What is gta7 CLAUDE.md?

Repository guidance for a browser-based 3D driving and walking demo built with TypeScript and Three.js, a JavaScript library for displaying 3D graphics. It documents the project structure, commands, coding conventions, and rules that must remain true.

Use it to install, run, build, test, and inspect the demo, and to guide edits to its vehicles, city, traffic, pedestrians, and player controls.

It gives a coding agent the project context needed before changing simulation code, reducing the risk of breaking gameplay, builds, or tests.

How depixeled-chris/gta7 configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to depixeled-chris/gta7. 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/depixeled-chris/gta7/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/depixeled-chris/gta7

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/depixeled-chris/gta7/claude-md/github.svg)](https://agentmods.dev/instructions/depixeled-chris/gta7/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/depixeled-chris/gta7/claude-md"><img src="https://agentmods.dev/badge/instructions/depixeled-chris/gta7/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/depixeled-chris/gta7/claude-md"><img src="https://agentmods.dev/badge/instructions/depixeled-chris/gta7/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 3,425 This file is loaded in full into every session.

When invoked 3,425 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	$0.03425	$0.03425
Opus 5.5	$0.01370	$0.01370
Sonnet 5.5	$0.00685	$0.00685
Haiku 4.5	$0.00343	$0.00343

Measured 2mo ago against content hash b77ef101287e, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

gta7 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 · 76 lines

How it starts

The opening of the file, as written. The whole thing — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

What this is

A browser-based, GTA-style 3D open-world vertical slice built from scratch in TypeScript + Three.js: a procedural night city you can drive a car around, get out, and walk on foot, with ambient traffic and pedestrians. It is a tech demo, not a full game. (The name is a joke.)

Commands

npm install                 # first-time setup
npm run dev                 # Vite dev server (hot reload) — play at the printed URL
npm run build               # tsc --noEmit (typecheck) THEN vite build -> dist/
npm test                    # Vitest: pure-logic unit tests (node env)
npm run test:watch          # Vitest in watch mode
npm run smoke               # build + headless-Chromium render check (see below)
npm run test:e2e            # build + render + gameplay (keyboard) + touch/mobile tests
npm run preview             # serve the built dist/

Run a single test file or case:

npx vitest run src/vehicles/VehicleModel.test.ts
npx vitest run -t "caps speed at maxSpeed"

The browser tests (scripts/smoke.mjs, scripts/interaction.mjs) require Chromium once: npx playwright install chromium. Both self-host the built app. smoke fails on any console/page error and decodes a screenshot to assert the scene actually rasterized (color diversity + lit-pixel fraction) rather than rendering a blank canvas. interaction drives the real game (keyboard) to assert gameplay: building collision, carjacking, shoving, pedestrian braking, and WASTED. touch runs a mobile (touch) context to assert the on-screen joystick drives the car and the buttons work, and that desktop shows no touch UI. All use the window.__game debug handle (mode, health, wasted, vehicles, player, city) exposed from main.ts — keep it in sync if you add state worth testing.

Architecture

The codebase is split along one hard line: the simulation core is pure and Three.js-free; the rendering/runtime layer owns everything that imports three. This is what makes the gameplay logic unit-testable in a node environment.

Read the full file on GitHub · 76 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 · 76 lines · 3,425 tokens per session scan A b77ef101287e

Subscribe to this mod's changes

gta7 CLAUDE.md is an instructions file published in the GitHub repository depixeled-chris/gta7 (21 stars, last pushed 5mo ago), licensed MIT. It adds 3,425 tokens to every session, about $0.0137 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.

gta7 CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
gta7 CLAUDE.mddepixeled-chris/gta7	Instructions file	21	5mo ago	MIT	A	3,425	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	yesterday	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

gta7: Instructions file for Claude Code