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-startersgit 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-starters)<a href="https://agentmods.dev/skills/nvidia/elements/agent-starters"><img src="https://agentmods.dev/badge/skills/nvidia/elements/agent-starters/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-starters"><img src="https://agentmods.dev/badge/skills/nvidia/elements/agent-starters.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 | $0.00047 | $0.01893 |
| Opus 5.5 | $0.00019 | $0.00757 |
| Sonnet 5.5 | $0.00009 | $0.00379 |
| Haiku 4.5 | $0.00005 | $0.00189 |
Grade A, and why
agent-starters 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 22d 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 — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Starters
Verify the real consumer path for every starter exposed by the stable production Elements CLI. A passing local repository build does not substitute for this production check.
Hard Constraints
- Run the production verifier before editing. Never substitute a repository build, local archive, workspace package, or unpublished CLI for that observation.
- Repair at most one actionable root cause and open at most one pull request per run. Report every other failure without widening the patch.
- Keep production evidence immutable. Record local-source checks separately as candidate validation.
- Do not change generated production projects, public APIs, unrelated packages, visual baselines, thresholds, or assertions to make verification pass.
- Full local CI must pass before opening a pull request. Never dismiss a failure as unrelated.
- Stop when an unmerged
topic/starters/*branch exists on the remote. This keeps one starter-agent repair in flight at a time.
Prepare the run
- Read the root
AGENTS.md, rungit status --short --branch, and preserve existing work. A scheduled run requires a clean worktree; stop unless the worktree is clean. - Fetch and prune
origin, resolve the current default branch, and start from its latest commit. Never push directly to the default branch. - List remote branches that match
origin/topic/starters/*and are not merged intoorigin/<default-branch>. Stop when one exists and report its branch and pull request, if any. - Verify GitHub access with
gh auth statusbefore relying on GitHub metadata or preparing a pull request.
Run production verification first
From the repository root, run:
mise exec -- node .agents/skills/agent-starters/scripts/index.js
The script owns CLI installation and provenance, production inventory discovery, project creation, dependency verification, starter CI or build checks, cache isolation, timeouts, evidence, cleanup, and result formatting. Node starters run pnpm run ci when the generated project exposes that script, and pnpm run build otherwise. External toolchain starters run their configured install and build commands. Do not duplicate or override its commands, starter list, expectations, or cache configuration in this skill.
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.
- 22d ago Changed 128d720307c6
- 1mo ago First seen · 121 lines · 47 tokens per session scan A a007bc335f25
agent-starters is a skill published in the GitHub repository NVIDIA/elements (102 stars, last pushed today), licensed Apache-2.0. It adds 47 tokens to every session and 1,893 once invoked, about $0.0002 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 2026-09-19.
Other skills, from other repositories
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.
compiler-commit
Use when you want to verify compiler changes and commit with the correct convention. Runs tests, lint, and format, then commits with the [compiler] or [rust-compiler] prefix.
release-safety
Release safety rules. INVOKE WHEN: yarn release, npm publish, release canary, release packages, publishing, skip checks, skip tests. NEVER skip checks or tests without explicit permission.
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.
pi-package-sandbox-test
Use when verifying that published Pi packages install and load for normal users, including pi.dev package compatibility checks, release validation, Daytona sandbox tests, and package installability audits.
vue-application-structure
Establishes or reviews the directory layout, component conventions, composable design, Pinia store structure, and Vue Router configuration for a Vue 3 TypeScript application. Invoked when the user asks to structure a Vue app, set up the project layout, or review Vue architecture.