Getting it into your agent
There is no command for this one: it runs only inside a plugin, and the catalogue could not identify which plugin ships it. The source is linked below.
Wrote 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/instructions/raananw/babylonjs-webpack-es6/agents-md)<a href="https://agentmods.dev/instructions/raananw/babylonjs-webpack-es6/agents-md"><img src="https://agentmods.dev/badge/instructions/raananw/babylonjs-webpack-es6/agents-md.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 | $0.02029 | $0.02029 |
| Opus 5 | $0.01014 | $0.01014 |
| Sonnet 5 | $0.00406 | $0.00406 |
| Haiku 4.5 | $0.00203 | $0.00203 |
Grade A, and why
babylonjs-webpack-es6 AGENTS.md 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 yesterday.
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 — 184 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Instructions for AI coding agents (and humans in a hurry) working in this repository.
What this project is
A Babylon.js + TypeScript + webpack (ES6 / tree-shakable modules) starter template. It renders one scene at a time into a full-page canvas. There is no framework, no router and no state management - keep it that way.
Layout
| Path | Purpose |
|---|---|
src/index.ts |
Entry point. Reads ?scene= / ?engine=, boots the engine, runs the render loop. Keep it thin. |
src/createEngine.ts |
Engine creation (WebGL / WebGPU) and engine-name resolution. |
src/createScene.ts |
The CreateSceneClass contract and the lazy getSceneModule() loader. |
src/scenes/index.ts |
The scene registry - names, labels, lazy loaders and visual-test opt-ins. |
src/developmentControls.ts |
Scene/engine picker; included in development and demo builds, excluded from normal production and tests. |
src/scenes/*.ts |
One file per scene. |
src/externals/*.ts |
Wrappers around wasm/external libs (Havok, Ammo) exposing a ready-promise. |
src/glsl/ |
Raw shaders, imported as strings via ts-shader-loader. |
assets/ |
Textures/models bundled through webpack asset modules (inlined below 8 KiB, emitted as files above). |
public/ |
Static files served as-is (index.html, workers). |
tests/validation.spec.ts |
Registry-driven Playwright smoke tests plus opt-in screenshots. |
webpack.config.js |
The only webpack config. Switches behaviour via --env production / --env test. |
.github/workflows/ |
CI, snapshot refresh and optional GitHub Pages deployment. |
How to add a scene (the only supported way)
- Create
src/scenes/myScene.ts:
import { Scene } from "@babylonjs/core/scene";
import { ArcRotateCamera } from "@babylonjs/core/Cameras/arcRotateCamera";
import { Vector3 } from "@babylonjs/core/Maths/math.vector";
import type { AbstractEngine } from "@babylonjs/core/Engines/abstractEngine";
import type { CreateSceneClass } from "../createScene";
export class MyScene implements CreateSceneClass {
// Optional: promises awaited before createScene() runs (wasm, external libs)
// preTasks = [havokModule];
createScene = async (
engine: AbstractEngine,
canvas: HTMLCanvasElement
): Promise<Scene> => {
const scene = new Scene(engine);
const camera = new ArcRotateCamera("camera", 0, Math.PI / 3, 10, Vector3.Zero(), scene);
camera.attachControl(canvas, true);
return scene;
};
}
export default new MyScene();
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.
- yesterday Changed · +1 tokens per session e9459cfd715e
- 6d ago First seen · 184 lines · 2,028 tokens per session scan A 531b79230b9f
babylonjs-webpack-es6 AGENTS.md is an instructions file published in the GitHub repository RaananW/babylonjs-webpack-es6 (206 stars, last pushed yesterday), licensed Apache-2.0. It adds 2,029 tokens to every session, about $0.0101 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 instructions, from other repositories
realvirtual-WEB CLAUDE.md
Claude Code instructions for game4automation/realvirtual-WEB, covering claude.md — realvirtual web, project overview, quick start, code conventions and file naming.
core CLAUDE.md
Claude Code instructions for module-federation/core, covering claude task parallelization & development guidelines, core principles, maximum parallelization strategy, universal parallel task patterns and for any codebase task.
core AGENTS.md
AGENTS.md instructions for module-federation/core, covering agents.md, scope and precedence, source of truth (in priority order), environment parity and worktree mode (required in worktrees).
OneJS CLAUDE.md
Claude Code instructions for Singtaa/OneJS: Agent guidance for this repository lives in AGENTS.md. Read it first.
better-godot-mcp AGENTS.md
AGENTS.md instructions for n24q02m/better-godot-mcp, covering agents.md - better-godot-mcp, build / lint / test commands, run a single test file, run a single test by name and mise shortcuts.
turn-based-game-mcp typescript.instructions.md
TypeScript development patterns and best practices for the turn-based games platform.