llmgine: Instructions file for Claude Code

CLAUDE.md

llmgine CLAUDE.md is an instructions file for Claude Code from lordbasilaiassistant-sudo/llmgine. It costs 507 tokens per session, scanned A, original, MIT.

A project instruction file for llmgine, an engine for building games with help from language models. It defines rules for deterministic simulation, validated actions, fallback behavior, data structure, 3D rendering, and voice output.

In plain words
What is it for?
Use it when changing llmgine's architecture, simulation, rendering, voice systems, browser integration, or other engine code.
Why use it?
It keeps AI-assisted features from changing game state unpredictably and records important design constraints and known pitfalls for contributors.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md.

This is lordbasilaiassistant-sudo/llmgine's own configuration. It tells Claude Code how to work on llmgine itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything llmgine configures →

Reuse

Borrowing it

Nothing to install: this file belongs to lordbasilaiassistant-sudo/llmgine. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/lordbasilaiassistant-sudo/llmgine/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/lordbasilaiassistant-sudo/llmgine

Made for: Claude Code.

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.

agentmods badge for llmgine CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/lordbasilaiassistant-sudo/llmgine/claude-md.svg)](https://agentmods.dev/instructions/lordbasilaiassistant-sudo/llmgine/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/lordbasilaiassistant-sudo/llmgine/claude-md"><img src="https://agentmods.dev/badge/instructions/lordbasilaiassistant-sudo/llmgine/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 507 This file is loaded in full into every session.
When invoked 507 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00507 $0.00507
Opus 5 $0.00253 $0.00253
Sonnet 5 $0.00101 $0.00101
Haiku 4.5 $0.00051 $0.00051

Measured 7d ago against content hash a6ad88368c06, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

llmgine CLAUDE.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 7d 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.

CLAUDE.md · 35 lines

What it actually says

llmgine — project notes for Claude

The LLM-native game engine (working name). Builds ALL our future games. Read ARCHITECTURE.md before touching structure — it is the contract.

Iron rules

  • src/core imports nothing and never references LLMs. Sim stays deterministic (seeded RNG, fixed timestep); replayable from seed + intent log.
  • LLM output enters the world ONLY via ActionRegistry verbs (validated). New capability = new verb with a validator, never direct state mutation.
  • Every LLM-augmented feature has a deterministic fallback (API-down = game still runs).
  • Components are plain serializable data. No classes/methods in component state.
  • 3D (src/render3d, three.js) is the PRIMARY renderer. 2D canvas is for prototyping only — never demo the engine in 2D (Anthony's 1/10 rating, 2026-07-10).
  • Voice = Kokoro neural TTS adapter; Web Speech is last-resort fallback only.

Gotchas that already burned us

  • GLM flash = reasoning model: without thinking:{type:"disabled"} content is empty (budget spent on reasoning_content). Provider handles it for z.ai URLs.
  • Browser: fetch and requestAnimationFrame stored in fields must be .bind(globalThis) — Node masks this, tests won't catch it.
  • three r155+ physical lights: point lights need candela-scale intensity (~10⁴ at our world scale); avoid dark light colors (linear-space multiply → black); CylinderGeometry defaults to CLOSED caps (openEnded=true for walls/stands).

Commands

  • npm test (unit, no network) · npm run test:live (real GLM; needs ZAI_API_KEY)
  • npm run demo → builds + serves arena on :4173, auto-detects local key via /dev/key
  • npm run typecheck && npm run build — CI gate. Conventional commits.

State

Changes

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.

  1. 7d ago First seen · 35 lines · 507 tokens per session scan A a6ad88368c06

Subscribe to this mod's changes

llmgine CLAUDE.md is an instructions file published in the GitHub repository lordbasilaiassistant-sudo/llmgine (1 stars, last pushed 10d ago), licensed MIT. It adds 507 tokens to every session, about $0.0025 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.

Related

Other instructions, from other repositories

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,182 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens