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 bullish0x/GameStudio --skill mobile-performancegit clone --depth 1 https://github.com/bullish0x/GameStudioWrote 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/bullish0x/gamestudio/mobile-performance)<a href="https://agentmods.dev/skills/bullish0x/gamestudio/mobile-performance"><img src="https://agentmods.dev/badge/skills/bullish0x/gamestudio/mobile-performance/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/bullish0x/gamestudio/mobile-performance"><img src="https://agentmods.dev/badge/skills/bullish0x/gamestudio/mobile-performance.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 | $0.00026 | $0.03297 |
| Opus 5 | $0.00013 | $0.01648 |
| Sonnet 5 | $0.00005 | $0.00659 |
| Haiku 4.5 | $0.00003 | $0.00330 |
Grade A, and why
mobile-performance 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 6d 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 — 525 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Mobile Performance Optimization
When to Use
Use this skill when:
- Building Three.js games for mobile devices
- Optimizing existing games for mobile
- Implementing adaptive quality settings
- Dealing with thermal throttling
- Reducing battery consumption
Core Principles
- Device Detection: Detect device capabilities and adjust accordingly
- Quality Scaling: Implement multiple quality presets
- Frame Rate Management: Adaptive FPS based on performance
- Thermal Awareness: Reduce load when device heats up
- Battery Optimization: Lower quality on battery power
- Progressive Enhancement: Start low, scale up if possible
Implementation
1. Device Detector
export interface DeviceCapabilities {
tier: 'low' | 'medium' | 'high';
gpu: string;
maxTextureSize: number;
supportsWebGL2: boolean;
isMobile: boolean;
isIOS: boolean;
isAndroid: boolean;
memory: number; // GB
cores: number;
pixelRatio: number;
}
export class DeviceDetector {
private capabilities: DeviceCapabilities;
constructor() {
this.capabilities = this.detect();
}
private detect(): DeviceCapabilities {
const canvas = document.createElement('canvas');
const gl = canvas.getContext('webgl2') || canvas.getContext('webgl');
if (!gl) {
throw new Error('WebGL not supported');
}
const debugInfo = gl.getExtension('WEBGL_debug_renderer_info');
const gpu = debugInfo
? gl.getParameter(debugInfo.UNMASKED_RENDERER_WEBGL)
: 'Unknown';
const maxTextureSize = gl.getParameter(gl.MAX_TEXTURE_SIZE);
const supportsWebGL2 = !!canvas.getContext('webgl2');
// Device detection
const ua = navigator.userAgent.toLowerCase();
const isMobile = /mobile|android|iphone|ipad|ipod/.test(ua);
const isIOS = /iphone|ipad|ipod/.test(ua);
const isAndroid = /android/.test(ua);
// Memory estimation (GB)
const memory = (navigator as any).deviceMemory || this.estimateMemory(gpu);
// CPU cores
const cores = navigator.hardwareConcurrency || 4;
// Pixel ratio (cap at 2 for performance)
const pixelRatio = Math.min(window.devicePixelRatio, 2);
// Determine device tier
const tier = this.calculateTier(gpu, memory, cores, isMobile);
return {
tier,
gpu,
maxTextureSize,
supportsWebGL2,
isMobile,
isIOS,
isAndroid,
memory,
cores,
pixelRatio,
};
}
private estimateMemory(gpu: string): number {
const gpuLower = gpu.toLowerCase();
// High-end
if (/adreno 6|mali-g7|apple a1[2-9]|m[1-9]/.test(gpuLower)) {
return 6;
}
// Mid-range
if (/adreno 5|mali-g5|apple a[9-11]/.test(gpuLower)) {
return 4;
}
// Low-end
return 2;
}
private calculateTier(
gpu: string,
memory: number,
cores: number,
isMobile: boolean
): 'low' | 'medium' | 'high' {
const gpuLower = gpu.toLowerCase();
// High-end devices
if (
memory >= 6 &&
cores >= 6 &&
(/adreno 6|mali-g7|apple a1[2-9]|m[1-9]|rtx|radeon rx/.test(gpuLower))
) {
return 'high';
}
// Low-end devices
if (
memory <= 2 ||
cores <= 4 ||
/adreno [2-4]|mali-[4-5]|apple a[6-8]/.test(gpuLower)
) {
return 'low';
}
// Medium by default
return 'medium';
}
getCapabilities(): DeviceCapabilities {
return this.capabilities;
}
getTier(): 'low' | 'medium' | 'high' {
return this.capabilities.tier;
}
}
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.
- 6d ago First seen · 525 lines · 26 tokens per session scan A b85ba6097292
mobile-performance is a skill published in the GitHub repository bullish0x/GameStudio (12 stars, last pushed 2mo ago), licensed MIT. It adds 26 tokens to every session and 3,297 once invoked, about $0.0001 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
android-development
Android development with Kotlin, Jetpack Compose, and modern Android architecture. Use when building Android apps, implementing Material Design, or following Android best practices.
flutter-development
Cross-platform development with Flutter and Dart for iOS, Android, Web, Desktop, and embedded. Use when building Flutter apps, implementing Material/Cupertino design, or optimizing Dart code.
game-development
Game development with Unity, Unreal Engine, and Godot. Use when building games, implementing game mechanics, physics, AI, or working with game engines.
ios-development
Comprehensive guide for building native Apple platform applications.
kotlin-multiplatform
KMP/CMP shared business logic, Compose Multiplatform, expect/actual, Ktor, SQLDelight, and platform-specific implementations. Use when building cross-platform Kotlin applications for Android, iOS, desktop, or web.
ar-vr-xr
AR/VR/XR development with Unity XR, WebXR, ARKit, ARCore, Meta Quest SDK, and spatial computing. Use when building augmented reality, virtual reality, mixed reality applications, or spatial experiences.