shogi-mcp: Instructions file for Claude Code

CLAUDE.md

shogi-mcp CLAUDE.md is an instructions file for Claude Code from azumausu/shogi-mcp. It costs 783 tokens per session, scanned A, original, MIT.

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.

In plain words
What is it for?
For installing dependencies, starting the REST or MCP service, configuring the engine path and ports, and enabling debugging or evaluation files.
Why use it?
It gives the agent the project overview, commands, service details, and environment variables needed to work in the repository.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md; mentions Claude Code.

This is azumausu/shogi-mcp's own configuration. It tells Claude Code how to work on shogi-mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything shogi-mcp configures →

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.

agentmods badge for shogi-mcp CLAUDE.md

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.

agentmods 80×15 button for shogi-mcp CLAUDE.md

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00783 $0.00783
Opus 5.5 $0.00313 $0.00313
Sonnet 5.5 $0.00157 $0.00157
Haiku 4.5 $0.00078 $0.00078

Measured 2mo ago against content hash d144236081fb, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, 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 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 · 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

  1. 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.)
  2. 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
  3. 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.

  1. 2mo 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 (2 stars, last pushed 1y ago), licensed MIT. It adds 783 tokens to every session, about $0.0031 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 2026-08-31.

Related

shogi-mcp CLAUDE.md compared with instructions from other repositories

shogi-mcp CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
shogi-mcp CLAUDE.mdazumausu/shogi-mcpInstructions file21y agoMITA783Claude Code
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file196ktodayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file144ktodayMITA8,130Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file196ktodayMITA5,685GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchainInstructions file150ktodayMITA4,680Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file196ktodayMITA3,153GitHub Copilot
generative-ai-for-beginners AGENTS.mdmicrosoft/generative-ai-for-beginnersInstructions file124ktodayMITA2,981Codex, OpenCode