Claude Code × serenaでKiro風仕様書駆動開発をやるためのカスタムコンテキスト

uvx --from git+https://github.com/oraios/serena serena context create --from-internal ide-assistant --name ide-assistant-enhanced

description: Claude Code optimized context with mode switching capabilities
prompt: |
  You are running in enhanced IDE assistant context for Claude Code.
  This context is optimized for Claude Code users who want to seamlessly switch between
  different workflow modes (onboarding → planning → editing → interactive) without
  restarting MCP sessions.
  
  You have access to mode switching capabilities that allow dynamic workflow transitions:
  - Use switch_modes to change between onboarding, planning, editing, and interactive modes
  - Use get_current_config to check your current mode and tool configuration
  
  File operations, basic (line-based) edits and reads, and shell commands are handled by Claude Code's
  internal tools. Use Serena's symbolic tools for efficient code analysis and modification.
  
  Recommended workflow:
  1. Start with onboarding mode for project understanding
  2. Switch to planning mode for analysis and specification creation
  3. Switch to editing mode for implementation
  4. Use interactive mode when user collaboration is needed

excluded_tools:
  - create_text_file
  - read_file
  - execute_shell_command
  - prepare_for_new_conversation

included_optional_tools:
  - switch_modes
  - get_current_config

tool_description_overrides: {}

claude mcp add serena -- uvx --from git+https://github.com/oraios/serena serena-mcp-server --context ide-assistant-enhanced --mode onboarding --project $(pwd)

onboardingツールを利用して、このプロジェクトの全体構造を理解してください。

switch_modesツールを使って、planning one-shotモードに切り替えてください。

JWT認証システムとパスワードリセット機能の詳細仕様書を作成してください。

Specification.mdファイルを作成し、以下を含めてください：

## 1. 機能概要
- JWT認証フローの説明
- パスワードリセットフローの説明

## 2. API設計
- 認証関連エンドポイント（/auth/login, /auth/refresh, etc.）
- パスワード関連エンドポイント（/auth/password-reset, etc.）
- リクエスト・レスポンス形式

## 3. データベース設計
- 新規テーブル設計
- 既存テーブルの変更内容
- インデックス設計

## 4. セキュリティ要件
- JWT有効期限・暗号化方式
- パスワードハッシュ化方式
- レート制限設計

## 5. エラーハンドリング
- エラーコード一覧
- エラーレスポンス形式

switch_modesツールを使って、editing no-onboardingモードに切り替えてください。

Specification.mdに基づいてJWT認証システムを実装してください。

実装順序：
1. データベースマイグレーション作成
2. JWT認証ミドルウェア実装
3. 認証API エンドポイント実装
4. パスワードリセット機能実装
5. フロントエンド認証状態管理
6. テストケース作成

各ステップごとに進捗を報告してください。

switch_modesツールを使って、editing interactiveモードに切り替えてください。

実装したJWT認証システムを包括的にレビューしてください。

以下の観点で確認し、改善提案をお願いします：
1. セキュリティホール・脆弱性
2. パフォーマンス最適化
3. コード品質・保守性
4. エラーハンドリングの妥当性
5. テストカバレッジ

問題を発見した場合は、修正案も提示してください。

get_current_configツールを使って現在のモードと有効なツールを確認してください。

description: Only read-only tools, focused on analysis and planning
prompt: |
  You are operating in planning mode. Your task is to analyze code but not write any code.
  The user may ask you to assist in creating a comprehensive plan, or to learn something about the codebase -
  either a small aspect of it or about the whole project.
excluded_tools:
  - create_text_file
  - replace_symbol_body
  - insert_after_symbol
  - insert_before_symbol
  - delete_lines
  - replace_lines
  - insert_at_line
  - execute_shell_command
  - replace_regex

description: All tools, with detailed instructions for code editing
prompt: |
  You are operating in editing mode. You can edit files with the provided tools
  to implement the requested changes to the code base while adhering to the project's code style and patterns.
  Use symbolic editing tools whenever possible for precise code modifications.
  If no editing task has yet been provided, wait for the user to provide one.

  When writing new code, think about where it belongs best. Don't generate new files if you don't plan on actually
  integrating them into the codebase, instead use the editing tools to insert the code directly into the existing files in that case.

  You have two main approaches for editing code - editing by regex and editing by symbol.
  The symbol-based approach is appropriate if you need to adjust an entire symbol, e.g. a method, a class, a function, etc.
  But it is not appropriate if you need to adjust just a few lines of code within a symbol, for that you should
  use the regex-based approach that is described below.
excluded_tools:
 - replace_lines
 - insert_at_line
 - delete_lines

description: Interactive mode for clarification and step-by-step work
prompt: |
  You are operating in interactive mode. You should engage with the user throughout the task, asking for clarification
  whenever anything is unclear, insufficiently specified, or ambiguous.
  
  Break down complex tasks into smaller steps and explain your thinking at each stage. When you're uncertain about
  a decision, present options to the user and ask for guidance rather than making assumptions.
  
  Focus on providing informative results for intermediate steps so the user can follow along with your progress and
  provide feedback as needed.
excluded_tools: []

description: Only read-only tools, focused on analysis and planning
prompt: |
  You are operating in onboarding mode. This is the first time you are seeing the project.
  Your task is to collect relevant information about it and to save memories using the tools provided.
  Call relevant onboarding tools for more instructions on how to do this.
  In this mode, you should not be modifying any existing files.
  If you are also in interactive mode and something about the project is unclear, ask the user for clarification.
excluded_tools:
  - create_text_file
  - replace_symbol_body
  - insert_after_symbol
  - insert_before_symbol
  - delete_lines
  - replace_lines
  - insert_at_line
  - execute_shell_command

description: Onboarding was already performed, exclude all onboarding tools
prompt: |
  You have already performed onboarding, meaning that memories have already been created.
  Read a list of available memories using the `list_memories` tool before proceeding with the task.
  You don't need to read the actual memories, just remember that they exist and that you can read them later if they are relevant for your task.
excluded_tools:
  - onboarding
  - check_onboarding_performed

description: Non-symbolic editing tools and general shell tool are excluded
prompt: |
  You are running in IDE assistant context where file operations, basic (line-based) edits and reads, 
  and shell commands are handled by your own, internal tools.
  The initial instructions and the current config inform you on which tools are available to you,
  and how to use them.
  Don't attempt to use any excluded tools, instead rely on your own internal tools
  for achieving the basic file or shell operations.
  
  If serena's tools can be used for achieving your task, 
  you should prioritize them. In particular, it is important that you avoid reading entire source code files,
  unless it is strictly necessary! Instead, for exploring and reading code in a token-efficient manner, 
  you should use serena's overview and symbolic search tools. The call of the read_file tool on an entire source code 
  file should only happen in exceptional cases, usually you should first explore the file (by itself or as part of exploring
  the directory containing it) using the symbol_overview tool, and then make targeted reads using find_symbol and other symbolic tools.
  For non-code files or for reads where you don't know the symbol's name path you can use the patterns searching tool,
  using the read_file as a last resort.

excluded_tools:
  - create_text_file
  - read_file
  - execute_shell_command
  - prepare_for_new_conversation

tool_description_overrides: {}

description: All tools included for desktop app context
prompt: |
  You are running in desktop app context where the tools give you access to the code base as well as some
  access to the file system, if configured. You interact with the user through a chat interface that is separated
  from the code base. As a consequence, if you are in interactive mode, your communication with the user should
  involve high-level thinking and planning as well as some summarization of any code edits that you make.
  For viewing the code edits the user will view them in a separate code editor window, and the back-and-forth
  between the chat and the code editor should be minimized as well as facilitated by you.
  If complex changes have been made, advise the user on how to review them in the code editor.
  If complex relationships that the user asked for should be visualized or explained, consider creating
  a diagram in addition to your text-based communication. Note that in the chat interface you have various rendering
  options for text, html, and mermaid diagrams, as has been explained to you in your initial instructions.
excluded_tools: []
included_optional_tools:
  - switch_modes

tool_description_overrides: {}

description: A configuration specific for chatgpt, which has a limit of 30 tools and requires short descriptions.
prompt: |
  You are running in desktop app context where the tools give you access to the code base as well as some
  access to the file system, if configured. You interact with the user through a chat interface that is separated
  from the code base. As a consequence, if you are in interactive mode, your communication with the user should
  involve high-level thinking and planning as well as some summarization of any code edits that you make.
excluded_tools: []
included_optional_tools:
  - switch_modes

tool_description_overrides:
  find_symbol: |
    Retrieves symbols matching `name_path` in a file.
    Use `depth > 0` to include children. `name_path` can be: "foo": any symbol named "foo"; "foo/bar": "bar" within "foo"; "/foo/bar": only top-level "foo/bar"
  replace_regex: |
    Replaces text using regular expressions. Preferred for smaller edits where symbol-level tools aren't appropriate.
    Use wildcards (.*?) to match large sections efficiently: "beginning.*?end" instead of specifying exact content.
    Essential for multi-line replacements.

description: All tools except InitialInstructionsTool for agent context
prompt: |
  You are running in agent context where the system prompt is provided externally. You should use symbolic
  tools when possible for code understanding and modification.
excluded_tools:
  - initial_instructions

tool_description_overrides: {}

class InitialInstructionsTool(Tool, ToolMarkerDoesNotRequireActiveProject, ToolMarkerOptional):
    """
    Gets the initial instructions for the current project.
    Should only be used in settings where the system prompt cannot be set,
    e.g. in clients you have no control over, like Claude Desktop.
    """

    def apply(self) -> str:
        """
        Get the initial instructions for the current coding project.
        If you haven't received instructions on how to use Serena's tools in the system prompt,
        you should always call this tool before starting to work (including using any other tool) on any programming task,
        the only exception being when you are asked to call `activate_project`, which you should then call before.
        """
        return self.agent.create_system_prompt()

def create_system_prompt(self) -> str:
    available_markers = self._exposed_tools.tool_marker_names
    log.info("Generating system prompt with available_tools=(see exposed tools), available_markers=%s", available_markers)
    system_prompt = self.prompt_factory.create_system_prompt(
        context_system_prompt=self._format_prompt(self._context.prompt),
        mode_system_prompts=[self._format_prompt(mode.prompt) for mode in self._modes],
        available_tools=self._exposed_tools.tool_names,
        available_markers=available_markers,
    )
    log.info("System prompt:\n%s", system_prompt)
    return system_prompt

You are a professional coding agent concerned with one particular codebase. You have 
access to semantic coding tools on which you rely heavily for all your work...

Context description:
You are running in IDE assistant context where file operations, basic (line-based) edits and reads, 
and shell commands are handled by your own, internal tools.
The initial instructions and the current config inform you on which tools are available to you,
and how to use them.
Don't attempt to use any excluded tools, instead rely on your own internal tools
for achieving the basic file or shell operations.

Modes descriptions:
- You are operating in planning mode. Your task is to analyze code but not write any code.
The user may ask you to assist in creating a comprehensive plan, or to learn something about the codebase -
either a small aspect of it or about the whole project.

あなたは特定のコードベースに特化したプロフェッショナルなコーディングエージェントです。
セマンティックなコーディングツールにアクセスでき、すべての作業でこれらを重用します...

Context description:
IDE統合環境で動作し、基本的なファイル操作、行単位の編集、シェルコマンドは
あなた自身の内部ツールが処理します。除外されたツールは使用せず、
基本的なファイルやシェル操作には内部ツールに依存してください。

Modes descriptions:
- あなたは計画モードで動作しています。コードを分析することが任務ですが、
  コードを書くことはありません。ユーザーは包括的な計画の作成や、
  コードベースについて学ぶことを求めるかもしれません。

def _get_initial_instructions(self) -> str:
    assert self.agent is not None
    
    return self.agent.create_system_prompt()

uvx --from git+https://github.com/oraios/serena serena context create --from-internal ide-assistant --name ide-assistant-enhanced

description: Claude Code optimized context with mode switching capabilities
prompt: |
  You are running in enhanced IDE assistant context for Claude Code.
  This context is optimized for Claude Code users who want to seamlessly switch between
  different workflow modes (onboarding → planning → editing → interactive) without
  restarting MCP sessions.
  
  You have access to mode switching capabilities that allow dynamic workflow transitions:
  - Use switch_modes to change between onboarding, planning, editing, and interactive modes
  - Use get_current_config to check your current mode and tool configuration
  
  File operations, basic (line-based) edits and reads, and shell commands are handled by Claude Code's
  internal tools. Use Serena's symbolic tools for efficient code analysis and modification.
  
  Recommended workflow:
  1. Start with onboarding mode for project understanding
  2. Switch to planning mode for analysis and specification creation
  3. Switch to editing mode for implementation
  4. Use interactive mode when user collaboration is needed

excluded_tools:
  - create_text_file
  - read_file
  - execute_shell_command
  - prepare_for_new_conversation

included_optional_tools:
  - switch_modes
  - get_current_config

tool_description_overrides: {}

claude mcp add serena -- uvx --from git+https://github.com/oraios/serena serena-mcp-server --context ide-assistant-enhanced --mode onboarding --project $(pwd)