World of ClaudeCraft is a browser-based classic-style multiplayer online game with a persistent shared world that can also run locally or be controlled through a Python reinforcement-learning interface. Players can quest and raid in the online world, while developers can host it themselves and train AI agents to play. The catalogue skills, agents, instructions, hooks, and setting support workflows for interacting with and developing the game.
Borrowing it
Nothing to install: this file belongs to levy-street/world-of-claudecraft. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/levy-street/world-of-claudecraft/main/CLAUDE.mdgit clone --depth 1 https://github.com/levy-street/world-of-claudecraftWrote 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/levy-street/world-of-claudecraft/claude-md)<a href="https://agentmods.dev/instructions/levy-street/world-of-claudecraft/claude-md"><img src="https://agentmods.dev/badge/instructions/levy-street/world-of-claudecraft/claude-md/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/instructions/levy-street/world-of-claudecraft/claude-md"><img src="https://agentmods.dev/badge/instructions/levy-street/world-of-claudecraft/claude-md.svg" alt="Reviewed on agentmods" width="80" 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 | $0.07326 | $0.07326 |
| Opus 5.5 | $0.02930 | $0.02930 |
| Sonnet 5.5 | $0.01465 | $0.01465 |
| Haiku 4.5 | $0.00733 | $0.00733 |
Grade A, and why
world-of-claudecraft 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 3d 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 — 367 lines — stays where its author put it; the contents beside it link to each section on GitHub.
World of ClaudeCraft
A classic-style micro-MMO and a headless reinforcement-learning
environment, both driven by one deterministic TypeScript simulation core.
Stack: TypeScript (ESM, strict) · Three.js renderer · ws WebSockets ·
Postgres (pg) · Vite + esbuild · Vitest. No UI framework in the game client; tiny
dependency set. The one sanctioned exception is the standalone admin dashboard
(src/admin/), which is built with Svelte 5 (it never touches the game client bundle).
Repo map
| Path | What it is |
|---|---|
src/sim/ |
Deterministic game core, the source of truth. No DOM/Three deps; runs in browser, server, and headless. |
src/sim/content/ |
Data-as-code: classes, abilities, talents, zones, dungeons, items, professions, mounts, deeds, Reliquary pages. |
src/render/ |
Three.js renderer (procedural geometry/textures/VFX + curated GLBs). Reads the world; never mutates it. |
src/game/ |
Local input, camera, keybinds, gamepad, mobile controls, sampled WebAudio SFX, and procedural music. |
src/ui/ |
Classic HUD (frames, windows, tooltips, map, FCT), procedural icons, i18n. |
src/styles/ |
Extracted HUD CSS under one @layer order, imported via src/main.ts (and src/boot.ts, index.html's entry). See src/styles/CLAUDE.md. |
src/net/ |
Online client: REST auth + WebSocket world mirror (ClientWorld), reconnect, native-app glue, wallet glue. |
src/admin/ |
Admin dashboard SPA (separate admin.html entry). |
src/guide/ |
Public guide/wiki SPA (separate guide.html entry, served at /wiki); spoiler-safe content generated from src/sim/. |
src/editor/ |
World editor SPA (separate root-level editor.html entry); its 3D viewport composes the real Sim + Renderer. |
src/world_api.ts + src/world_api/ |
IWorld, the seam render/ui depend on: one facet interface per domain file under src/world_api/, re-aggregated by the barrel (see Architecture). |
src/main.ts |
Client entry (index.html reaches it through src/boot.ts); fixes the world seed. |
server/ |
Authoritative game server: HTTP+WS, world loop, Postgres, auth, social, moderation. |
server/http/ |
The REST request pipeline spine: table router, middleware onion, per-domain RouteDef tables, typed schemas, stable error codes. |
server/epic/ · server/steam/ · server/parse/ · server/email/ |
Store/platform glue, combat-parse ingest, transactional email; each has its own CLAUDE.md. |
headless/ + python/ |
RL env server (env_server.ts) + Python Gym bindings. |
bot/ |
Discord bot (role sync, relay, activity feed; own CLAUDE.md). |
electron/ (+ build/) |
Desktop (Steam) shell + packaging assets; see docs/desktop-release.md. |
android/ + ios/ |
Capacitor native shells (npm run native:*). |
tests/ |
Vitest suite (subdirectory map in tests/CLAUDE.md). |
scripts/ |
Asset/build/i18n/SFX tooling + browser E2E / screenshot scripts. |
patches/ + data/ |
pnpm-patched dependencies (Three.js is patched; check before bumping it) + checked-in map data. |
public/ · docs/ |
Static assets, deployed verbatim to the live site · design + PRD + ops docs. |
mediawiki/ + deploy/ |
Player-wiki container + production first-boot assets (see DEPLOY.md). |
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.
- 3d ago Changed · +24 tokens per session 9e7dbdf31749
- 1mo ago Changed · +6 lines · +123 tokens per session 4c091411698f
- 1mo ago Changed · +7 lines · +138 tokens per session 1809c01ef8c2
- 2mo ago First seen · 354 lines · 7,041 tokens per session scan A 70274e21e8a7
world-of-claudecraft CLAUDE.md is an instructions file published in the GitHub repository levy-street/world-of-claudecraft (2,323 stars, last pushed today), licensed MIT. It adds 7,326 tokens to every session, about $0.0293 per session on Opus 5.5. 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
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).
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.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
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.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.