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 Bbeierle12/Skill-MCP-Claude --skill audio-reactivegit clone --depth 1 https://github.com/Bbeierle12/Skill-MCP-ClaudeWrote 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/bbeierle12/skill-mcp-claude/audio-reactive)<a href="https://agentmods.dev/skills/bbeierle12/skill-mcp-claude/audio-reactive"><img src="https://agentmods.dev/badge/skills/bbeierle12/skill-mcp-claude/audio-reactive/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/bbeierle12/skill-mcp-claude/audio-reactive"><img src="https://agentmods.dev/badge/skills/bbeierle12/skill-mcp-claude/audio-reactive.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 | $0.00046 | $0.03316 |
| Opus 5.5 | $0.00018 | $0.01326 |
| Sonnet 5.5 | $0.00009 | $0.00663 |
| Haiku 4.5 | $0.00005 | $0.00332 |
Grade A, and why
audio-reactive scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 555 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Audio Reactive Visuals
Connecting audio analysis to visual parameters.
Quick Start
import * as Tone from 'tone';
const analyser = new Tone.Analyser('fft', 256);
const player = new Tone.Player('/audio/music.mp3');
player.connect(analyser);
player.toDestination();
function animate() {
const fft = analyser.getValue();
const bass = (fft[2] + 100) / 100; // Normalize to 0-1
// Apply to visual
element.style.transform = `scale(${1 + bass * 0.2})`;
requestAnimationFrame(animate);
}
Core Patterns
Audio-to-Visual Mapping
class AudioReactiveMapper {
constructor(analyser) {
this.analyser = analyser;
this.smoothers = {
bass: new Smoother(0.85),
mid: new Smoother(0.9),
high: new Smoother(0.92)
};
}
// Get values optimized for different visual properties
getValues() {
const fft = this.analyser.getValue();
const len = fft.length;
// Extract and normalize bands
const rawBass = this.avgRange(fft, 0, len * 0.1);
const rawMid = this.avgRange(fft, len * 0.1, len * 0.5);
const rawHigh = this.avgRange(fft, len * 0.5, len);
return {
bass: this.smoothers.bass.update(this.normalize(rawBass)),
mid: this.smoothers.mid.update(this.normalize(rawMid)),
high: this.smoothers.high.update(this.normalize(rawHigh))
};
}
avgRange(data, start, end) {
let sum = 0;
for (let i = Math.floor(start); i < Math.floor(end); i++) {
sum += data[i];
}
return sum / (end - start);
}
normalize(db) {
return Math.max(0, Math.min(1, (db + 100) / 100));
}
}
class Smoother {
constructor(factor = 0.9) {
this.factor = factor;
this.value = 0;
}
update(input) {
this.value = this.factor * this.value + (1 - this.factor) * input;
return this.value;
}
}
Visual Property Mappings
Scale/Size
// Pulse on bass
function updateScale(element, bass) {
const scale = 1 + bass * 0.3; // 1.0 to 1.3
element.style.transform = `scale(${scale})`;
}
// Three.js mesh
function updateMeshScale(mesh, bass) {
const scale = 1 + bass * 0.5;
mesh.scale.setScalar(scale);
}
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.
- 1mo ago First seen · 555 lines · 46 tokens per session scan A aa254e0dbbce
audio-reactive is a skill published in the GitHub repository Bbeierle12/Skill-MCP-Claude (9 stars, last pushed yesterday), licensed MIT. It adds 46 tokens to every session and 3,316 once invoked, about $0.0002 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.
Other skills, from other repositories
fast-dash
Build a Fast Dash web app from a Python function. Use when the user wants to turn a function into an interactive app, add a UI to an existing function, build a dashboard / form / wizard, add a chat assistant to an app, or make an app that AI agents can drive over MCP. Fast Dash infers UI components from type hints, so…
flask-expert
Expert-level Flask web development, REST APIs, extensions, and production deployment. Use when the user mentions Python, web framework, REST APIs, or Jinja2, or when the task involves Flask Fundamentals or Flask Extensions.
flask-werkzeug-attack
Exploit Flask/Werkzeug debugger exposure for traceback and SECRET leaks.
flask
Flask - Lightweight Python web framework for microservices, REST APIs, and flexible web applications with extensive extension ecosystem.
flask
Ship Flask apps with application factories, blueprints, Alembic migrations, env-backed secrets, and gunicorn workers agents routinely miswire.
wechat-automation
A Windows desktop automation tool for sending messages through WeChat, a popular messaging app.