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 Impertio-Studio/Three.js-Claude-Skill-Package --skill threejs-impl-audiogit clone --depth 1 https://github.com/Impertio-Studio/Three.js-Claude-Skill-PackageWrote 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/impertio-studio/three.js-claude-skill-package/threejs-impl-audio)<a href="https://agentmods.dev/skills/impertio-studio/three.js-claude-skill-package/threejs-impl-audio"><img src="https://agentmods.dev/badge/skills/impertio-studio/three.js-claude-skill-package/threejs-impl-audio.svg" alt="Measured on agentmods" 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 | $0.00111 | $0.02162 |
| Opus 5 | $0.00056 | $0.01081 |
| Sonnet 5 | $0.00022 | $0.00432 |
| Haiku 4.5 | $0.00011 | $0.00216 |
Grade A, and why
threejs-impl-audio 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 7d 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 — 266 lines — stays where its author put it; the contents beside it link to each section on GitHub.
threejs-impl-audio
Quick Reference
Class Hierarchy
EventDispatcher
└── Object3D
├── AudioListener (receiver — attach to camera)
├── Audio (non-positional — background music, UI sounds)
└── PositionalAudio (3D spatial — attached to scene objects)
Supporting classes:
AudioLoader— loads audio files intoAudioBufferAudioAnalyser— real-time frequency analysis for visualization
Architecture Overview
| Component | Role | Attach To |
|---|---|---|
AudioListener |
Virtual ear (Web Audio API destination) | Camera (ALWAYS) |
Audio |
Non-positional sound (same volume everywhere) | Any Object3D or scene |
PositionalAudio |
3D spatial sound (volume depends on distance) | Mesh or Object3D in scene |
AudioLoader |
Async audio file loader | N/A (utility) |
AudioAnalyser |
FFT frequency data extractor | Wraps an Audio instance |
Critical Warnings
NEVER call sound.play() without first ensuring the AudioContext is resumed after user interaction. Modern browsers ALWAYS suspend the AudioContext until a user gesture (click, tap, keypress) occurs.
NEVER create more than one AudioListener per scene. Multiple listeners produce undefined spatialization behavior.
NEVER set autoplay = true and expect playback without user interaction. The browser WILL block it silently.
ALWAYS attach the AudioListener to the camera. If attached to another object, spatial audio calculations use the wrong reference position.
ALWAYS call listener.context.resume() inside a user interaction handler before playing any audio.
NEVER forget to handle the onError callback in AudioLoader.load(). Missing audio files fail silently without error handling.
AudioListener Setup
The AudioListener is the scene's virtual microphone. It wraps the Web Audio API's AudioContext and AudioDestinationNode.
import * as THREE from 'three';
const listener = new THREE.AudioListener();
camera.add( listener ); // ALWAYS add to camera
What ships with it
3 files 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.
- 7d ago First seen · 266 lines · 111 tokens per session scan A fbb2766f9f17
threejs-impl-audio is a skill published in the GitHub repository Impertio-Studio/Three.js-Claude-Skill-Package (11 stars, last pushed 2mo ago), licensed MIT. It adds 111 tokens to every session and 2,162 once invoked, about $0.0006 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 2026-08-30.
Other skills, from other repositories
wechat-article-writer
A Chinese-language content-creation workflow for public-account and social-media writing. It supports article drafting, cover images, illustrations, process diagrams, style analysis, and adapting writing to selected styles.
remotion-upgrade
Upgrade Remotion, and related packages.
gemini-watermark-remover
Remove visible Gemini image watermarks from local image files by calling the project's CLI. Use when the user wants an agent to clean one or more local Gemini-generated images and save de-watermarked output files.
infographic-creator
Create beautiful infographics based on given text content. Use when users request to create infographics.
baocut
BaoCut-only operator for the installed bcut CLI and .bcut projects. Implicitly trigger only when the request explicitly names BaoCut or bcut, targets a .bcut project or BaoCut Subtitle Studio, or continues a BaoCut workflow already established in the conversation. Do not trigger solely for generic audio or video…
nano-banana
Generate professional presentation slides and high-quality illustrations using Gemini image generation API (Nano Banana 2), with interactive browser-based review and iterative editing. Full workflow: content planning conversation → slidesplan.json → batch image generation → review with feedback → targeted slide…