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 RadOrigin-LLC/RAD-Claude-Skills --skill chrome-ext-ui-reactgit clone --depth 1 https://github.com/RadOrigin-LLC/RAD-Claude-SkillsWrote 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/radorigin-llc/rad-claude-skills/chrome-ext-ui-react)<a href="https://agentmods.dev/skills/radorigin-llc/rad-claude-skills/chrome-ext-ui-react"><img src="https://agentmods.dev/badge/skills/radorigin-llc/rad-claude-skills/chrome-ext-ui-react/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/radorigin-llc/rad-claude-skills/chrome-ext-ui-react"><img src="https://agentmods.dev/badge/skills/radorigin-llc/rad-claude-skills/chrome-ext-ui-react.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 | $0.00114 | $0.01133 |
| Opus 5.5 | $0.00046 | $0.00453 |
| Sonnet 5.5 | $0.00023 | $0.00227 |
| Haiku 4.5 | $0.00011 | $0.00113 |
Grade A, and why
chrome-ext-ui-react 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 — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.
React UI in Chrome Extensions
React works in extension popups, side panels, options pages, and content script injected UIs. Each context has unique constraints. The core challenges are: state dies with popup close, Shadow DOM is required for content script UI, and portaled components break in Shadow DOM.
State Management Rule
Extension popups render from scratch on every toolbar click and die when they lose focus. Side panels persist longer but still need storage-backed state.
Never rely on React useState alone for persistent data. Always back state with chrome.storage:
function useChromeState<T>(key: string, defaultValue: T) {
const [value, setValue] = useState<T>(defaultValue);
const [loading, setLoading] = useState(true);
useEffect(() => {
chrome.storage.local.get({ [key]: defaultValue }).then((result) => {
setValue(result[key]);
setLoading(false);
});
const listener = (changes: Record<string, chrome.storage.StorageChange>, area: string) => {
if (area === 'local' && key in changes) setValue(changes[key].newValue);
};
chrome.storage.onChanged.addListener(listener);
return () => chrome.storage.onChanged.removeListener(listener);
}, [key]);
const set = async (newValue: T) => {
setValue(newValue);
await chrome.storage.local.set({ [key]: newValue });
};
return [value, set, loading] as const;
}
Shadow DOM for Content Script UI
Inject extension UI into web pages using Shadow DOM to prevent CSS pollution:
export default defineContentScript({
matches: ['<all_urls>'],
cssInjectionMode: 'ui',
main(ctx) {
const ui = createShadowRootUi(ctx, {
name: 'my-extension',
position: 'inline',
onMount(container) {
const root = createRoot(container);
root.render(<App />);
return root;
},
onRemove(root) { root.unmount(); },
});
ui.mount();
},
});
Fix Portaled Components
React UI libraries (Radix UI, Headless UI, Shadcn) portal modals, dialogs, and tooltips to document.body. In content scripts, this forces them outside the Shadow DOM, stripping all styles. Configure the portal container:
What ships with it
1 file 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.
- 1mo ago First seen · 132 lines · 114 tokens per session scan A 008d1f2a63d1
chrome-ext-ui-react is a skill published in the GitHub repository RadOrigin-LLC/RAD-Claude-Skills (5 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 114 tokens to every session and 1,133 once invoked, about $0.0005 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 2026-08-31.
Other skills, from other repositories
app-docs
Generate complete user documentation for a web app with screenshots. Browses the app via browser automation, screenshots every screen, and produces a structured user guide with step-by-step instructions, annotated screenshots, workflow diagrams, and reference tables. Supports quick (key screens), standard (all pages)…
responsiveness-check
Test website responsiveness across viewport widths using browser automation. Resizes a single session through breakpoints, screenshots each width, and detects layout transitions (column changes, nav switches, overflow). Produces comparison reports showing exactly where layouts break. Trigger with 'responsiveness…
web-quality-audit
Run an evidence-led web quality audit covering performance, accessibility, SEO, best practices, and agentic browsing. Use when asked to "audit my site", "review web quality", "run lighthouse audit", "check page quality", or "optimize my website".
chrome-extension-wxt
Build Chrome extensions with the WXT framework and TypeScript, React, Vue, or Svelte. Use when creating browser extensions or cross-browser add-ons. Triggers on "chrome extension", "browser extension", WXT, manifest v3, or wxt.config.ts.
aws-spa-deploy
Use this skill whenever the user is deploying a React/Vite single-page app to AWS, or mentions Amplify Hosting, amplify.yml, CDK, Lambda function URLs, or wiring up Lambda + API Gateway for a frontend. Covers Amplify hosting (SPA rewrites, build cache, Node version, security headers), custom domains and certificates…
ui-test
Runs UI tests described in plain English by driving real Chrome via the Claude-in-Chrome extension. Covers end-to-end flows (clicks, forms, assertions), visual checks (screenshot + optional baseline diff), accessibility (axe-core), performance (Web Vitals + light Lighthouse-style metrics), and an interactive --debug…