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/cuspymd/mcp-server-mod/claude-mdgit clone --depth 1 https://github.com/cuspymd/mcp-server-modWrote 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/cuspymd/mcp-server-mod/claude-md)<a href="https://agentmods.dev/instructions/cuspymd/mcp-server-mod/claude-md"><img src="https://agentmods.dev/badge/instructions/cuspymd/mcp-server-mod/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 | $0.01265 | $0.01265 |
| Opus 5 | $0.00633 | $0.00633 |
| Sonnet 5 | $0.00253 | $0.00253 |
| Haiku 4.5 | $0.00127 | $0.00127 |
Grade A, and why
mcp-server-mod 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 3d 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 — 135 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.
Project Overview
This is a Minecraft Fabric mod that implements an MCP (Model Context Protocol) server, allowing LLMs like Claude to execute Minecraft commands through HTTP requests. The mod runs on Fabric 26.2 and creates an HTTP server on port 8080 that accepts MCP protocol messages.
Development Commands
Building the Mod
./gradlew build # Build the mod JAR
./gradlew clean build # Clean build from scratch
Running in Development
./gradlew runClient # Run Minecraft client with the mod loaded
./gradlew runServer # Run Minecraft server with the mod loaded
Code Quality
./gradlew check # Run all checks and tests
./gradlew test # Run unit tests only
Architecture Overview
Core Components
- MCPServerModClient: Client-side entry point that starts the HTTP MCP server
- HTTPMCPServer: HTTP server implementation (port 8080) that handles MCP protocol
- CommandExecutor: Executes Minecraft commands with safety validation and result capture
- SafetyValidator: Validates commands against security rules and size limits
- BlockCompressor: Optimizes block change representations by grouping connected regions
- BlockScanner: Scans world areas to detect block changes and structures
- MCPConfig: Configuration management for server settings and safety rules
Package Structure
The mod uses Fabric's split environment feature with separate client and main source sets:
src/
├── main/java/cuspymd/mcp/mod/ # Server-side and shared code
│ ├── MCPServerMod.java # Main mod class
│ ├── MCPServerModServer.java # Dedicated server entry point
│ ├── config/MCPConfig.java # Configuration management
│ ├── server/MCPProtocol.java # MCP protocol definitions
│ ├── bridge/HTTPMCPServer.java # HTTP server implementation
│ ├── command/ # Shared command safety/executor interfaces
│ └── utils/ # Shared utility interfaces and compression
├── client/java/cuspymd/mcp/mod/ # Client-side code
│ ├── MCPServerModClient.java # Client mod initializer
│ ├── command/ # Client command execution system
│ │ ├── CommandExecutor.java
│ │ ├── SafetyValidator.java
│ │ ├── CommandResult.java
│ │ └── ChatMessageCapture.java
│ └── utils/ # Utility classes
│ ├── BlockCompressor.java
│ ├── BlockScanner.java
│ ├── CommandParser.java
│ ├── CoordinateUtils.java
│ └── PlayerInfoProvider.java
└── test/java/cuspymd/mcp/mod/ # Unit tests
└── BlockCompressorTest.java
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.
- 3d ago First seen · 135 lines · 1,265 tokens per session scan A 4a92762e1a1e
mcp-server-mod CLAUDE.md is an instructions file published in the GitHub repository cuspymd/mcp-server-mod (10 stars, last pushed 1mo ago), licensed CC0-1.0. It adds 1,265 tokens to every session, about $0.0063 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
GameDesignOS AGENTS.md
Instructions for DY-2026/GameDesignOS, covering gamedesignos agent 入口, 默认接法, agent 执行规则, 什么时候用整个项目 and 每个 skill 单独怎么用.
claudemon CLAUDE.md
Instructions for zamarrowski/claudemon, covering ai agent guidelines, project shape, general guidelines, general rules and guards & defensive code.
unity-code-style-guide AGENTS.md
Instructions for krogh-jacobsen/unity-code-style-guide, covering agents.md — unity 6 c, project setup — edit this block, never do these — they corrupt the project, deprecated in unity 6 and if you read nothing else.
nes-php-glfw copilot-instructions.md
Instructions for oliverearl/nes-php-glfw, covering github copilot development guidelines for nes emulator, agent document source of truth, project overview, code style & standards and documentation.
game-and-watch-retro-go-sd CLAUDE.md
Claude Code instructions for sylverb/game-and-watch-retro-go-sd, covering claude.md, what this project is, build / flash workflow, architecture and three storage tiers, one elf.
Cities2-MCP AGENTS.md
Instructions for mayor-modder/Cities2-MCP, covering agent rules, workspace safety, commit and pr safety, public-facing writing and merge and release gates.