cuopt-skill-evolution

A rule for updating the cuOpt skill instructions after solving a difficult or unusual problem. The update records useful lessons for future cuOpt work.

In plain words
What is it for?
Use it after non-trivial cuOpt work to check whether the instructions should include a new lesson or procedure.
Why use it?
It prevents the same solution or mistake from being rediscovered in later tasks.

Cursor rule for Codex

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.

agentmods
npx agentmods add rules/nvidia/cuopt/cuopt-skill-evolution
Clone the repo
git clone --depth 1 https://github.com/NVIDIA/cuopt

Made for: Codex.

Per session 65 This file is loaded in full into every session.
When invoked 65 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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.

ModelPer sessionOnce invoked
Fable 5 $0.00065 $0.00065
Opus 5 $0.00032 $0.00032
Sonnet 5 $0.00013 $0.00013
Haiku 4.5 $0.00006 $0.00006

Measured yesterday against content hash 781b25689721, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

cuopt-skill-evolution 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 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.

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/rules/cuopt-skill-evolution.mdc · 9 lines

What it actually says

Skill Evolution

After resolving a non-trivial problem, read and follow skills/cuopt-skill-evolution/SKILL.md to check whether the learning should be captured as a skill update.

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.

  1. yesterday First seen · 9 lines · 65 tokens per session scan A 781b25689721

Subscribe to this mod's changes

cuopt-skill-evolution is a cursor rule published in the GitHub repository NVIDIA/cuopt (1,032 stars, last pushed 3d ago), licensed Apache-2.0. It adds 65 tokens to every session, about $0.0003 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.