repo's Dockerfile if it doesn't yet exist, and run a GPU smoke test inside the container. Every other kermt- skill depends on this; invoke it first.

NVIDIA/skills · 69 tokens

harbor

CLI toolkit for managing containerized LLM services. Use when the user wants to start, stop, configure, or manage AI/LLM services like Ollama, Open WebUI, llama.cpp, vLLM, LiteLLM, ComfyUI, and 250+ others. Triggers on requests to "run a model", "start ollama", "set up an LLM", "configure harbor", "manage services"…

av/harbor · 114 tokens

vss-deploy-video-embedding

Use this skill when deploying, operating, integrating, or customizing the VSS RT-Embed Video Embedding microservice. Covers standalone Docker Compose deployment, the /v1 REST API for text/video embeddings and live streams, Redis/Kafka/OTel integration, troubleshooting, and bring-your-own-model (BYOM) custom embedding…

NVIDIA-AI-Blueprints/video-search-and-summarization · 115 tokens

etl-integration-nifi

Apache NiFi specialist for flow-based data integration, routing, and provenance tracking. Deep expertise in processors, FlowFiles, connections, process groups, clustering, record-oriented processing, and NiFi 2.x modernization. WHEN: \"Apache NiFi\", \"NiFi\", \"NiFi processor\", \"FlowFile\", \"process group\"…

Kilo-Org/kilo-marketplace · 168 tokens

senior-ml-engineer

Skill de engenharia de ML para colocar modelos em produção, construir pipelines MLOps e integrar LLMs. Cobre implantação de modelos, feature stores, monitoramento de drift, sistemas RAG e otimização de custos. Use quando o usuário perguntar sobre implantar modelos de ML em produção, configurar infraestrutura MLOps…

ricneves-ai/flowgrammers-skills · 110 tokens

workshop-build-an-agent: Skill for Claude Code