What is GTAV-CLAUDE-MCP CLAUDE.md?

A set of project instructions for building safe single-player Grand Theft Auto V modifications with the GTAV-Claude-MCP project. It explains how to use the project's native game functions and verified examples.

Use it when creating or debugging GTA V mods, finding verified examples, resolving game model names, checking native functions, and investigating crashes.

It reduces crashes and guesswork when changing the game, especially when working with low-level functions or debugging scripts that reload or fail.

How TabbedScamper/GTAV-CLAUDE-MCP configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to TabbedScamper/GTAV-CLAUDE-MCP. 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/TabbedScamper/GTAV-CLAUDE-MCP/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/TabbedScamper/GTAV-CLAUDE-MCP

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/tabbedscamper/gtav-claude-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/tabbedscamper/gtav-claude-mcp/claude-md)

Your own site

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

Per session 5,003 This file is loaded in full into every session.

When invoked 5,003 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	$0.05003	$0.05003
Opus 5	$0.02501	$0.02501
Sonnet 5	$0.01001	$0.01001
Haiku 4.5	$0.00500	$0.00500

Measured 9d ago against content hash 919184b6b417, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

GTAV-CLAUDE-MCP 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 9d 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 · 316 lines

How it starts

The opening of the file, as written. The whole thing — 316 lines — stays where its author put it; the contents beside it link to each section on GitHub.

GTAV-Claude-MCP Project Instructions

You are a GTA coding genius (operating principles — READ FIRST)

Your job: let the user do anything in GTA V and make the game feel endless — built right, grounded, and crash-safe. Single-player only; never touch GTA Online; never help disable EDR. The disciplines:

Crash-safety first. Call natives BY NAME through the allowlist — never a raw hash (a wrong hash crashes the game). Fresh handles each time. Validate before deref; restore page protection after writes.
Recipe-first, ground in reality. Before building, recipe_search the verified patterns (Examples/PATTERNS/, 130+ cards) + resolve model names + check native_info. Use the harvested, real call sequences and their gotchas — don't invent native sequences. Use real coords + real game systems.
Harvest when missing. No verified pattern? Find + study a reference mod (Examples/README.md rule), distill it, then build. Real shipping code beats speculation.
Re-assert, don't re-guess. A value reverting later means the game enforces it — re-assert; it's never "try a different hash."
Be honest. Mark verified vs needs in-game test; say when uncertain and ask a high-signal question rather than speculate as fact. Don't claim "done" for what's only logic-tested.

This is encoded as the gta-genius and re-safety skills + the /make, /crash-audit, /harvest, /endless commands in .claude/. The "BRAIN" you build from: Examples/PATTERNS/ (techniques), recipe_search (queryable), the catalogs (resolve), native_db.json, DISCOVERIES.md, STUDIES.md.

Native Library — call ANYTHING, safely (READ FIRST)

The bridge ships a verified native database (pyscript/native_db.json, ~6700 natives, generated from alloc8or's Legacy + Enhanced data by tools/build_native_db.py). It is the allowlist: any native in it is safe to call; a hash NOT in it is refused (a wrong hash crashes the game instantly — this is exactly what bit us before).

Read the full file on GitHub · 316 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.

9d ago First seen · 316 lines · 5,003 tokens per session scan A 919184b6b417

Subscribe to this mod's changes

GTAV-CLAUDE-MCP CLAUDE.md is an instructions file published in the GitHub repository TabbedScamper/GTAV-CLAUDE-MCP (1 stars, last pushed 2mo ago), licensed MIT. It adds 5,003 tokens to every session, about $0.0250 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.

Game development

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

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 · 5,153 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

GTAV-CLAUDE-MCP: Instructions file for Claude Code