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 hoangatg/ai-agent-toolkit --skill 3d-web-experiencegit clone --depth 1 https://github.com/hoangatg/ai-agent-toolkitWrote 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/hoangatg/ai-agent-toolkit/3d-web-experience)<a href="https://agentmods.dev/skills/hoangatg/ai-agent-toolkit/3d-web-experience"><img src="https://agentmods.dev/badge/skills/hoangatg/ai-agent-toolkit/3d-web-experience/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/hoangatg/ai-agent-toolkit/3d-web-experience"><img src="https://agentmods.dev/badge/skills/hoangatg/ai-agent-toolkit/3d-web-experience.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 | $0.00044 | $0.00711 |
| Opus 5 | $0.00022 | $0.00356 |
| Sonnet 5 | $0.00009 | $0.00142 |
| Haiku 4.5 | $0.00004 | $0.00071 |
Grade A, and why
3d-web-experience 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 8d 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 — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.
3D Web Experience
Make the web dimensional. Create experiences, not just pages.
1. Technology Selection
| Technology | Best For |
|---|---|
| Three.js | Full control, vanilla JS |
| React Three Fiber | React ecosystem, declarative |
| Babylon.js | Game-like experiences |
| A-Frame | Quick prototypes, VR/AR |
| Spline | Design-first, no-code |
2. React Three Fiber Architecture
Component Structure
<Canvas>
<Scene>
<Lighting />
<Camera />
<Models />
<Effects />
</Scene>
</Canvas>
Key Libraries
| Library | Purpose |
|---|---|
| @react-three/fiber | React renderer for Three.js |
| @react-three/drei | Helpers, controls, abstractions |
| @react-three/postprocessing | Visual effects |
| @react-three/rapier | Physics engine |
| leva | Debug controls/GUI |
3. Performance Optimization
| Technique | Impact |
|---|---|
| Instancing | Render 1000s of same geometry |
| LOD (Level of Detail) | Reduce geometry at distance |
| Texture compression | KTX2, basis textures |
| Frustum culling | Only render visible objects |
| Object pooling | Reuse instead of create/destroy |
| Web Workers | Offload heavy computation |
Performance Budget
| Metric | Target |
|---|---|
| Draw calls | < 100 |
| Triangles | < 500K (mobile), < 2M (desktop) |
| Texture memory | < 100MB |
| Frame rate | 60fps (desktop), 30fps (mobile) |
4. 3D Asset Pipeline
| Format | Use Case |
|---|---|
| glTF/GLB | Standard, web-optimized |
| DRACO | Compressed geometry |
| KTX2 | Compressed textures |
| HDR/EXR | Environment maps |
5. Common Use Cases
| Use Case | Key Techniques |
|---|---|
| Product configurator | Materials, camera, interaction |
| Data visualization | Instancing, animation |
| Portfolio/landing | Scroll-driven animation |
| Game | Physics, collision, state |
| AR/VR | WebXR, spatial interaction |
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.
- 8d ago First seen · 109 lines · 44 tokens per session scan A 1cb5601148ee
3d-web-experience is a skill published in the GitHub repository hoangatg/ai-agent-toolkit (1 stars, last pushed 5mo ago), licensed MIT. It adds 44 tokens to every session and 711 once invoked, about $0.0002 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
ux-ui
Use this agent when you need to design, audit, migrate, rewire, or rewrite UX/UI.
refactoring-ui
Apply UI design principles from Refactoring UI by Adam Wathan & Steve Schoger. Covers visual hierarchy (size, weight, color, spacing), layout systems (spacing scales, grids), typography (type scales, line-height, alignment), color (HSL palettes, shade systems, accessible contrast), depth (shadow elevation, overlap)…
frontend-design
Guidance for distinctive, intentional visual design when building new UI or reshaping an existing one. Helps with aesthetic direction, typography, and making choices that don't read as templated defaults.
frontend-patterns
Frontend development patterns for React, Next.js, state management, performance optimization, and UI best practices.
coding-standards
Universal coding standards, best practices, and patterns for TypeScript, JavaScript, React, and Node.js development.
design-review
Designer's eye QA: finds visual inconsistency, spacing issues, hierarchy problems, AI slop patterns, and slow interactions — then fixes them. Iteratively fixes issues in source code, committing each fix atomically and re-verifying with before/after screenshots. For plan-mode design review (before implementation), use…