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 fanfan-de/anybox --skill web-game-foundationsgit clone --depth 1 https://github.com/fanfan-de/anyboxWrote 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/fanfan-de/anybox/web-game-foundations)<a href="https://agentmods.dev/skills/fanfan-de/anybox/web-game-foundations"><img src="https://agentmods.dev/badge/skills/fanfan-de/anybox/web-game-foundations/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/fanfan-de/anybox/web-game-foundations"><img src="https://agentmods.dev/badge/skills/fanfan-de/anybox/web-game-foundations.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Memory Poisoning · line 67 Skill manipulates agent memory, state, or stored context. Memory corruption can alter personality, override safety rules, or cause unpredictable behavior.Fix: Protect agent memory and state from modification by untrusted content. Use read-only memory for critical instructions and validate all state changes.
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 | $0.00038 | $0.00975 |
| Opus 5 | $0.00019 | $0.00487 |
| Sonnet 5 | $0.00008 | $0.00195 |
| Haiku 4.5 | $0.00004 | $0.00097 |
Grade A, and why
web-game-foundations 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 9d 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 — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Web Game Foundations
Overview
Use this skill to establish the non-negotiable architecture before implementation starts. Browser games degrade quickly when simulation, rendering, UI, asset loading, and input handling are mixed together.
Default rule: simulation state is owned outside the renderer, browser UI is not forced into the canvas unless there is a clear reason, and shipped 3D assets default to GLB or glTF 2.0 rather than ad hoc model formats.
Use This Skill When
- the user has not settled the engine or renderer choice
- the task is about boundaries, module shape, state ownership, or asset policy
- multiple specialist skills need one shared architectural frame
Do Not Stay Here When
- the runtime track is clearly Phaser
- the runtime track is clearly vanilla Three.js
- the runtime track is clearly React Three Fiber
- the task is purely about shipped 3D assets
Once the stack is clear, hand off to the runtime or asset specialist skill.
Architecture Rules
- Separate simulation from rendering.
- Simulation owns entities, turns, timers, collisions, progression, and saveable state.
- The renderer owns scene composition, animation playback, camera, particles, and input plumbing.
- Keep input mapping explicit.
- Define actions such as
move,confirm,cancel,ability-1, andpause. - Map physical inputs to actions in one place.
- Define actions such as
- Treat asset loading as a first-class system.
- Use stable manifest keys.
- Group by domain: characters, environment, UI, audio, FX.
- For 3D content, standardize on GLB or glTF 2.0 unless the chosen engine ecosystem requires another format upstream.
- Define save/debug/perf boundaries up front.
- Save serializable simulation state, not renderer objects.
- Keep debug overlays and perf probes easy to toggle.
- Use DOM overlays for menus and HUD by default.
- Canvas or WebGL should handle the playfield.
- DOM should handle text-heavy HUD, menus, settings, and accessibility-sensitive controls.
- In 3D, keep the persistent UI budget small so the scene stays readable and interactive.
- Lock 3D runtime conventions early.
- Choose consistent units, origins, pivots, and naming conventions.
- Decide how collision proxies, LODs, and baked lighting data are authored before runtime integration starts.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 9d ago First seen · 96 lines · 38 tokens per session scan A ef35c1954fa0
web-game-foundations is a skill published in the GitHub repository fanfan-de/anybox (57 stars, last pushed 1mo ago), licensed MIT. It adds 38 tokens to every session and 975 once invoked, about $0.0002 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
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.
unity-version-split
Split a C# file into Unity 6.5+ and pre-Unity 6.5 variants. Use when a file needs different implementations for different Unity versions due to API changes (e.g., EntityId vs int, GetEntityId vs GetInstanceID).
godot-signals-groups
Build event-driven, decoupled Godot 4.7 gameplay with signals and node groups: declare and emit custom signals, connect with Callables (incl. bind/one-shot), and broadcast to many nodes via groups and callgroup. Use when wiring node communication in a Godot project, replacing tight references with signals…
motion
How an agent turns a character mesh into a usable animated FBX — and how to judge whether the result is shippable.
unity-addressables
Manage Addressables groups, entries, profiles and content builds (com.unity.addressables, reflection-based).
threejs-exposure-color-grading
Build a measured exposure and grading path in Three.js. Use for a 64x36 encoded luminance meter, asynchronous readback, weighted log-average exposure, asymmetric adaptation, single tone-map ownership, and a generated 32-cube post-tone-map LUT.