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/ibuildthecloud/chess-mcp/claude-mdgit clone --depth 1 https://github.com/ibuildthecloud/chess-mcpWrote 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/ibuildthecloud/chess-mcp/claude-md)<a href="https://agentmods.dev/instructions/ibuildthecloud/chess-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/ibuildthecloud/chess-mcp/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 | $0.00686 | $0.00686 |
| Opus 5 | $0.00343 | $0.00343 |
| Sonnet 5 | $0.00137 | $0.00137 |
| Haiku 4.5 | $0.00069 | $0.00069 |
Grade A, and why
chess-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 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 — 69 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 Model Context Protocol (MCP) server that implements an interactive chess game. It exposes chess functionality through MCP tools and provides a web-based chessboard interface using MCP-UI.
Development Commands
npm run dev- Start the development server (runstsx src/server.ts)npm run format- Format code with Biomenpm run lint- Lint and fix code with Biome
The server runs on http://localhost:3000/mcp
Architecture
MCP Server with Express Integration
This project uses a custom MCP middleware framework that integrates MCP servers with Express.js. Understanding this architecture is critical:
-
Server Creation Pattern (
src/server.ts:76-130):newServer()creates a newMcpServerinstance for each session- Tools are registered using
server.registerTool()with Zod schemas for validation - Tool handlers receive arguments and a context object with
sessionId
-
Custom MCP Middleware (
src/lib/mcp/middleware.ts):Middleware(newServer)function wraps the server creation function- Manages session lifecycle and transport layer
- Maps HTTP requests to MCP protocol using
StreamableHTTPServerTransport - Session IDs come from
mcp-session-idheader (seesrc/lib/mcp/header.ts) - Maintains a registry of active transports keyed by session ID
-
Game State Management (
src/lib/store.ts):- Games persist to
./games/{sessionId}.jsonas FEN strings loadGame(sessionId)retrieves existing games or returns nullsaveGame(sessionId, game)persists the current game state- Session ID from MCP context ties games to specific clients
- Games persist to
MCP Tool Implementation
Two tools are exposed:
chess_get_board_state: Returns current board state (no arguments)chess_move: Makes a move or starts new game- Takes
movestring (algebraic notation like "e4" or "new") - Validates moves using chess.js library
- Takes
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 · 69 lines · 686 tokens per session scan A a8f1a4a013fa
chess-mcp CLAUDE.md is an instructions file published in the GitHub repository ibuildthecloud/chess-mcp (5 stars, last pushed 11mo ago), licensed Apache-2.0. It adds 686 tokens to every session, about $0.0034 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.