What is shogi-mcp CLAUDE.md?

A Claude Code instruction file for a Shogi AI engine wrapper. Shogi is a Japanese chess-like board game; the project exposes the engine through a web API and an MCP server.

For installing dependencies, starting the REST or MCP service, configuring the engine path and ports, and enabling debugging or evaluation files.

It gives the agent the project overview, commands, service details, and environment variables needed to work in the repository.

How azumausu/shogi-mcp configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to azumausu/shogi-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/azumausu/shogi-mcp/main/CLAUDE.md

Clone the repo

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

Your own site

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

Per session 783 This file is loaded in full into every session.

When invoked 783 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	$0.00783	$0.00783
Opus 5	$0.00392	$0.00392
Sonnet 5	$0.00157	$0.00157
Haiku 4.5	$0.00078	$0.00078

Measured 9d ago against content hash d144236081fb, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

shogi-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 9d 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 · 70 lines

How it starts

The opening of the file, as written. The whole thing — 70 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 Shogi AI Engine wrapper that provides both REST API and MCP (Model Context Protocol) server interfaces for a Shogi engine. The project wraps a native Shogi engine binary to provide modern API access for AI-powered Shogi analysis.

Key Commands

Running the Services

REST API Server: npm run start:rest - Starts the REST API server on port 8787 (configurable via PORT env var)
MCP Server: npm run start:mcp - Starts the MCP server for stdio communication
Install Dependencies: npm install - Installs Express and MCP SDK dependencies

Environment Variables

ENGINE_PATH: Path to the Shogi engine binary (default: ./engine/engine)
PORT: REST server port (default: 8787)
REST_BASE: MCP server's REST API base URL (default: http://localhost:8787)
DEBUG: Set to "1" to enable engine communication debug logs
EVAL_FILE: Optional path to evaluation file for the engine
EVAL_DIR: Optional directory containing evaluation files

Architecture

Core Components

AIEngine Class (engine.js):
- Manages USI protocol communication with the native Shogi engine binary
- Handles engine lifecycle, position setup, and analysis requests
- Uses mutex for thread-safe sequential operations
- Parses engine info lines to extract evaluation data (score, PV, depth, etc.)
REST API Server (rest.js):
- Express server providing HTTP endpoints for engine analysis
- Main endpoint: GET /analyze with query parameters:
  - sfen (required): Board position in SFEN format
  - depth: Search depth (default: 30, max: 30)
  - multipv: Number of best moves to analyze (default: 10, max: 10)
  - threads: Engine threads (default: 1, max: 8)
  - forceMove: Optional move to analyze after the given position
MCP Server (mcp-server.mjs):
- Implements Model Context Protocol for AI agent integration
- Provides three tools:
  - ping: Health check tool
  - analyze: Full position analysis with MultiPV
  - eval_at: Evaluate position after a specific move
- Communicates with REST API internally

Read the full file on GitHub · 70 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.

9d ago First seen · 70 lines · 783 tokens per session scan A d144236081fb

Subscribe to this mod's changes

shogi-mcp CLAUDE.md is an instructions file published in the GitHub repository azumausu/shogi-mcp (1 stars, last pushed 1y ago), licensed MIT. It adds 783 tokens to every session, about $0.0039 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.

Game development

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

shogi-mcp: Instructions file for Claude Code