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 agent-web-modernizationgit 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/agent-web-modernization)<a href="https://agentmods.dev/skills/nvidia/elements/agent-web-modernization"><img src="https://agentmods.dev/badge/skills/nvidia/elements/agent-web-modernization/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/agent-web-modernization"><img src="https://agentmods.dev/badge/skills/nvidia/elements/agent-web-modernization.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00072 | $0.02459 |
| Opus 5.5 | $0.00029 | $0.00984 |
| Sonnet 5.5 | $0.00014 | $0.00492 |
| Haiku 4.5 | $0.00007 | $0.00246 |
Grade A, and why
agent-web-modernization 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 2d 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 — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Web Modernization
Fix one browser modernization issue and produce at most one focused pull request per run. Find compatibility code that no longer serves its purpose, or a native browser API that can replace a custom implementation with a concrete maintenance benefit. Carry the selected improvement through implementation, validation, and a pull request.
The browser target is the Chromium build installed by the Playwright version pinned in the repository dependencies. Resolve that version and its Chromium build during each run from the repository's dependency declarations, lockfile, and installed Playwright package. Use this target for compatibility decisions and validation. Do not substitute system Chrome, the latest Chrome release, or a separately installed Chromium version, and do not embed fixed browser versions in this skill.
Invocation of this skill authorizes one validated pull request, never a direct default-branch change or an automatic merge.
Prepare the Run
- Read the root
AGENTS.mdand rungit status --short --branch. Preserve existing work. Start from a clean worktree; stop if the worktree has changes. - Fetch and prune
origin, resolve its current default branch, and base the investigation and eventual change on its latest commit. Do not assume the checkout contains recent fixes. - Verify GitHub access with
gh auth statusbefore relying on GitHub metadata or preparing a pull request. Prefer available GitHub tools for metadata, withghas a fallback. - Find local
topic/web-modernization/*and remoteorigin/topic/web-modernization/*branches not merged into the current remote default branch, including unpublished local branches retained after a publishing failure. Stop when either exists and report its branch and associated PR, if any. - Search open PRs for browser modernization work and the affected area. Recheck the selected candidate before publishing to avoid duplicating another fix.
Read the target project's DEVELOPMENT.md, package manifest, and nearer agent instructions before analyzing or running its commands. Follow the required guidelines for any files that may change.
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.
- 2d ago First seen · 104 lines · 72 tokens per session scan A a635ece7a075
agent-web-modernization is a skill published in the GitHub repository NVIDIA/elements (113 stars, last pushed yesterday), licensed Apache-2.0. It adds 72 tokens to every session and 2,459 once invoked, about $0.0003 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 2026-11-04.
agent-web-modernization compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| agent-web-modernizationNVIDIA/elements | Skill | 113 | yesterday | Apache-2.0 | A | 72 | Claude Code, Codex |
| vue-application-structuresoulcodex/agentic | Skill | 10 | 7d ago | MIT | A | 63 | Claude Code, Codex |
| react-application-structuresoulcodex/agentic | Skill | 10 | 7d ago | MIT | A | 63 | Claude Code, Codex |
| vue-component-designsoulcodex/agentic | Skill | 10 | 7d ago | MIT | A | 70 | Claude Code, Codex |
| next-application-structuresoulcodex/agentic | Skill | 10 | 7d ago | MIT | A | 64 | Claude Code, Codex |
| react-component-designsoulcodex/agentic | Skill | 10 | 7d ago | MIT | A | 56 | Claude Code, Codex |
| compiler-commitreact/react | Skill | 252k | yesterday | MIT | A | 42 | Claude Code |