Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add instructions/chapmanjw/minecraft-java-fabric-claude-plugin/claude-mdgit clone --depth 1 https://github.com/chapmanjw/minecraft-java-fabric-claude-pluginWrote 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.
[](https://agentmods.dev/instructions/chapmanjw/minecraft-java-fabric-claude-plugin/claude-md)<a href="https://agentmods.dev/instructions/chapmanjw/minecraft-java-fabric-claude-plugin/claude-md"><img src="https://agentmods.dev/badge/instructions/chapmanjw/minecraft-java-fabric-claude-plugin/claude-md.svg" alt="Measured on agentmods" height="20"></a>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 | $0.02351 | $0.02351 |
| Opus 5 | $0.01175 | $0.01175 |
| Sonnet 5 | $0.00470 | $0.00470 |
| Haiku 4.5 | $0.00235 | $0.00235 |
Grade A, and why
minecraft-java-fabric-claude-plugin 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 4d 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.
How it starts
The opening of the file, as written. The whole thing — 125 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.
Commands
node scripts/validate-plugin.mjs # validate manifests, frontmatter, and skill/folder name alignment (Node 20+)
python -m pip install -r tools/requirements.txt # one-time: deps for the voxel + terrain toolkits (numpy, Pillow, scipy; optional opensimplex)
python tools/examples/example_bean.py # smoke-test the voxel toolkit (renders 3 PNGs + a fills JSON)
No build step for the markdown content — skills and agents are plain markdown
and take effect in the next Claude Code session after the plugin is reloaded.
The tools/ directory adds a small Python helper layer (the voxel and
terrain toolkits) that the builder skills run locally; the voxel toolkit is
numpy + Pillow, the terrain toolkit adds scipy (+ optional opensimplex), and
the builder harness is stdlib-only. They are referenced from skills via
${CLAUDE_PLUGIN_ROOT}/tools/…. These helpers
run in Claude Code (CLI or desktop app), where the agent has local Bash and
can read the PNGs they produce.
Architecture
This is the Claude-facing piece of a two-repository system. The MCP server is embedded in the Fabric mod and runs inside Minecraft — there is no separate server process and no behavior pack.
The mod has two entrypoints / two MCP endpoints from one jar:
Claude (Code / Desktop)
│ MCP over Streamable HTTP │ MCP over Streamable HTTP
│ minecraft-java (127.0.0.1:8765/mcp) │ minecraft-java-client (127.0.0.1:8766/mcp)
▼ ▼
McpServerMod (main entrypoint) McpClientMod (client entrypoint)
│ server API, server main thread │ client API, client/render thread
│ WORLD tools (level_/block_/entity_…) │ INSPECTION tools (view_capture, sense_*, client_status)
▼ ▼
the Minecraft world ◄──── same world, the client joins as a player ────►
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.
- 4d ago First seen · 125 lines · 2,351 tokens per session scan A 220937047efe
minecraft-java-fabric-claude-plugin CLAUDE.md is an instructions file published in the GitHub repository chapmanjw/minecraft-java-fabric-claude-plugin (6 stars, last pushed 7d ago), licensed MIT. It adds 2,351 tokens to every session, about $0.0118 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.
Other instructions, from other repositories
minecraft-dev-mcp CLAUDE.md
Instructions for MCDxAI/minecraft-dev-mcp, covering claude code context - minecraft dev mcp, project overview, release status, architecture and core services (src/services/).
minecraft-dev-mcp AGENTS.md
Instructions for MCDxAI/minecraft-dev-mcp, covering agent handbook – minecraft dev mcp, project snapshot, what agents should prioritize, architecture wayfinder (src/) and available mcp tools (for llm surfaces).
ashfox AGENTS.md
AGENTS.md instructions for sigee-min/ashfox, a project described as: Powerful Blockbench MCP server and AI-native low-poly workbench for modeling, pixel texturing, rigging, animation, and game-ready exports from a prompt.
minecraft-modding-mcp AGENTS.md
Instructions for adhi-jp/minecraft-modding-mcp, covering agents.md, purpose and scope, core release policy, public mcp contract (must) and change coupling rules (must).
minestom-mcp AGENTS.md
Instructions for RonaldBunk/minestom-mcp, a project described as: A stdio MCP server for Minestom, implemented with the Model Context Protocol SDK and TanStack AI tool definitions.
minecraft-document-mcp CLAUDE.md
Claude Code instructions for PYmili/minecraft-document-mcp, covering claude.md, 项目概述, 常用命令, 启动 mcp 服务器 and 开发模式(支持热重载).