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 vivekkachhadiyatech/skills --skill landing-3dgit clone --depth 1 https://github.com/vivekkachhadiyatech/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/vivekkachhadiyatech/skills/landing-3d)<a href="https://agentmods.dev/skills/vivekkachhadiyatech/skills/landing-3d"><img src="https://agentmods.dev/badge/skills/vivekkachhadiyatech/skills/landing-3d/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/vivekkachhadiyatech/skills/landing-3d"><img src="https://agentmods.dev/badge/skills/vivekkachhadiyatech/skills/landing-3d.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 | $0.00204 | $0.03891 |
| Opus 5.5 | $0.00082 | $0.01556 |
| Sonnet 5.5 | $0.00041 | $0.00778 |
| Haiku 4.5 | $0.00020 | $0.00389 |
Grade A, and why
landing-3d scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
**The signature shader beat (flagship briefs).** Once the direction wants glass/atmosphere/dense particles/a lit world, build it from `../knowledge/shader-craft.md` (dispersion glass, FBM domain-warp fog, GPGPU particles How it starts
The opening of the file, as written. The whole thing — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Landing 3D
Build a real-time 3D/WebGL scroll landing page. Knowledge lives in ../knowledge/ — do not answer from memory. Read three-3d-webgl.md (reliability: init, fallback, perf, dispose, the self-diagnosing gate) AND three-3d-craft.md (scene craft: bloom/lighting/material/motion discipline, the ANTI-TROPE list, concept-first grounding, references/libraries). For a flagship/cinematic brief also read shader-craft.md (hand-GLSL recipes — dispersion glass, FBM fog, GPGPU particles, baked lighting, cinematic post; the highest-leverage premium move, made safe via LYGIA includes + real-GL compile) and asset-pipeline.md (bespoke/generated visual as the default hero; GLB+Draco+KTX loading; stock reads generic). Reliability makes it run; craft makes it not look generic — the recurring miss is engineering-sound but mediocre-looking 3D. This is a specialization of landing-page; reuse its art-direction, reference-grounding, and gate discipline, and add the 3D-specific gates below.
Scope check first. Real-time 3D is expensive and fails on weak devices. Use this skill ONLY when the brief genuinely needs live 3D (a rotating/explorable object, a reactive particle field, generative geometry, a scroll-driven camera through a scene). If the effect is a fixed cinematic that could be a video, STOP — that is media-asset:generate (pre-rendered), not this. scroll-world-style pre-rendered scroll video is NOT this skill.
1. Zero-assumption intake gate
Do not emit until unambiguous. Ask (with a recommended default) if any is unknown:
- What is the 3D subject, concretely? (product mesh + source
.glb? procedural geometry? particle field?) A 3D page with no real subject is decoration — reject or downgrade tolanding-page. - Performance budget + audience devices? (desktop-first vs must-run-on-mid-mobile). This sets the DPR cap and whether the mobile fallback is poster-only.
- Asset: is there a
.glb/.gltfmodel (and its poly/texture budget), or is geometry generated in-code? - Motion appetite: idle auto-rotate only, or full scroll-driven camera/scrubbing?
- Brand/tokens: reuse existing (scan first) or net-new?
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 · 111 lines · 204 tokens per session scan A 3bafd5be8584
landing-3d is a skill published in the GitHub repository vivekkachhadiyatech/skills (2 stars, last pushed 3mo ago), licensed MIT. It adds 204 tokens to every session and 3,891 once invoked, about $0.0008 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…