NVIDIA cuOpt is an optimization engine that uses GPUs to solve mathematical planning problems such as linear programming, quadratic programming, and vehicle routing. Developers and operations teams use its C++, C, Python, and server APIs for large-scale optimization, while the catalogue's agent skills connect it with agent-based optimization workflows.
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/cuopt --skill cuopt-user-rulesgit clone --depth 1 https://github.com/NVIDIA/cuoptWrote 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/cuopt/cuopt-user-rules)<a href="https://agentmods.dev/skills/nvidia/cuopt/cuopt-user-rules"><img src="https://agentmods.dev/badge/skills/nvidia/cuopt/cuopt-user-rules/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/cuopt/cuopt-user-rules"><img src="https://agentmods.dev/badge/skills/nvidia/cuopt/cuopt-user-rules.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 5 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 Agent Snooping · line 128 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
- medium Excessive Agency · line 189 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 201 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 Privilege Escalation · line 202 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.
- low Privilege Escalation · line 180 Skill requests more permissions than appear necessary for its stated functionality. Review if elevated access is justified.Fix: Request only the minimum permissions required. Document why each permission is needed. Remove broad permissions like '*' or 'all'.
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 | $0.00042 | $0.02114 |
| Opus 5.5 | $0.00017 | $0.00846 |
| Sonnet 5.5 | $0.00008 | $0.00423 |
| Haiku 4.5 | $0.00004 | $0.00211 |
Grade B, and why
cuopt-user-rules scanned grade B with 2 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 9d 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.
- Use `sudo` or run as root Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
| REST Server | `cuopt-server` or Docker | `curl /cuopt/health` | How it starts
The opening of the file, as written. The whole thing — 234 lines — stays where its author put it; the contents beside it link to each section on GitHub.
cuOpt User Rules
Read this when helping someone use cuOpt (calling the SDK, installing, deploying the server). For modifying cuOpt itself, switch to cuopt-developer.
Ask Before Assuming
Always clarify ambiguous requirements before implementing:
- What language/interface?
- What problem type?
- What constraints matter?
- What output format?
Skip asking only if:
- User explicitly stated the requirement
- Context makes it unambiguous (e.g., user shows Python code)
Handle Incomplete Questions
If a question seems partial or incomplete, ask follow-up questions:
- "Could you tell me more about [missing detail]?"
- "What specifically would you like to achieve with this?"
- "Are there any constraints or requirements I should know about?"
Common missing information to probe for:
- Problem size (number of vehicles, locations, variables, constraints)
- Specific constraints (time windows, capacities, precedence)
- Performance requirements (time limits, solution quality)
- Integration context (existing codebase, deployment environment)
Don't guess — ask. A brief clarifying question saves time vs. solving the wrong problem.
Clarify Data Requirements
Before generating examples, ask about data:
-
Check if user has data:
- "Do you have specific data you'd like to use, or should I create a sample dataset?"
- "Can you share the format of your input data?"
-
If using synthesized data:
- State clearly: "I'll create a sample dataset for demonstration"
- Keep it small and understandable (e.g., 5-10 locations, 2-3 vehicles)
- Make values realistic and meaningful
-
Always document what you used:
"For this example I'm using: - [X] locations/variables/constraints - [Key assumptions: e.g., all vehicles start at depot, 8-hour shifts] - [Data source: synthesized / user-provided / from docs]" -
State assumptions explicitly:
- "I'm assuming [X] — let me know if this differs from your scenario"
- List any default values or simplifications made
What ships with it
4 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.
- 9d ago Changed 66af17dd90cb
- 1mo ago First seen · 234 lines · 42 tokens per session scan B 6de15c9b3437
cuopt-user-rules is a skill published in the GitHub repository NVIDIA/cuopt (1,074 stars, last pushed today), licensed Apache-2.0. It adds 42 tokens to every session and 2,114 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it B with 2 findings (asks for root, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
pytorch-profile-analysis
Analyze single-file PyTorch/Kineto Chrome trace .json(.gz) files using the VeloQ CLI. Use for CPU/CUDA/kernel correlation, ProfilerStep/annotation slicing, memory/shape grouping, and single-trace NCCL evidence.
iket-profiling
Profile inside a CuTe DSL (cutlass.cute) kernel with IKET (In-Kernel Event Tracing) and the run-iket profiler. Use when developing or tuning a CuTe DSL kernel and you need per-warp timelines of kernel phases (setup, mainloop, epilogue), producer/consumer (TMA/MMA) activity, or time spent in pipeline and mbarrier…
nsys-profile-analysis
Analyze Nsight Systems .nsys-rep or pqtdir/ timeline traces using the VeloQ CLI. Use for GPU idle gaps, launch causes, CPU/GPU correlation, NVTX, CUDA graphs, metrics, sampling, and overlap/concurrency.
optimization-or
Use this Skill for operations research and optimization: LP/QP/MILP with cvxpy and OR-Tools, convex relaxation, sensitivity analysis, and Gurobi/GLPK solver interface.
sglang-diffusion-cache-dit
Workflow for upgrading/integrating cache-dit in SGLang diffusion (multimodalgen): DBCache, DMD calibrator, TaylorSeer, SVDQuant DQ; porting upstream PRs and resolving conflicts against the per-request knob system; adding new cache knobs; building the sglang generate CLI test matrix; precision validation (PSNR / log…
ml-training-recipes
Battle-tested PyTorch training recipes for all domains — LLMs, vision, diffusion, medical imaging, protein/drug discovery, spatial omics, genomics. Covers training loops, optimizer selection (AdamW, Muon), LR scheduling, mixed precision, debugging, and systematic experimentation. Use when training or fine-tuning…