What is beamng-mcp CLAUDE.md?

Repository instructions for BeamNG vehicle and simulator work, including architecture, development, testing, Blender-to- game workflows, and safety rules. BeamNG is a vehicle simulation game and engine.

Use them when modifying the BeamNG project, especially its Blender asset pipeline, simulator behavior, packaging, tests, or safety-sensitive systems.

They direct the agent to the authoritative project rules and required test gates before changing simulator behavior or related assets.

How eric-rolph/beamng-mcp configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to eric-rolph/beamng-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/eric-rolph/beamng-mcp/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/eric-rolph/beamng-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/eric-rolph/beamng-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/eric-rolph/beamng-mcp/claude-md)

Your own site

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

Per session 548 This file is loaded in full into every session.

When invoked 548 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	$0.00548	$0.00548
Opus 5.5	$0.00219	$0.00219
Sonnet 5.5	$0.00110	$0.00110
Haiku 4.5	$0.00055	$0.00055

Measured 2mo ago against content hash 1eda885c5865, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

beamng-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 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 · 33 lines

What it actually says

beamng-mcp — session entry point

AGENTS.md in this directory is the authoritative repository constitution: architecture and ownership boundaries, the gated Blender→BeamNG pipeline, the Cannon Car Wash baseline, Repository policy, validated runtimes, and the accumulated hard-won engine laws. Read the sections of AGENTS.md relevant to your task before changing protocol, safety, structural, packaging, or live-simulator behavior. This file only routes; it never overrides that document.

The knowledge ladder, most-current first:

docs/ARCHITECTURE.md, docs/DEVELOPMENT.md, docs/TOOLS.md, docs/SOFTBODY_AUTHORING.md — system design and the opt-in live gates.
The test suites are the gates: static suites always; lupa state-machine suites from the repo venv (they SKIP silently without lupa); *_live.py only against the sentinel-isolated profile.
AGENTS.md — the constitution, including per-mod round ledgers and engine laws.
examples/giant_props/workflow_archive/ — frozen as-run critic/audit harnesses. Reference designs only; never re-run them.

Operational facts every session needs:

Venv python: .\.venv\Scripts\python.exe. Blender: side-by-side 4.5.4 at C:\Users\ericr\Applications\Blender\4.5.4\blender.exe (see AGENTS.md for invocations).
Giant props build: python examples/giant_props/build.py <key> prop|dist|harvest — dist is a RE-ZIP of mod/, never a rebuild, and prop can downgrade cooked textures without a certified harvest manifest. Read the release re-cut law in AGENTS.md before touching a shipped mod.
Local play deployment: python examples/giant_props/deploy_local.py reports the REAL profile (%LOCALAPPDATA%\BeamNG\BeamNG.drive\current\mods) against every release lock; --deploy syncs what is stale, hash-verified. Tests and fixtures NEVER go to the real profile — live gates use the sentinel profile env vars in AGENTS.md and install through the service.
Generated release-bound text files must be written with newline="\n"; JBeam/material outputs stay strict JSON.
Do not commit, push, merge, or publish a mod unless the user explicitly asks.

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 · 33 lines · 548 tokens per session scan A 1eda885c5865

Subscribe to this mod's changes

beamng-mcp CLAUDE.md is an instructions file published in the GitHub repository eric-rolph/beamng-mcp (2 stars, last pushed 1mo ago), licensed MIT. It adds 548 tokens to every session, about $0.0022 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.

Game development autonomous-driving beamng beamngpy computer-vision lua mcp-server

beamng-mcp CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
beamng-mcp CLAUDE.mderic-rolph/beamng-mcp	Instructions file	2	1mo ago	MIT	A	548	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	144k	today	MIT	A	7,461	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	5,685	GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	today	MIT	A	4,680	Codex, OpenCode
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	281k	yesterday	MIT	A	4,335	Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	3,086	GitHub Copilot

beamng-mcp: Instructions file for Claude Code