What is ev2090 CLAUDE.md?

Project instructions for EV·2090, a 3D space simulation game with a live non-player-character economy, built as a monorepo—a repository containing several related applications and packages.

Use them when changing the frontend, Cloudflare backend, MCP server, admin dashboard, or the four npm workspaces.

They explain the technology stack and enforce the boundary between the Three.js game engine and React interface code, reducing cross-layer changes that could break the project.

How Anashel-RPG/ev2090 configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to Anashel-RPG/ev2090. 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/Anashel-RPG/ev2090/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/Anashel-RPG/ev2090

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/anashel-rpg/ev2090/claude-md/github.svg)](https://agentmods.dev/instructions/anashel-rpg/ev2090/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/anashel-rpg/ev2090/claude-md"><img src="https://agentmods.dev/badge/instructions/anashel-rpg/ev2090/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/anashel-rpg/ev2090/claude-md"><img src="https://agentmods.dev/badge/instructions/anashel-rpg/ev2090/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 3,724 This file is loaded in full into every session.

When invoked 3,724 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.

Model	Per session	Once invoked
Fable 5.1	$0.03724	$0.03724
Opus 5.5	$0.01490	$0.01490
Sonnet 5.5	$0.00745	$0.00745
Haiku 4.5	$0.00372	$0.00372

Measured 2mo ago against content hash 8c01c9d4f4b6, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

ev2090 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 2mo 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 · 291 lines

How it starts

The opening of the file, as written. The whole thing — 291 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md — Project Context for AI Assistants

Project

EV · 2090 — a 3D space simulation game with a live NPC economy. Live: https://ev2090.com | API: https://ws.ev2090.com | MCP: https://mcp.ev2090.com

Tech Stack

Frontend: React 19 + Three.js 0.172 + TypeScript 5.7 + Vite 6
Backend: Cloudflare Workers + Durable Objects + R2 + Queues
MCP Server: 37 tools, OAuth 2.0 PKCE (worker-mcp/)
Admin Dashboard: React + Vite, local-only, never deployed (admin/)
Monorepo: 4 npm workspaces — frontend/, worker/, worker-mcp/, admin/

Architecture — The One Rule

The engine (frontend/src/engine/) is pure Three.js with ZERO React dependencies. React communicates with the engine only through GameCanvasHandle (imperative ref in GameCanvas.tsx). The engine pushes GameState to React at ~20fps via a subscribe callback.

NEVER import React in engine/ files. NEVER import Three.js in components/ files.

When a component needs 3D rendering, create a standalone class in engine/ and instantiate it from the component via useEffect — see ShipPreview.ts and ShipDetailRenderer.ts for the pattern.

Key Files

File	Purpose
`frontend/src/engine/Engine.ts`	Core game loop, scene, renderer, all subsystem orchestration
`frontend/src/components/GameCanvas.tsx`	React-to-Engine bridge (forwardRef + useImperativeHandle)
`frontend/src/components/Game.tsx`	Top-level React orchestrator — state, layout, breakpoints
`frontend/src/types/game.ts`	Shared types: GameState, ShipState, RadarContact, LightConfig
`frontend/src/engine/ShipCatalog.ts`	Ship definitions (11 built-in + community registry)
`worker/src/index.ts`	HTTP router + CORS + queue consumer
`worker/src/chat-room.ts`	Durable Object — SSE chat, 7 messages, ping keep-alive
`worker/src/board-room.ts`	Durable Object — community notes per planet station
`worker/src/ship-forge.ts`	Durable Object — AI ship pipeline (Grok → Gemini → MeshyAI)
`worker/src/economy-region.ts`	Durable Object — NPC economy simulation (SQLite, 60s alarm tick)
`worker/src/admin.ts`	Admin API endpoints (auth required via ADMIN_API_KEY)
`worker-mcp/src/index.ts`	MCP server entry point — 37 tools, OAuth 2.0 PKCE
`admin/src/App.tsx`	Admin dashboard SPA — Economy, Region Detail, Infra Health, Trade Viewer

Read the full file on GitHub · 291 lines

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.

2mo ago First seen · 291 lines · 3,724 tokens per session scan A 8c01c9d4f4b6

Subscribe to this mod's changes

ev2090 CLAUDE.md is an instructions file published in the GitHub repository Anashel-RPG/ev2090 (10 stars, last pushed 8mo ago), licensed MIT. It adds 3,724 tokens to every session, about $0.0149 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 2026-08-31.

ev2090 CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
ev2090 CLAUDE.mdAnashel-RPG/ev2090	Instructions file	10	8mo ago	MIT	A	3,724	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	today	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

ev2090: Instructions file for Claude Code