NVIDIA Elements is a design system and agent-oriented toolkit for building operational interfaces for AI/ML, robotics, and autonomous-vehicle software. Its CLI and MCP tools provide component APIs, design tokens, examples, imports, validation, and setup guidance across several web frameworks.
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/elements --skill authoring-benchmarksgit clone --depth 1 https://github.com/NVIDIA/elementsWrote 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/elements/authoring-benchmarks)<a href="https://agentmods.dev/skills/nvidia/elements/authoring-benchmarks"><img src="https://agentmods.dev/badge/skills/nvidia/elements/authoring-benchmarks/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/elements/authoring-benchmarks"><img src="https://agentmods.dev/badge/skills/nvidia/elements/authoring-benchmarks.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 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 Prompt Injection · line 23 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
- medium Prompt Injection · line 29 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
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 | $0.00105 | $0.02322 |
| Opus 5.5 | $0.00042 | $0.00929 |
| Sonnet 5.5 | $0.00021 | $0.00464 |
| Haiku 4.5 | $0.00011 | $0.00232 |
Grade A, and why
authoring-benchmarks 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.
How it starts
The opening of the file, as written. The whole thing — 215 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Authoring Benchmarks
Create browser benchmarks that answer a specific performance question. Browser behavior is the product behavior, so Chromium is the default runtime for component and utility benchmarks.
Required Context
Before changing benchmarks:
- Read the testing overview.
- Read the Bench section of the Vite internals documentation.
- Read the target project's
DEVELOPMENT.md. - Inspect the implementation, its unit tests, and the closest existing benchmark.
Use the guidance-build skill as well when adding or changing Wireit tasks. Use the audit-ci skill instead when measuring pnpm run ci, build orchestration, or the CI completion path.
Choose the Correct Performance Test
| Question | Tool |
|---|---|
| How fast is a repeatable function, DOM traversal, state synchronization, filter, or component update? | Browser benchmark (*.test.bench.ts) |
| How does a page load, score in Lighthouse, or consume network resources? | Lighthouse test (*.test.lighthouse.ts) |
| Did a visual rendering result change? | Visual test (*.test.visual.ts) |
| Which build or test task controls CI wall-clock time? | audit-ci workflow |
| Is behavior correct? | Unit, accessibility, SSR, or integration test |
Do not use an SSR benchmark as a substitute for browser lifecycle performance. SSR serialization and browser DOM work are different workloads.
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 · 215 lines · 105 tokens per session scan A 3ff39d519e05
authoring-benchmarks is a skill published in the GitHub repository NVIDIA/elements (102 stars, last pushed today), licensed Apache-2.0. It adds 105 tokens to every session and 2,322 once invoked, about $0.0004 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 2026-09-03.
Other skills, from other repositories
vue-component-testing
Applies the three-tier test taxonomy for Vue 3 applications: writes unit tests for composables and Pinia stores with Vitest, component tests for behaviour and user interactions with @testing-library/vue, and acceptance tests for full user flows with Playwright. Ensures tests focus on observable behaviour, not…
next-application-structure
Establishes or reviews directory layout, server/client boundaries, routing, data-fetching strategy, and testing structure for Next.js 14+ App Router TypeScript applications. Invoked when the user asks to structure a Next app, set App Router conventions, or review architecture for React parity.
authoring-data-quality-checks
Adds and runs data quality checks (dbt-test style assertions) on a project's warehouse tables and saved-query views, and HogQL catalog metrics: not-null, uniqueness, accepted values, referential integrity, row-count bounds, freshness, and custom HogQL. Metrics support custom SQL checks only. Use when asked to test a…
Cypress v14 Component Testing
Component testing patterns with Cypress v14 including React, Vue, and Angular component mounting, custom mount commands, interaction testing, visual snapshots, and integration with Vite and Webpack bundlers.
sfnext-testing
Write and run tests for a Storefront Next project: Vitest + React Testing Library unit tests, route loader/action tests (createLoaderArgs, createTestContext), Storybook stories with snapshot, interaction (play) and a11y runs, and a pointer to the CodeceptJS/Playwright e2e suite. Use for "write a test for this…
test-building-blocks
Test building block catalog — typed patterns for Storybook play-function tests, Vitest hook tests, Vitest unit tests, MSW handlers, and test data fixtures. Read the relevant rule file before writing or modifying any test, handler, or fixture. Covers: deciding which kind of test to write, authoring a new test from…