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 5.5 | $0.00038 | $0.00346 |
| Sonnet 5.5 | $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 2mo 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.
- 2mo 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 2mo ago), licensed Apache-2.0. It adds 95 tokens to every session and 866 once invoked, about $0.0004 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.
threejs-web-designer compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| threejs-web-designerqfoldit/Protein-Design-MCP | Skill | 1 | 2mo ago | Apache-2.0 | A | 95 | Claude Code |
| imagegenopenai/codex | Skill | 134k | today | Apache-2.0 | A | 113 | Codex |
| playwright-climicrosoft/playwright | Skill | 99k | today | Apache-2.0 | A | 19 | Claude Code |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | today | MIT | A | 200 | Claude Code, Codex |
| systematic-debuggingobra/superpowers | Skill | 314k | 3d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 95 | Claude Code |
| next-partial-prefetching-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 103 | Claude Code |