What is cuda-quantum?

A skill for CUDA-Q, NVIDIA's programming model for combining quantum circuits with classical code and running simulations on GPUs or quantum hardware. It includes Python and C++ patterns and CUDA-QX extensions for chemistry and error correction.

It is for writing CUDA-Q kernels, simulating quantum programs, building variational algorithms, targeting quantum hardware, modelling molecular systems, and implementing quantum error correction.

It gives developers established patterns for constructing circuits, running GPU-accelerated simulations, and configuring hardware backends. It also explains how to use multiple GPUs and inspect circuits.

cuda-quantum — Skill for Claude Code and Codex by dtunai

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.

Any agent

npx skills add dtunai/agent-skills-for-compute --skill cuda-quantum

Clone the repo

git clone --depth 1 https://github.com/dtunai/agent-skills-for-compute

Made for: Claude Code, Codex.

Its marketplace also offers this one on its own, as the plugin cuda-quantum — /plugin install cuda-quantum after adding the marketplace above.

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/dtunai/agent-skills-for-compute/cuda-quantum/github.svg)](https://agentmods.dev/skills/dtunai/agent-skills-for-compute/cuda-quantum)

Your own site

<a href="https://agentmods.dev/skills/dtunai/agent-skills-for-compute/cuda-quantum"><img src="https://agentmods.dev/badge/skills/dtunai/agent-skills-for-compute/cuda-quantum/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/dtunai/agent-skills-for-compute/cuda-quantum"><img src="https://agentmods.dev/badge/skills/dtunai/agent-skills-for-compute/cuda-quantum.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 100 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,372 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.

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	$0.00100	$0.02372
Opus 5	$0.00050	$0.01186
Sonnet 5	$0.00020	$0.00474
Haiku 4.5	$0.00010	$0.00237

Measured 10d ago against content hash ce9113df0424, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

cuda-quantum 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 10d 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.

skills/cuda-quantum/SKILL.md · 207 lines

How it starts

The opening of the file, as written. The whole thing — 207 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CUDA-Q (CUDA Quantum)

Overview

Programming model and toolchain for hybrid quantum-classical computing on NVIDIA GPUs. CUDA-Q provides Python and C++ APIs for building quantum circuits, running GPU-accelerated simulations, executing variational algorithms, and targeting real quantum hardware — all through a unified kernel-based programming model.

Quick Pattern

Incorrect — raw gate operations without kernel:

# No kernel decorator, no GPU acceleration
from qiskit import QuantumCircuit
qc = QuantumCircuit(2)
qc.h(0)
qc.cx(0, 1)

Correct — CUDA-Q kernel with GPU simulation:

import cudaq

@cudaq.kernel
def bell_pair():
    qubits = cudaq.qvector(2)
    h(qubits[0])
    x.ctrl(qubits[0], qubits[1])
    mz(qubits)

result = cudaq.sample(bell_pair, shots_count=1000)
print(result)

Quick Command

# Install CUDA-Q
pip install cuda-quantum

# Install CUDA-QX extensions
pip install cudaq-solvers cudaq-qec

# Run with GPU backend
python my_circuit.py --target nvidia

# Run with multi-GPU
mpiexec -np 4 python my_circuit.py --target nvidia --target-option mgpu

# Draw circuit
python -c "import cudaq; print(cudaq.draw(my_kernel, *args))"

Quick Reference

Core API

Function	Purpose
`@cudaq.kernel`	Decorate function as quantum kernel (JIT compiled)
`cudaq.qvector(N)`	Allocate N qubits
`cudaq.qubit()`	Allocate single qubit
`cudaq.sample(kernel, *args)`	Sample measurement outcomes
`cudaq.run(kernel, *args)`	Execute kernel with return values
`cudaq.observe(kernel, hamiltonian, *args)`	Compute expectation value
`cudaq.evolve(hamiltonian, dims, schedule, state)`	Dynamics time evolution
`cudaq.vqe(kernel, hamiltonian, optimizer)`	Run VQE optimization
`cudaq.get_state(kernel, *args)`	Get full statevector
`cudaq.draw(kernel, *args)`	ASCII circuit visualization
`cudaq.translate(kernel, format)`	Translate to OpenQASM
`cudaq.set_target(name)`	Select simulation/hardware backend

Read the full file on GitHub · 207 lines

Files

What ships with it

8 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.

10d ago First seen · 207 lines · 100 tokens per session scan A ce9113df0424

Subscribe to this mod's changes

cuda-quantum is a skill published in the GitHub repository dtunai/agent-skills-for-compute (2 stars, last pushed 6mo ago), licensed MIT. It adds 100 tokens to every session and 2,372 once invoked, about $0.0005 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 2026-08-31.

C and C++Languages Python Scientific

cuopt-numerical-optimization-api

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.

NVIDIA/skills · 51 tokens

cuopt-developer

Modify, build, test, debug, and contribute to NVIDIA cuOpt (C++/CUDA, Python, server, CI). Use for solver internals, PRs, DCO, and code conventions.

NVIDIA/cuopt · 47 tokens

torchtalk-analyzer

Analyze PyTorch internals across Python, C++, and CUDA layers using the TorchTalk MCP server. Use when asked about how PyTorch operators work internally, where functions are implemented, what would break if code is modified, or finding tests for PyTorch operators.

opendatahub-io/ai-helpers · 58 tokens

cuda-quantum