black-souls-mcp: Instructions file for Claude Code

CLAUDE.md

black-souls-mcp CLAUDE.md is an instructions file for Claude Code, Codex from yk4464/black-souls-mcp. It costs 2,425 tokens per session, scanned B, original, MIT.

A development guide for a local MCP server that lets AI agents interact with the BLACK SOULS role-playing game through 36 tools. MCP is a standard way for an AI assistant to call external tools.

In plain words
What is it for?
Use it when building the server, checking types, running smoke or integration tests, debugging tool calls, or evaluating game actions such as menu navigation.
Why use it?
It documents the Windows commands, build checks, tests, game-runtime requirements, and safe handling of extracted game data.

Instructions file for Claude CodeCodex

Written for Codex and Claude Code: reads ~/.codex or $CODEX_HOME, but also the file is CLAUDE.md. Also seen: mentions CLAUDE.md; mentions Claude Code; mentions AGENTS.md.

This is yk4464/black-souls-mcp's own configuration. It tells Claude Code and Codex how to work on black-souls-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 black-souls-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to yk4464/black-souls-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/yk4464/black-souls-mcp/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/yk4464/black-souls-mcp

Made for: Claude Code, Codex.

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 black-souls-mcp CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/yk4464/black-souls-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/yk4464/black-souls-mcp/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/yk4464/black-souls-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/yk4464/black-souls-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 black-souls-mcp CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/yk4464/black-souls-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/yk4464/black-souls-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 2,425 This file is loaded in full into every session.
When invoked 2,425 The same file — it is already loaded in full.
Security scan B 1 finding. 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 $0.02425 $0.02425
Opus 5 $0.01213 $0.01213
Sonnet 5 $0.00485 $0.00485
Haiku 4.5 $0.00243 $0.00243

Measured 10d ago against content hash bb16a9596c77, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade B, and why

black-souls-mcp CLAUDE.md scanned grade B with 1 finding 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 10d 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

安装脚本:`install.ps1` 注册到 `~/.codex/config.toml`(带标记块平衡校验)并备份到 `runtime/backup/`;`uninstall.ps1` 移除注册块;`rollback.ps1` 按文件名内嵌时间戳恢复最近备份。
CLAUDE.md · 95 lines

How it starts

The opening of the file, as written. The whole thing — 95 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.

项目概述

black-souls-mcp 是一个本地 stdio MCP 服务器,让 AI 代理通过 36 个 black_souls_* 工具与运行中的 BLACK SOULS(RPG Maker VX Ace / RGSS3)游戏交互。服务器与游戏之间的通信完全基于文件系统(无网络、无 socket)。AGENTS.md 是面向所有代理的仓库准则;本文件补充 Claude Code 视角的操作细节,两者冲突时以 AGENTS.md 为准。

常用命令

本项目只在 Windows 上开发运行。在 bash 中请使用 npm.cmd 而非 npm

npm.cmd run check             # 提交前标准命令:清理 + 构建 + smoke + unit
npm.cmd run build             # 清理 dist/ 后编译 TypeScript
npm.cmd run typecheck         # 仅类型检查
npm.cmd test                  # 只跑 smoke + unit(依赖已有 dist/,改源码先 build)
npm.cmd run test:integration  # 需要已准备好的 runtime/game
npm.cmd run test:live         # 会真的启动游戏并发送键盘输入
node scripts/call_tool.mjs black_souls_status '{}'   # 手动调用单个工具(调试用)
node evals/runner.mjs menu_navigation                # 跑一个评测场景(需真实游戏)
.\check.ps1 -IncludeRuntime   # 源码 + 游戏副本 + Codex 注册整体校验

CI(.github/workflows/ci.yml)在 windows-latest + Node 18/22 上运行 npm run checknpm audit --audit-level=highnpm pack --dry-run

Python 维护脚本(仅在写入游戏数据时使用)

# 从 RGSSAD v3 归档提取单个文件(纯标准库,支持 SHA-256 门禁)
python scripts/extract_rgss3a_file.py Game.rgss3a "Data/Scripts.rvdata2" out.rvdata2

# 把 rgss/BlackSoulsBridge.rb 注入 Scripts.rvdata2(纯标准库、字节保持,优先使用)
python scripts/patch_rvdata2_binary.py Scripts.rvdata2 rgss/BlackSoulsBridge.rb --title Main --backup backup.rvdata2

注入语义是整体替换标题为 Main 的脚本条目;BlackSoulsBridge.rb 末尾自带 rgss_main { SceneManager.run },它就是新的 Main,绝不能删除这一行。重复注入是幂等安全的。备选 patch_rvdata2.py 需要 pip install -r requirements-tools.txt(rubymarshal)。

架构

源码结构(src/

文件 职责
index.ts MCP 入口;注册全部 36 个工具;execute()/result() 统一响应封装
bridge.ts 文件 IPC 全部逻辑:快照读取、sendSequencesendQuery、save/load/situation/health/wait
game.ts 启动(含 Game.exe SHA-256 门禁)、强制结束、存档列表、完整性信息
config.ts 路径解析(环境变量覆盖)
memory.ts AI 持久记忆:scratchpad / longterm / goals / session log(<ROOT>/memory/,原子写)
navigation.ts BFS 寻路 findPath(导出可单测)、navigateinteract
battle.ts battleAction 一次完成战斗回合

Read the full file on GitHub · 95 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. 10d ago First seen · 95 lines · 2,425 tokens per session scan B bb16a9596c77

Subscribe to this mod's changes

black-souls-mcp CLAUDE.md is an instructions file published in the GitHub repository yk4464/black-souls-mcp (2 stars, last pushed today), licensed MIT. It adds 2,425 tokens to every session, about $0.0121 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other instructions, from other repositories

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

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens