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 memory-managementgit 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/memory-management)<a href="https://agentmods.dev/skills/bullish0x/gamestudio/memory-management"><img src="https://agentmods.dev/badge/skills/bullish0x/gamestudio/memory-management/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/memory-management"><img src="https://agentmods.dev/badge/skills/bullish0x/gamestudio/memory-management.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 | $0.00019 | $0.04787 |
| Opus 5 | $0.00010 | $0.02393 |
| Sonnet 5 | $0.00004 | $0.00957 |
| Haiku 4.5 | $0.00002 | $0.00479 |
Grade A, and why
memory-management 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 5d 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 — 816 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Mobile Memory Management
When to Use
Use this skill when:
- Optimizing for mobile memory constraints
- Preventing memory leaks
- Managing texture memory
- Implementing object pooling
- Handling low memory warnings
- Optimizing garbage collection
Core Principles
- Proactive Disposal: Clean up resources explicitly
- Object Pooling: Reuse instead of allocate
- Texture Management: Compress and limit VRAM
- Lazy Loading: Load resources on demand
- Memory Monitoring: Track and respond to pressure
- GC Optimization: Minimize garbage collection pauses
Memory Management Implementation
1. Resource Manager
// memory/ResourceManager.ts
export interface Disposable {
dispose(): void;
}
export class ResourceManager {
private resources = new Map<string, Disposable>();
private refCounts = new Map<string, number>();
private memoryUsage = 0;
register<T extends Disposable>(id: string, resource: T): T {
if (this.resources.has(id)) {
// Resource already exists, increment ref count
this.refCounts.set(id, (this.refCounts.get(id) ?? 0) + 1);
return this.resources.get(id) as T;
}
this.resources.set(id, resource);
this.refCounts.set(id, 1);
// Track memory usage
if ('memory' in resource) {
this.memoryUsage += (resource as any).memory;
}
return resource;
}
get<T extends Disposable>(id: string): T | undefined {
return this.resources.get(id) as T | undefined;
}
release(id: string): void {
const refCount = this.refCounts.get(id) ?? 0;
if (refCount <= 1) {
// Last reference, dispose resource
const resource = this.resources.get(id);
if (resource) {
resource.dispose();
if ('memory' in resource) {
this.memoryUsage -= (resource as any).memory;
}
}
this.resources.delete(id);
this.refCounts.delete(id);
} else {
// Decrement ref count
this.refCounts.set(id, refCount - 1);
}
}
getMemoryUsage(): number {
return this.memoryUsage;
}
clear(): void {
for (const resource of this.resources.values()) {
resource.dispose();
}
this.resources.clear();
this.refCounts.clear();
this.memoryUsage = 0;
}
// Get resources sorted by memory usage
getResourcesByMemory(): Array<{ id: string; memory: number }> {
const resources: Array<{ id: string; memory: number }> = [];
for (const [id, resource] of this.resources) {
if ('memory' in resource) {
resources.push({ id, memory: (resource as any).memory });
}
}
return resources.sort((a, b) => b.memory - a.memory);
}
}
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.
- 5d ago First seen · 816 lines · 19 tokens per session scan A 8825949656b5
memory-management is a skill published in the GitHub repository bullish0x/GameStudio (11 stars, last pushed 2mo ago), licensed MIT. It adds 19 tokens to every session and 4,787 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.