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 hoangatg/ai-agent-toolkit --skill web-gamesgit clone --depth 1 https://github.com/hoangatg/ai-agent-toolkitWrote 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/hoangatg/ai-agent-toolkit/web-games)<a href="https://agentmods.dev/skills/hoangatg/ai-agent-toolkit/web-games"><img src="https://agentmods.dev/badge/skills/hoangatg/ai-agent-toolkit/web-games.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 | $0.00020 | $0.00788 |
| Opus 5 | $0.00010 | $0.00394 |
| Sonnet 5 | $0.00004 | $0.00158 |
| Haiku 4.5 | $0.00002 | $0.00079 |
Grade A, and why
web-games 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 3d 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.
This is a copy
97% identical to web-games — 4 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 151 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Web Browser Game Development
Framework selection and browser-specific principles.
1. Framework Selection
Decision Tree
What type of game?
│
├── 2D Game
│ ├── Full game engine features? → Phaser
│ └── Raw rendering power? → PixiJS
│
├── 3D Game
│ ├── Full engine (physics, XR)? → Babylon.js
│ └── Rendering focused? → Three.js
│
└── Hybrid / Canvas
└── Custom → Raw Canvas/WebGL
Comparison (2025)
| Framework | Type | Best For |
|---|---|---|
| Phaser 4 | 2D | Full game features |
| PixiJS 8 | 2D | Rendering, UI |
| Three.js | 3D | Visualizations, lightweight |
| Babylon.js 7 | 3D | Full engine, XR |
2. WebGPU Adoption
Browser Support (2025)
| Browser | Support |
|---|---|
| Chrome | ✅ Since v113 |
| Edge | ✅ Since v113 |
| Firefox | ✅ Since v131 |
| Safari | ✅ Since 18.0 |
| Total | ~73% global |
Decision
- New projects: Use WebGPU with WebGL fallback
- Legacy support: Start with WebGL
- Feature detection: Check
navigator.gpu
3. Performance Principles
Browser Constraints
| Constraint | Strategy |
|---|---|
| No local file access | Asset bundling, CDN |
| Tab throttling | Pause when hidden |
| Mobile data limits | Compress assets |
| Audio autoplay | Require user interaction |
Optimization Priority
- Asset compression - KTX2, Draco, WebP
- Lazy loading - Load on demand
- Object pooling - Avoid GC
- Draw call batching - Reduce state changes
- Web Workers - Offload heavy computation
4. Asset Strategy
Compression Formats
| Type | Format |
|---|---|
| Textures | KTX2 + Basis Universal |
| Audio | WebM/Opus (fallback: MP3) |
| 3D Models | glTF + Draco/Meshopt |
Loading Strategy
| Phase | Load |
|---|---|
| Startup | Core assets, <2MB |
| Gameplay | Stream on demand |
| Background | Prefetch next level |
5. PWA for Games
Benefits
- Offline play
- Install to home screen
- Full screen mode
- Push notifications
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.
- 3d ago First seen · 151 lines · 20 tokens per session scan A 1213dbf108ac
web-games is a skill published in the GitHub repository hoangatg/ai-agent-toolkit (1 stars, last pushed 5mo ago), licensed MIT. It adds 20 tokens to every session and 788 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It is 97% identical to web-games, differing in 4 lines, and is treated as a copy.
Other skills, from other repositories
codex
Delegate coding tasks to the OpenAI Codex CLI for features, refactoring, PR reviews, and batch fixes. Requires the codex CLI and typically a git repository.
opencode
Delegate coding tasks to the OpenCode CLI for feature work, refactoring, PR review, and autonomous-style runs. Requires opencode installed where the agent can execute shell commands.
deepnote
DeepNote knowledge base: persistent interlinked markdown wiki with ingest, query, lint, link graph and history.
golang-patterns
Idiomatic Go patterns, best practices, and conventions for building robust, efficient, and maintainable Go applications.
clickhouse-io
ClickHouse database patterns, query optimization, analytics, and data engineering best practices for high-performance analytical workloads.
springboot-patterns
Spring Boot architecture patterns, REST API design, layered services, data access, caching, async processing, and logging. Use for Java Spring Boot backend work.