What is vibecraft CLAUDE.md?

Development instructions for VibeCraft, an AI-powered Minecraft WorldEdit MCP server. WorldEdit is a Minecraft tool for making large building and terrain changes with commands.

Use them when changing the Python MCP server, its Minecraft connection and safety checks, its data files, or the agent's building instructions.

They explain the repository layout and distinguish developing the server from using the separate building agent.

How amenti-labs/vibecraft configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to amenti-labs/vibecraft. 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/amenti-labs/vibecraft/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/amenti-labs/vibecraft

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/amenti-labs/vibecraft/claude-md/github.svg)](https://agentmods.dev/instructions/amenti-labs/vibecraft/claude-md)

Your own site

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

Per session 1,274 This file is loaded in full into every session.

When invoked 1,274 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	$0.01274	$0.01274
Opus 5.5	$0.00510	$0.00510
Sonnet 5.5	$0.00255	$0.00255
Haiku 4.5	$0.00127	$0.00127

Measured 2mo ago against content hash fd51c6c68bf0, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

vibecraft 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 · 153 lines

How it starts

The opening of the file, as written. The whole thing — 153 lines — stays where its author put it; the contents beside it link to each section on GitHub.

VibeCraft Development Guide

You are working on the VibeCraft codebase - an AI-powered Minecraft WorldEdit MCP server.

Note: This CLAUDE.md is for developing VibeCraft. To use VibeCraft as a building agent, run Claude Code from the /agent folder instead.

Repository Structure

vibecraft/
├── agent/                    # VibeCraft AGENT files (run Claude from here to BUILD in Minecraft)
│   ├── .claude/skills/       # 7 building skills (worldedit, structures, terrain, etc.)
│   ├── context/              # AI reference guides (MD files agent reads)
│   ├── CLAUDE.md             # Agent system prompt
│   └── AGENTS.md             # Source for agent prompt (copied to CLAUDE.md)
│
├── mcp-server/               # MCP SERVER CODE (Python)
│   ├── src/vibecraft/
│   │   ├── server.py         # Main MCP server entry point
│   │   ├── tools/            # Tool handlers (modular)
│   │   ├── rcon_manager.py   # RCON protocol handler
│   │   ├── code_sandbox.py   # Safe code execution for build()
│   │   ├── sanitizer.py      # Command validation
│   │   └── ...
│   ├── data/                 # Server data files (JSON loaded by tools)
│   ├── pyproject.toml        # Dependencies
│   └── start-vibecraft.sh    # Server launcher
│
├── dev_docs/                 # Development documentation
├── docs/                     # User documentation
├── docker-compose.yml        # Minecraft server setup
└── setup-all.sh              # One-command setup

Experimenting with VibeCraft

The main way to experiment is by modifying the agent prompt and skills.

Most development work happens in the agent/ folder:

cd agent
claude  # Start Claude Code as the building agent

Then iterate on:

agent/CLAUDE.md — The agent's system prompt (auto-generated from AGENTS.md)
agent/.claude/skills/ — Building skills that teach the agent specific workflows
agent/context/ — Reference materials the agent can read

Workflow:

Make changes to skills or prompts
Run claude in the agent/ folder
Ask it to build something and observe behavior
Refine the instructions based on results

Read the full file on GitHub · 153 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 · 153 lines · 1,274 tokens per session scan A fd51c6c68bf0

Subscribe to this mod's changes

vibecraft CLAUDE.md is an instructions file published in the GitHub repository amenti-labs/vibecraft (107 stars, last pushed 9mo ago), licensed MIT. It adds 1,274 tokens to every session, about $0.0051 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.

Game development

vibecraft CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
vibecraft CLAUDE.mdamenti-labs/vibecraft	Instructions file	107	9mo ago	MIT	A	1,274	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

vibecraft: Instructions file for Claude Code