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 chrisgliddon/bevy-skills --skill bevy-wasm-webgpugit clone --depth 1 https://github.com/chrisgliddon/bevy-skillsWrote 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/chrisgliddon/bevy-skills/bevy-wasm-webgpu)<a href="https://agentmods.dev/skills/chrisgliddon/bevy-skills/bevy-wasm-webgpu"><img src="https://agentmods.dev/badge/skills/chrisgliddon/bevy-skills/bevy-wasm-webgpu/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/chrisgliddon/bevy-skills/bevy-wasm-webgpu"><img src="https://agentmods.dev/badge/skills/chrisgliddon/bevy-skills/bevy-wasm-webgpu.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 | $0.00070 | $0.01266 |
| Opus 5 | $0.00035 | $0.00633 |
| Sonnet 5 | $0.00014 | $0.00253 |
| Haiku 4.5 | $0.00007 | $0.00127 |
Grade A, and why
bevy-wasm-webgpu 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 — 149 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Bevy 0.19 — browser WASM
When to use this skill
- Build a Bevy client for
wasm32-unknown-unknown. - Choose the broadly compatible WebGL2 path or WebGPU path.
- Generate JS bindings, serve assets, and reduce artifact size.
- Diagnose missing canvas, insecure-context, codec, or asset-path failures.
Canonical manifest
[package]
name = "myclient"
version = "0.1.0"
edition = "2024"
[dependencies]
bevy = { version = "0.19", default-features = false, features = [
"3d",
"ui",
"touch",
] }
[profile.wasm-release]
inherits = "release"
opt-level = "z"
lto = "fat"
codegen-units = 1
strip = "debuginfo"
The 3d profile supplies Bevy's renderer, Winit, and the default WebGL2 path.
Add audio only if needed; browser audio must begin after user interaction.
Build and serve
rustup target add wasm32-unknown-unknown
cargo install wasm-bindgen-cli
cargo build --profile wasm-release --target wasm32-unknown-unknown
wasm-bindgen --target web --out-name myclient --out-dir public \
target/wasm32-unknown-unknown/wasm-release/myclient.wasm
# Optional: install Binaryen first, then verify this actually reduces size.
wasm-opt -Oz public/myclient_bg.wasm -o public/myclient_bg.opt.wasm
mv public/myclient_bg.opt.wasm public/myclient_bg.wasm
python3 -m http.server --directory public 8080
Copy or link the project assets/ directory to public/assets/; Bevy fetches
assets over HTTP relative to the served page/asset root.
Minimal HTML
<!doctype html>
<html lang="en">
<head>
<meta charset="utf-8">
<meta name="viewport" content="width=device-width,initial-scale=1">
<title>My Bevy game</title>
<style>html,body,#bevy{width:100%;height:100%;margin:0;background:#000}</style>
</head>
<body>
<canvas id="bevy"></canvas>
<script type="module">
import init from "./myclient.js";
await init();
</script>
</body>
</html>
Bind the primary window to that existing canvas. Otherwise Window::default() has
canvas: None, so Bevy/Winit creates and appends a second canvas:
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 · 149 lines · 70 tokens per session scan A 97b6d318dbe9
bevy-wasm-webgpu is a skill published in the GitHub repository chrisgliddon/bevy-skills (11 stars, last pushed 15d ago), licensed MIT. It adds 70 tokens to every session and 1,266 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 2026-08-31.
Other skills, from other repositories
browser-game
Turn an incomplete browser-game brief into evidence-bound checkpoints and standard-stamped successor delivery.
bg3-steam-launcher
Launch Baldur's Gate 3 through Steam on macOS and load saved games using macos-automator and peekaboo MCP servers. Designed for testing bg3se-macos (Script Extender) development. Use when: (1) launching BG3 from Steam, (2) loading a BG3 saved game, (3) testing SE mod injection, (4) user asks to "start BG3", "load my…
multiplatform-conversion
Converting a single-target FlatRedBall2 desktop sample into a dual-target desktop + KNI BlazorGL (Blazor WebAssembly / browser) project. Use when the user mentions web deployment, browser/WASM/itch.io targets, KNI, or asks to add web support to an existing game. Assumes you already have a working desktop sample — see…
agent-casino-gambling
Interact with MoltCasino - a 3D Vegas-style casino built for AI agents.
browser-fps
Build a one-room first-person browser game from a brief - engine evidence, a design brief, checkpointed waves, and a playable probe.
webg-spec-to-goal
Convert a web game idea (even a vague one like "build a Raiden-type game" or "make a card game") into a complete Codex /goal-ready Phaser 3 project — runnable scaffold, goals-plan.md, and all goal folders (GOAL.md + VERIFY.md + PROGRESS.md) generated at once. Auto-detects genre (shoot-em-up, card game, platformer…