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 roedyrustam/vibes-plug --skill web-game-engine-expertgit clone --depth 1 https://github.com/roedyrustam/vibes-plugWrote 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/roedyrustam/vibes-plug/web-game-engine-expert)<a href="https://agentmods.dev/skills/roedyrustam/vibes-plug/web-game-engine-expert"><img src="https://agentmods.dev/badge/skills/roedyrustam/vibes-plug/web-game-engine-expert/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/roedyrustam/vibes-plug/web-game-engine-expert"><img src="https://agentmods.dev/badge/skills/roedyrustam/vibes-plug/web-game-engine-expert.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 | $0.00084 | $0.05036 |
| Opus 5.5 | $0.00034 | $0.02014 |
| Sonnet 5.5 | $0.00017 | $0.01007 |
| Haiku 4.5 | $0.00008 | $0.00504 |
Grade A, and why
web-game-engine-expert 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 2d 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 — 427 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Web Game Engine Expert (Physics, Architecture & Game Loops)
English
Orchestration & Integration
Connects and orchestrates with relevant domain skills:
web-3d-graphics-expert— Visual rendering layer (WebGPU, Three.js, Babylon.js, PlayCanvas).glsl-shader-expert— Custom gameplay shaders, damage flashes, VFX materials.ui-ux-pro-max— In-game HUD overlays, crosshairs, radial inventory menus, and responsive virtual touch joysticks.design-system-architect— Consistent game UI tokens, custom bitmap/web fonts, and health/resource bar theming.visual-ui-auditor— Auditing responsive canvas scaling, DPI-aware pixel ratios (window.devicePixelRatio), and HUD contrast against 3D backgrounds.anti-slop— Enforcing zero placeholder physics, non-jittering deterministic game loops, and complete asset lifecycles.webxr-ar-vr-expert— Spatial controls and VR/AR controller tracking.realtime-collaboration-expert— Low-latency multiplayer state synchronization (WebRTC / WebTransport).performance-web-vitals— Frame budgeting (16.6ms for 60fps, 8.3ms for 120fps) and eliminating Garbage Collection stalls.wasm-edge-computing-expert— Compiling custom Rust/C++ simulation modules to WASM.
Description
Production-grade guidance for engineering commercial-quality 2D and 3D web games running at steady 60 to 144+ FPS. Enforces strict game architectural patterns: Fixed-Timestep Accumulators with render interpolation, WebAssembly Physics Engines (Rapier 3D, Jolt Physics, Havok), Zero-GC Object Pooling to eliminate JavaScript garbage collection stutters, Entity Component System (ECS) architectures, Web Audio API 3D Spatial Sound (HRTF), and WebTransport / WebRTC low-latency netcode.
Trigger Conditions
Activate this skill when the user is:
- Developing a web-based game or physics simulation (2D or 3D).
- Integrating physics with
@dimforge/rapier3d,jolt-physics,@babylonjs/havok, or@react-three/rapier. - Building or refactoring a game loop to fix frame pacing or physics stuttering on 120Hz/144Hz monitors.
- Implementing an Entity Component System (ECS) with
bitECSorminiplex. - Designing zero-allocation object pools for projectiles, particles, or temporary math vectors.
- Adding Gamepad API, Pointer Lock mouse look, or mobile virtual touch controls.
- Integrating 3D positional audio via the Web Audio API.
- Architecting multiplayer game networking with WebTransport (QUIC datagrams) or WebRTC DataChannels.
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.
- 2d ago Changed · +95 lines · +84 tokens per session 11aeef77837f
- 3d ago Changed · +2 lines · -84 tokens per session 34c20dd805b8
- 7d ago Changed cd0dc80e2d0a
- 15d ago Changed a1b397958559
- 21d ago Changed f6f6fe59446a
- 21d ago Changed 7e029c963c2a
- 23d ago Changed · -6 lines · +71 tokens per session 8ad88cbc66cc
- 25d ago Changed · +6 lines · -71 tokens per session 4adab0b1d91c
- 1mo ago Changed · +227 lines · +40 tokens per session 61d354e1fdc7
- 1mo ago First seen · 103 lines · 44 tokens per session scan A 05d2ebd863e0
web-game-engine-expert is a skill published in the GitHub repository roedyrustam/vibes-plug (113 stars, last pushed today), licensed MIT. It adds 84 tokens to every session and 5,036 once invoked, about $0.0003 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 2026-09-03.
Other skills, from other repositories
ai-engineering-toolkit
Overview of six AI engineering workflows: prompt evaluation (8-dimension scoring), context budget planning, RAG pipeline design, agent security audit (65-point checklist), eval harness building, and product sense coaching.
ai-prompt-regression-testing
Use when comparing prompt changes against a fixed evaluation set: record actual model settings, required checks, missing results, judge limitations and case-level regression evidence.
pixel-art-storyboard
Convert short scene descriptions, book/album cover briefs, or 2-paragraph synopses into seamless-loop animated pixel-art covers rendered as self-contained HTML+canvas. Companion skill to pixel-art-studio. Use when the user asks to "make a cover for", "animated book cover", "looped pixel scene", "convert this story…
cpp
Expert modern C++ (C++17/C++20/C++23) assistance covering RAII, smart pointers, template metaprogramming, STL containers, move semantics, and memory profiling. Use when developing high-performance native systems, low-latency algorithms, game engines, or embedded C++ codebases.
frontier
Execute any task at frontier quality. Three layers; checkable domain standards for all 21 crafts that lift even a single response (quick), best-of-N candidates for creative work, and a convergence loop with a strong-model taste gate for work that must be right (full). Self-contained; bundles the protocol, every craft…
game-ui-design
Research-grounded workflow for designing, reviewing, and improving video game user interfaces, including HUDs, menus, navigation, focus states, onboarding/tutorials, objective tracking, input prompts, readability, accessibility, and destructive-action flows. Use when asked how to make good game UI, critique a game UI…