mise use -g npm:@anthropic/claude-code

$ claude

╭──────────────────────────────────────────────────────────╮
│ ✻ Welcome to Claude Code!                                │
│                                                          │
│   /help for help, /status for your current setup         │
│                                                          │
│   cwd: /Users/cffnpwr/git/github.com/cffnpwr/deadman-rs  │
╰──────────────────────────────────────────────────────────╯


 What's new:
  • Fixed a memory leak causing a MaxListenersExceededWarning message to appear

╭─────────────────────────────────────────────────────────────────────────────╮
│ > Try "how does libpcap.rs work?"                                           │
╰─────────────────────────────────────────────────────────────────────────────╯
  ? for shortcuts

# CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working
with code in this repository.

## General Principles

YOU MUST: Respond in Japanese when communicating with users and writing
technical documentation.

YOU MUST: Write CLAUDE.md files and system instructions in English for
optimal processing.

YOU MUST: When insufficient information is provided to complete a user's
request, clearly state what information is missing and specify what additional
details would be needed to fulfill the request.

YOU MUST: If you don't know something, explicitly state that you don't know
rather than guessing or providing uncertain information.

YOU MUST: When writing CLAUDE.md using `/init` command, always write rules in
English and include detailed directory structure to provide comprehensive
project context

IMPORTANT: English is preferred for CLAUDE.md because Claude Code processes
rules more efficiently in English context

## Git Operations Guidelines

YOU MUST: Use Git slash commands for all Git operations when available.

YOU MUST: When users request Git operations through natural language (e.g., "コミットしてください", "プッシュしてください"),
always respond by directing them to use the appropriate slash command instead.

NEVER: Perform Git operations directly when requested through natural language.

YOU MUST: Explain which slash command should be used and why slash commands are preferred for Git operations.

## Code Quality Guidelines

@instructions/code_quality.md

## Editor Configuration

@instructions/editor.md

## Important Instruction Reminders

@instructions/reminders.md

# Claude Code Instruction Reflection

You are an expert in prompt engineering, specializing in optimizing AI code
assistant instructions. Your task is to analyze and improve the instructions
for Claude Code.

Follow these steps carefully:

## 1. Analysis Phase

Review the chat history in your context window.

Then, examine the current Claude instructions, commands and config
<claude_instructions>
/CLAUDE.md
/.claude/commands/*
**/CLAUDE.md
.claude/settings.json
.claude/settings.local.json
</claude_instructions>

Analyze the chat history, instructions, commands and config to identify areas
that could be improved. Look for:

- Inconsistencies in Claude's responses
- Misunderstandings of user requests
- Areas where Claude could provide more detailed or accurate information
- Opportunities to enhance Claude's ability to handle specific types of
queries or tasks
- New commands or improvements to a commands name, function or response
- Permissions and MCPs we've approved locally that we should add to the
config, especially if we've added new tools or require them for the
command to work

## 2. Interaction Phase

Present your findings and improvement ideas to the human. For each suggestion:
a) Explain the current issue you've identified
b) Propose a specific change or addition to the instructions
c) Describe how this change would improve Claude's performance

Wait for feedback from the human on each suggestion before proceeding.
If the human approves a change, move it to the implementation phase.
If not, refine your suggestion or move on to the next idea.

## 3. Implementation Phase

For each approved change:
a) Clearly state the section of the instructions you're modifying
b) Present the new or modified text for that section
c) Explain how this change addresses the issue identified in the
analysis phase

## 4. Output Format

Present your final output in the following structure:

```xml
<analysis>
[List the issues identified and potential improvements]
</analysis>

<improvements>
[For each approved improvement:
1. Section being modified
2. New or modified instruction text
3. Explanation of how this addresses the identified issue]
</improvements>

<final_instructions>
[Present the complete, updated set of instructions for Claude, incorporating
all approved changes]
</final_instructions>
```

Remember, your goal is to enhance Claude's performance and consistency while
maintaining the core functionality and purpose of the AI assistant. Be thorough
in your analysis, clear in your explanations, and precise in your
implementations.

# Git Commit

YOU MUST: Follow the Git guidelines defined in @../../instructions/git.md

YOU MUST: Use Git MCP server tools for all Git operations when available.

YOU MUST: Only use command line Git operations for functions not supported by the Git MCP server.

Execute the following workflow:

1. Check current git status and staged changes using git_status
2. Review changes with git_diff (both staged and unstaged)
3. **DISPLAY COMMIT CONFIRMATION** - Present the following information to the user for confirmation:
   - **Target Branch**: Show the current branch name
   - **Files to be committed**: List all staged files with their status (Added, Modified, Deleted, etc.)
   - **Proposed commit message**: Show the commit message that will be used
4. **WAIT FOR USER CONFIRMATION** - Ask user to confirm before proceeding with the commit
5. Create commit using git_commit with proper Conventional Commits format and Japanese message
6. Verify commit was created successfully

## Commit Message Format

YOU MUST: Follow Conventional Commits standards with this specific format:

```text
<type> <emoji>: <commit message>
```

## Commit Types

YOU MUST: Choose from the following types:

- **build**: Changes that affect the build system or external dependencies
- **ci**: Changes to CI configuration files and scripts
- **docs**: Documentation only changes
- **feat**: A new feature
- **fix**: A bug fix
- **perf**: A code change that improves performance
- **refactor**: A code change that neither fixes a bug nor adds a feature
- **style**: Changes that do not affect the meaning of the code
- **test**: Adding missing tests or correcting existing tests

## Commit Message Guidelines

YOU MUST: Write commit messages on a single line without line breaks
YOU MUST: Write commit messages concisely and descriptively
YOU MUST: Use noun-ending form (体言止め) in Japanese
YOU MUST: Clearly indicate what was changed or implemented

## Commit Granularity Guidelines

YOU MUST: Make atomic commits - one logical change per commit
YOU MUST: Separate different types of changes into different commits
NEVER: Mix features and bug fixes in a single commit
NEVER: Combine multiple unrelated changes in one commit

Examples of proper commit separation:

- **Wrong**: `feat ✨: ログイン機能の追加とパスワードバリデーションのバグ修正`
- **Correct**:
  - `feat ✨: ログイン機能の追加`
  - `fix 🐛: パスワードバリデーションのバグ修正`

YOU MUST: For large features, break down into smaller, logical commits:

- **Wrong**: `feat ✨: ユーザー管理システム全体の実装`
- **Correct**:
  - `feat ✨: ユーザー登録機能の実装`
  - `feat ✨: ユーザー認証機能の実装`
  - `feat ✨: ユーザープロフィール管理機能の実装`

## Examples

- `feat ✨: ログイン機能の実装`
- `fix 🐛: データベース接続エラーの修正`
- `docs 📚: README.mdの更新`
- `refactor ♻️: ユーザー認証ロジックのリファクタリング`