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 agentmods add skills/frogobox/frogo-sdk/engine-selectionnpx skills add frogobox/frogo-sdk --skill engine-selectiongit clone --depth 1 https://github.com/frogobox/frogo-sdkWhat 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 | $0.00070 | $0.01213 |
| Opus 5 | $0.00035 | $0.00607 |
| Sonnet 5 | $0.00014 | $0.00243 |
| Haiku 4.5 | $0.00007 | $0.00121 |
Grade A, and why
engine-selection 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 — 116 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Engine selection
Pick tools that match delivery target, interaction model, and team constraints. Engines serve the game type — not the reverse.
Fit questions (ask first)
- Platform: Web, mobile, PC, console, VR?
- Primary loop: Action/physics, turn-based, narrative branch, management/UI, hybrid?
- Presentation: Full-screen canvas, DOM/UI chrome, or both?
- Toolchain: No-build / ESM OK, or bundler + editor OK?
- Authoring: Code-only, or designers need Twine/Ink/Godot/Unity editors?
Architecture patterns
| Pattern | When | Notes |
|---|---|---|
| Full engine shell | Game is the canvas/scene | Phaser, Godot, Unity, Kaplay as app root |
| Renderer + custom logic | You want draw power, own gameplay | PixiJS, Three.js + your systems |
| Hybrid shell + guest | Dense UI/text + occasional skill-checks | DOM/app shell; mount canvas engines in modals/viewports only |
| Narrative runtime | Branching prose is the product | Ink, Twine; host chrome separately |
| Content-as-data | Levels/events authored as packs | JSON/YAML + thin loader; engine optional |
Web — decision tree
What type of game?
│
├── Mostly DOM / panels / forms / text UI
│ ├── + small arcade/spatial challenges
│ │ └── Hybrid: custom shell + guest
│ │ Raw Canvas/WebGL → Kaplay → Phaser → PixiJS
│ └── + branching story
│ └── Ink (inkjs) or Twine export → host in DOM
│
├── Full-screen 2D game
│ ├── Full gameplay features (scenes, physics, input)
│ │ └── Phaser 4 (or Kaplay if you want lighter/faster prototype)
│ └── Mostly rendering / custom systems
│ └── PixiJS 8 (or Raw Canvas/WebGL if tiny scope)
│
└── Full-screen 3D game
├── Full engine / physics / XR
│ └── Babylon.js
└── Rendering-focused / lighter
└── Three.js
Quick comparison (web & common exports)
| Tool | Type | Best for | Watch-outs |
|---|---|---|---|
| Raw Canvas / WebGL | 2D/low-level | Tiny games, learning, no framework tax | You own everything |
| Kaplay (ex-Kaboom) | 2D toolkit | Fast prototypes, jam games | Less “full product” structure than Phaser |
| Phaser 4 | 2D engine | Complete 2D features | Heavier; often bundled |
| PixiJS 8 | 2D renderer | Performance, custom game code | Not a full gameplay framework alone |
| Three.js | 3D renderer | Visuals, lightweight 3D | You add gameplay systems |
| Babylon.js | 3D engine | Fuller 3D + XR | Heavier than Three for simple scenes |
| Ink + inkjs | Narrative | Complex branching prose | Weak for real-time multi-entity sims |
| Twine / Twison / TweeJS | Narrative | Educator-friendly branches | Export/host glue; not a physics engine |
| Godot 4 | Full engine | 2D/3D indie, open source | Web export iteration cost |
| Unity | Full engine | Large teams, multi-platform | Heavy for simple web UI games |
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 First seen · 116 lines · 70 tokens per session scan A 9eb7bd67ee6a
engine-selection is a skill published in the GitHub repository frogobox/frogo-sdk (21 stars, last pushed 2d ago), licensed Apache-2.0. It adds 70 tokens to every session and 1,213 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
sceneview-web
Build 3D and WebXR (AR/VR) experiences in the browser with SceneView for Web — Filament.js (WebGL2/WASM) wrapped in a Kotlin/JS DSL and a plain-JavaScript API on window.sceneview. Use whenever the user asks for "3D in the browser", "a web model viewer", "WebXR AR/VR", or any browser 3D/AR app where the dependency is…
gameobject-component-destroy
Destroy one or more Components from a target GameObject. Missing (null) components are skipped — they cannot be destroyed. Use 'gameobject-find' and 'gameobject-component-get' to identify the components first.
assets-prefab-save
Save the currently opened prefab edit stage back to its prefab asset without exiting the stage. Pair with 'assets-prefab-open' to enter the edit mode first.
mobile-games
Mobile game development principles. Touch input, battery, performance, app stores.
build-game-monster-system
Build, integrate, audit, or refactor rigged monsters for Three.js and web action games. Use for monster asset contracts, procedural or imported creature rigs, semantic joints and sockets, hurtboxes and attack volumes, combat animation states, enemy-runtime adapters, LODs, deterministic review fixtures, and validating…
nip85-trusted-assertions
The NIP-85 trusted-assertions model in Quartz (nip85TrustedAssertions/) — kind 10040 trust-provider lists, kind 30382 contact cards / user assertions, 30383 event assertions, 30384 addressable assertions, 30385 external-id assertions. Use when building or parsing these events, working with the typed tags (RankTag…