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 calesthio/generative-media-skills --skill threejs-scene-compositiongit clone --depth 1 https://github.com/calesthio/generative-media-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/calesthio/generative-media-skills/threejs-scene-composition)<a href="https://agentmods.dev/skills/calesthio/generative-media-skills/threejs-scene-composition"><img src="https://agentmods.dev/badge/skills/calesthio/generative-media-skills/threejs-scene-composition/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/calesthio/generative-media-skills/threejs-scene-composition"><img src="https://agentmods.dev/badge/skills/calesthio/generative-media-skills/threejs-scene-composition.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00085 | $0.04144 |
| Opus 5 | $0.00043 | $0.02072 |
| Sonnet 5 | $0.00017 | $0.00829 |
| Haiku 4.5 | $0.00009 | $0.00414 |
Grade A, and why
threejs-scene-composition 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 9d 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 — 331 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Three.js scene composition
Use Three.js when depth, camera, lighting, material response, geometry, or spatial animation carries the media idea and a browser-rendered scene is an appropriate production surface. This skill begins after asset requirements and creative intent are known and ends with a reproducible rendered scene package.
It does not teach mesh modeling, retopology, rig authoring, physics simulation, WebXR product design, or game logic. It may consume approved glTF assets, animation clips, textures, environment maps, fonts, data, and audio cues produced elsewhere.
Evidence stance
- Documented fact means behavior specified by official Three.js, Khronos, WebGL, or W3C sources.
- Production heuristic means a useful starting point that must be tested on the actual scene and delivery hardware.
- Empirical observation means a result measured from the scene, frame output, browser, GPU, or encoded deliverable.
Three.js releases frequently and examples/addons may change paths or APIs. Facts and links were checked 2026-07-12. Pin and record the installed revision, check migration notes, and test the exact target browser and renderer before delivery. WebGPU support and renderer parity are especially volatile.
Decide whether Three.js is the right renderer
Use Three.js when the deliverable needs:
- a real 3D camera, parallax, depth, occlusion, or spatial continuity;
- glTF scene or product assets rendered with browser PBR materials;
- skeletal, morph-target, keyframe, or procedural 3D animation;
- custom shaders, particles, instancing, or post-processing;
- deterministic frame capture from a browser-based composition system;
- one scene adapted across aspect ratios or camera framings.
Prefer another approach when:
- a 2D compositor can express the result more clearly and cheaply;
- the job is to prepare a mesh for downstream engines rather than compose a shot;
- exact offline path tracing, feature-film simulation, or DCC-native handoff is required;
- a static product render already exists and no 3D revision value remains;
- the target depends on browser interactions rather than a rendered media deliverable.
What ships with it
1 file beside SKILL.md 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.
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.
- 9d ago First seen · 331 lines · 85 tokens per session scan A 07e5044adfd3
threejs-scene-composition is a skill published in the GitHub repository calesthio/generative-media-skills (170 stars, last pushed 2mo ago), licensed MIT. It adds 85 tokens to every session and 4,144 once invoked, about $0.0004 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 2026-09-03.
Other skills, from other repositories
widgets
Render rich HTML inline via tags with theme-aware styling. Load when emitting an mcwidget so the iframe inherits the dashboard theme instead of clashing with light / dark / custom palettes.
web-verify
Look at your OWN front-end change before claiming it works -- navigate the loopback URL of a dev server or pod you started, screenshot the surface you changed, read the image to judge it, and embed it in chat. Three capture backends: playwright-cli (the session the dashboard Browser panel shows), the agent-browser CLI…
web-design
Penguin visual language for generated web pages and app UIs — GitHub-style simplicity with a single blue accent, light and pure-black dark themes, design tokens, component and chat-interface recipes, plus an opt-in warm paper editorial theme.
frontend-design-workflow
Workflow for frontend features, visual changes, and product design changes. Present mockup options before writing code, build against the project's design system, capture the right evidence type (screenshots vs video), and run a new-user usability review before finalizing. Use when building or changing UI, styling…
research-to-website
Build informative websites from research reports. Transforms research output (markdown or typst/pdf) into polished, domain-appropriate websites with professional design, data visualization, and scroll-based animations. Triggers on research-to-website tasks, report visualization, or when converting research into web…
building-ui
Complete guide for building beautiful apps with Expo Router. Covers fundamentals, styling, components, navigation, animations, patterns, and native tabs.