What is nvidia-cuopt-skills?

A set of agent skills for NVIDIA cuOpt, a solver for routing and mathematical optimisation problems. These include vehicle routing, linear and mixed-integer programming, and quadratic programming.

Use it to formulate routing and optimisation problems, install cuOpt with Python, C, Conda, or Docker, run its REST server, and develop or debug its C++, CUDA, Python, server, and CI code.

It helps translate optimisation problems into cuOpt models and covers the practical work of installing, using, changing, testing, and serving cuOpt.

nvidia-cuopt-skills — Plugin by NVIDIA

Install

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.

Claude Code

/plugin marketplace add NVIDIA/cuopt

agentmods

npx agentmods add plugins/nvidia/cuopt/marketplace

Clone the repo

git clone --depth 1 https://github.com/NVIDIA/cuopt

Made for: Claude Code.

Per session not measured What this adds to a session before it is invoked.

When invoked not measured Not applicable: nothing here is loaded into a session.

Security scan A 1 finding. Scan, not verified.

Origin original No closer match found in the catalogue.

Security

Grade A, and why

nvidia-cuopt-skills scanned grade A 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 yesterday.

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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

"description": "cuOpt REST server — start server, endpoints, Python/curl client examples. Use when the user is deploying or calling the REST API."

.claude-plugin/marketplace.json · 67 lines

How it starts

The opening of the file, as written. The whole thing — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.

{
  "name": "nvidia-cuopt-skills",
  "owner": {
    "name": "NVIDIA"
  },
  "metadata": {
    "description": "Agent skills for NVIDIA cuOpt: routing (VRP, TSP, PDP), LP/MILP/QP, installation (user/developer), and REST server.",
    "version": "26.10.00"
  },
  "plugins": [
    {
      "name": "cuopt-user-rules",
      "source": "./skills/cuopt-user-rules",
      "skills": "./",
      "description": "Base rules for end users calling NVIDIA cuOpt (routing/LP/MILP/QP/install/server). Not for cuOpt internals — use cuopt-developer for those."
    },
    {
      "name": "cuopt-developer",
      "source": "./skills/cuopt-developer",
      "skills": "./",
      "description": "Modify, build, test, debug, and contribute to NVIDIA cuOpt (C++/CUDA, Python, server, CI). Use for solver internals, PRs, DCO, and code conventions."
    },
    {
      "name": "cuopt-install",
      "source": "./skills/cuopt-install",
      "skills": "./",
      "description": "Install cuOpt for Python, C, or as a server (pip, conda, Docker) — system requirements, install commands, and verification. Use when the user wants to install or verify cuOpt for any user-facing interface."
    },
    {
      "name": "cuopt-numerical-optimization-formulation",
      "source": "./skills/cuopt-numerical-optimization-formulation",
      "skills": "./",
      "description": "Numerical optimization (LP, MILP, QP) — concepts, problem-text parsing, and formulation patterns. What LP, MILP, and QP are, required formulation questions, modeling elements, common patterns, and how to parse problem statements (parameters, constraints, decisions, objective). Domain concepts; no API or interface."
    },
    {
      "name": "cuopt-numerical-optimization-api",
      "source": "./skills/cuopt-numerical-optimization-api",
      "skills": "./",
      "description": "LP, MILP, and QP (beta) with cuOpt — Python, C, and CLI. Use when the user is solving LP, MILP, or QP with any cuOpt interface."
    },
    {
      "name": "cuopt-mul

Read the full file on GitHub · 67 lines

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.

yesterday First seen · 67 lines scan A 03604a9c51c1

Subscribe to this mod's changes

nvidia-cuopt-skills is a plugin published in the GitHub repository NVIDIA/cuopt (1,032 stars, last pushed 3d ago), licensed Apache-2.0. Its token cost is not measured: this kind of file is read by the harness, not the model. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Backend and APIs Debugging DevOps and cloud GPU Optimization cuda linear-programming

veloq

VeloQ is an agent-friendly profile-query CLI for Nsight Systems, Nsight Compute, and PyTorch/Kineto traces.

lucifer1004/VeloQ · not measured

VeloQ

Agent-friendly GPU profile-query CLI.

lucifer1004/VeloQ · not measured

gpu-server-setup

Plugin marketplace listing 1 plugin: gpu-server-setup.

EvilFreelancer/gpu-server-setup · not measured

gpu-server-setup

Prepare a Linux server with NVIDIA GPUs for LLM and neural-network workloads: NVIDIA driver + CUDA from the official repo, Docker Engine + NVIDIA Container Toolkit as the mandatory base, GPU passthrough into containers, staged verification gates, optional docker-compose presets for vLLM, Infinity, OpenWebUI and Ollama.

EvilFreelancer/gpu-server-setup · not measured