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.
git clone --depth 1 https://github.com/alevizio/globestudioWrote 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/plugins/alevizio/globestudio/gemini-extension)<a href="https://agentmods.dev/plugins/alevizio/globestudio/gemini-extension"><img src="https://agentmods.dev/badge/plugins/alevizio/globestudio/gemini-extension/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/plugins/alevizio/globestudio/gemini-extension"><img src="https://agentmods.dev/badge/plugins/alevizio/globestudio/gemini-extension.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
globestudio 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 5d 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.
What it actually says
{
"name": "globestudio",
"version": "1.4.0",
"description": "Dotted world maps and animated 3D globes from globestudio.app. Bundles the globestudio agent skill, which teaches Gemini CLI to add, edit and embed them, and the hosted Globestudio MCP server.",
"mcpServers": {
"globestudio": {
"httpUrl": "https://globestudio.app/mcp"
}
}
}
What ships with it
43 files beside gemini-extension.json 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.
- examples/conference-badge/config.json 913 B
- examples/conference-badge/README.md 2.8 KB
- examples/country-highlight/index.html 4.4 KB
- examples/country-highlight/README.md 2.7 KB
- examples/embed-snippet/index.html 4.5 KB
- examples/embed-snippet/README.md 3.6 KB
- examples/framer-component/GlobestudioGlobe.tsx 6.4 KB
- examples/framer-component/README.md 3.5 KB
- examples/funding-map-story/index.html 7.3 KB
- examples/funding-map-story/README.md 2.7 KB
- examples/hero-globe/index.html 3.6 KB
- examples/hero-globe/README.md 3.0 KB
- examples/react-component/Globestudio.tsx 7.3 KB
- examples/react-component/README.md 4.3 KB
- examples/README.md 4.0 KB
- examples/shader-presets-showcase/index.html 5.5 KB
- examples/shader-presets-showcase/README.md 1.6 KB
- examples/starter-react/.gitignore 36 B
- examples/starter-react/index.html 295 B
- examples/starter-react/package.json 398 B
- examples/starter-react/README.md 2.8 KB
- examples/starter-react/src/App.jsx 1.1 KB
- examples/starter-react/src/main.jsx 239 B
- examples/starter-react/src/styles.css 845 B
- examples/starter-react/vite.config.js 136 B runs code
- examples/svg-country-pack/README.md 3.6 KB
- scripts/build-openai-plugin.sh 1.8 KB runs code
- scripts/capture-og-canvas.js 18 KB runs code
- scripts/capture-thumbnails.js 4.1 KB runs code
- scripts/check-bundle-size.js 13 KB runs code
- scripts/generate-changelog-rss.js 4.7 KB runs code
- scripts/generate-look-thumbs.js 4.8 KB runs code
- scripts/generate-og-animated.js 4.3 KB runs code
- scripts/generate-og-default.js 31 KB runs code
- scripts/generate-sitemap.js 5.6 KB runs code
- scripts/generate-skill-references.js 1.4 KB runs code
- scripts/prerender.js 18 KB runs code
- scripts/simplify-cities.js 1.6 KB runs code
- scripts/simplify-rivers.js 2.0 KB runs code
- scripts/site-facts.js 1.2 KB runs code
- scripts/skill-references.js 34 KB runs code
- scripts/static-bodies.jsx 4.7 KB
- scripts/strip-css-comments.js 1.5 KB runs code
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.
- 5d ago Changed 7c29a8308f5c
- 10d ago First seen · 11 lines scan A fa73078c706f
globestudio is a plugin published in the GitHub repository alevizio/globestudio (19 stars, last pushed 5d ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 2026-10-05.
Other plugins, from other repositories
arena
Build interfaces with Arena, a token-driven design system: design tokens, React and Angular component libraries, a shared Tailwind layer, guidelines, and a style plugin any project can replace. It carries the design language and not the skin, so any project brings its own palette and fonts.
ui-ux-design-pro
World-class, one-stop design intelligence for coding agents across two tracks: interfaces (web/apps, components, design systems, the modern React+Tailwind+shadcn stack) AND visual/marketing design (presentations & decks, social carousels & posts, ads, A4/A3 posters, flyers, business cards, event banners…
document-design-system
A design system for documents: evidence-led analytical reports, diagrams, charts, decks, and thirty-four prose presets across eleven reading patterns — composed from a pattern's modules when no preset fits — plus guided brand theming, all sharing one semantic token contract. Writing lands as Markdown by default…
humane
21 design-method skills for people and agents: evidence, prototypes, tokens, typography, semantic interactions, scroll stories, optional sound, reviews, and framework adaptation.
subframe
Design and build UIs with Subframe. Create pixel-perfect React + Tailwind pages using your design system, explore design variations, and implement with business logic.
dotclaude-design
A design/UX audit layer for Claude Code. /dotclaude:design elicits your design north-star; ux, flow, pages, a11y, interaction, and design-token audits grade every screen against it, plus a product-designer IA/flow spec.