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 qfoldit/Protein-Design-MCP --skill threejs-web-designergit clone --depth 1 https://github.com/qfoldit/Protein-Design-MCPWrote 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/qfoldit/protein-design-mcp/threejs-web-designer)<a href="https://agentmods.dev/skills/qfoldit/protein-design-mcp/threejs-web-designer"><img src="https://agentmods.dev/badge/skills/qfoldit/protein-design-mcp/threejs-web-designer/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/qfoldit/protein-design-mcp/threejs-web-designer"><img src="https://agentmods.dev/badge/skills/qfoldit/protein-design-mcp/threejs-web-designer.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 | $0.00095 | $0.00866 |
| Opus 5 | $0.00048 | $0.00433 |
| Sonnet 5 | $0.00019 | $0.00173 |
| Haiku 4.5 | $0.00010 | $0.00087 |
Grade A, and why
threejs-web-designer 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 10d 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 — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.
threejs-web-designer
Status: community ecosystem, no single official skill. Neither Three.js's maintainers nor Vercel/Poimandres (React Three Fiber) publish one authoritative "the" Claude skill for this stack -- there is instead a crowded, actively-maintained community ecosystem (multiple independent skill repos covering R3F fundamentals, drei, physics via Rapier, shaders, performance). The core APIs referenced below (Canvas, useFrame, drei) are stable, well-documented public APIs, not claims about any specific skill's authority.
Stack
npm install three @react-three/fiber @react-three/drei
npm install -D @types/three
npm install @react-three/postprocessing # optional
npm install @react-three/xr # needed specifically for WebXR interactions
UAG -> R3F mapping
Baseline from game-designer/references/uag_schema.md: node type=mesh -> <mesh> + geometry/material JSX, type=light -> <pointLight>/<directionalLight>, parent_child -> React component nesting (children), physics_collision -> Rapier (@react-three/rapier) rigidbody/collider, on_grab/interactions -> @react-three/xr interaction hooks.
Core patterns (stable, standard R3F -- verify against current docs for anything beyond this)
import { Canvas, useFrame } from '@react-three/fiber'
function Node({ position, rotation }) {
const ref = useRef()
useFrame((state, delta) => {
// per-frame updates here; NEVER call setState inside useFrame -- causes
// unnecessary re-renders and defeats the point of the render loop
})
return (
<mesh ref={ref} position={position} rotation={rotation}>
<boxGeometry args={[1, 1, 1]} />
<meshStandardMaterial color="#6366f1" />
</mesh>
)
}
export default function Scene({ uag }) {
return (
<Canvas camera={{ position: [0, 0, 5], fov: 75 }} dpr={[1, 2]}>
{uag.nodes.filter(n => !n.parent_id).map(n => <Node key={n.id} {...n} />)}
</Canvas>
)
}
Workflow
- Confirm the UAG passed
game-designer/scripts/uag_validate.py. - Walk
nodesrespectingparent_idhierarchy as React component nesting (root nodes first). - Map
constraints/interactionsto Rapier/@react-three/xrper the table above; unmapped types get flagged, not silently dropped. - Performance: cap device pixel ratio (
dpr={[1,2]}), usedrei's<Instances>for repeated geometry (e.g. many identical procedural plants froml-systems), and dispose of geometries/materials on unmount -- GPU resources leak silently otherwise.
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.
- 10d ago First seen · 62 lines · 95 tokens per session scan A 13db88599e33
threejs-web-designer is a skill published in the GitHub repository qfoldit/Protein-Design-MCP (1 stars, last pushed 13d ago), licensed Apache-2.0. It adds 95 tokens to every session and 866 once invoked, about $0.0005 per session on Opus 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
visual-ralph
Visual Ralph orchestration for frontend UI from generated references, static references, or live URL targets, using $ralph with built-in visual verdict and pixel-diff evidence until the implementation matches and leaves a reproducible design system.
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
repro-admin
Reproduce an EmDash admin UI bug. Attach a container, start the demo dev server, drive the admin with agent-browser using the dev-bypass session, and capture the reproduction as screenshots plus a replayable transcript.
create-site
Creates a new Power Pages code site (SPA) using React, Angular, Vue, or Astro. Guides through the full process from initial concept to deployed site: requirements discovery, scaffolding, component planning, design, implementation, validation, and deployment. Use when the user wants to create, build, or scaffold a new…
prototype-web
A clickable, high-fidelity web product prototype with navigation, a hero section, feature cards, steps, social proof, and optional pricing. It is designed to resemble a finished landing page while remaining a prototype.
menu-transitions-rtl
Animate react-horizontal-scrolling-menu scrolling and build right-to-left menus: noPolyfill defaults to true since v8, so transitionDuration (default 500), a custom-easing-function transitionBehavior, and per-call ScrollOptions { duration, boundary } on scrollToItem/scrollNext/scrollPrev are silently ignored unless…