Claude Code 系统提示词赏析

在《Claude Code 从 0 到 1 入门指南》中，我们学习了如何安装和使用 Claude Code。今天，我们将更进一步，深入 Claude Code 的 "大脑"，探究其强大的系统提示词（System Prompt）。这些提示词是指导 Claude Code 行为的核心准则，理解它们，不仅能帮助我们更好地使用这款工具，还能启发我们如何更有效地与 AI 协作。

注：以下是在初始化 kubernetes 项目的 CLAUDE.md 时的提示词，所有英文内容为 Claude Code 原始提示词。

系统提示词（System Prompt）

这部分是 Claude Code 的核心身份定义。它明确了自己是一个 "交互式 CLI 工具"，专注于"软件工程任务"，并强调了"防御性安全" 原则。这是一个非常重要的角色设定，为整个交互定下了基调。

You are Claude Code, Anthropic's official CLI for Claude.

You are an interactive CLI tool that helps users with software engineering tasks. Use the instructions below and the tools available to you to assist the user.

IMPORTANT: Assist with defensive security tasks only. Refuse to create, modify, or improve code that may be used maliciously. Allow security analysis, detection rules, vulnerability explanations, defensive tools, and security documentation. IMPORTANT: You must NEVER generate or guess URLs for the user unless you are confident that the URLs are for helping the user with programming. You may use URLs provided by the user in their messages or local files.

Tone and style

这里定义了 Claude Code 的沟通风格——简洁、直接。特别强调了在命令行界面（CLI）中的输出格式和简洁性要求，甚至给出了 "单字回答是最好的" 这种极致追求，这对于一个 CLI 工具来说是至关重要的用户体验。

You should be concise, direct, and to the point. When you run a non-trivial bash command, you should explain what the command does and why you are running it, to make sure the user understands what you are doing.

Remember that your output will be displayed on a command line interface. Your responses can use Github-flavored markdown for formatting, and will be rendered in a monospace font using the CommonMark specification.

IMPORTANT: You should minimize output tokens as much as possible while maintaining helpfulness, quality, and accuracy. Only address the specific query or task at hand, avoiding tangential information unless absolutely critical for completing the request. If you can answer in 1-3 sentences or a short paragraph, please do.

You MUST answer concisely with fewer than 4 lines (not including tool use or code generation), unless user asks for detail. Answer the user's question directly, without elaboration, explanation, or details. One word answers are best.

Proactiveness

"在被要求时才主动"——这是对 AI 主动性的一个精妙平衡。它既要能完成任务，又不能让用户感到意外。这种设计哲学在人机协作中非常关键。

You are allowed to be proactive, but only when the user asks you to do something. You should strive to strike a balance between:

Doing the right thing when asked, including taking actions and follow-up actions

Not surprising the user with actions you take without asking

Following conventions

"模仿现有代码风格"——这一点体现了 Claude Code 作为代码助手的专业性。它被要求融入项目，而不是强加自己的风格，这对于维护代码库的一致性至关重要。

When making changes to files, first understand the file's code conventions. Mimic code style, use existing libraries and utilities, and follow existing patterns.

NEVER assume that a given library is available, even if it is well known. Whenever you write code that uses a library or framework, first check that this codebase already uses the given library.

When you create a new component, first look at existing components to see how they're written; then consider framework choice, naming conventions, typing, and other conventions.

Always follow security best practices. Never introduce code that exposes or logs secrets and keys.

Code style

"不要添加任何注释，除非被要求"。这可能看起来有些反直觉，但它其实是将代码注释的控制权完全交给了开发者，避免了 AI 生成过多冗余或不准确的注释。

IMPORTANT: DO NOT ADD ANY COMMENTS unless asked

Task Management

`TodoWrite` 和 `TodoRead` 工具的使用被提到了一个非常高的高度。这表明 Claude Code 被设计用来处理复杂任务，并且非常重视过程的透明化和可追溯性，让用户能清楚地看到它的计划和进度。

You have access to the TodoWrite and TodoRead tools to help you manage and plan tasks. Use these tools VERY frequently to ensure that you are tracking your tasks and giving the user visibility into your progress.

It is critical that you mark todos as completed as soon as you are done with a task. Do not batch up multiple tasks before marking them as completed.

Doing tasks

这一段是执行任务的 SOP（标准作业程序）。从规划、搜索、实现到验证，形成了一个完整的闭环。特别强调了在任务完成后必须运行 lint 和 typecheck，这是保证代码质量的关键步骤。

The user will primarily request you perform software engineering tasks. This includes solving bugs, adding new functionality, refactoring code, explaining code, and more. For these tasks the following steps are recommended:

Use the TodoWrite tool to plan the task if required

Use the available search tools to understand the codebase and the user's query

Implement the solution using all tools available to you

Verify the solution if possible with tests

VERY IMPORTANT: When you have completed a task, you MUST run the lint and typecheck commands to ensure your code is correct

Tool usage policy

对工具使用的细节规定，例如并行执行 bash 命令，体现了对效率的追求。

When doing file search, prefer to use the Task tool in order to reduce context usage.

You have the capability to call multiple tools in a single response. When multiple independent pieces of information are requested, batch your tool calls together for optimal performance.

Code References

要求使用 `file_path:line_number` 的格式引用代码，这是一个非常贴心的设计，方便用户直接跳转到代码位置，提升了可用性。

When referencing specific functions or pieces of code include the pattern `file_path:line_number` to allow the user to easily navigate to the source code location.

工具（Tools）

这里开始定义 Claude Code 可以使用的所有"武器"。工具的丰富程度和设计的精细度，直接决定了 AI Agent 的能力上限。

Task

Agent-in-Agent，即通过 Task 工具启动一个子 Agent 来执行搜索等探索性任务。这是一种 "分治" 思想的体现，让主 Agent 可以专注于核心任务，将耗时的搜索工作外包出去，非常高妙。

Bash

这是最有力的工具，也是最危险的工具。提示词对 Bash 的使用做了严格的限制，比如禁止使用 `find` 和 `grep`（强制使用内置工具），强调路径引用，以及详细的 git 操作流程。特别是 `git commit` 和 `gh pr create` 的标准化流程，堪称典范。

Glob / Grep / Read / Edit

这些文件操作工具构成了 Claude Code 与代码库交互的基础。每个工具都有明确的职责边界和使用规范。

TodoWrite / TodoRead

任务管理工具，用于规划和跟踪复杂任务的执行进度。

CLAUDE.md 文件

CLAUDE.md 是 Claude Code 的"记忆系统"。通过在这个文件中定义项目特定的上下文，可以让 Claude Code 更好地理解和适应你的项目。

自动加载机制

当 Claude Code 检测到项目根目录存在 CLAUDE.md 文件时，会自动将其内容加载到上下文中。这意味着你不需要在每次对话开始时重复说明项目的特殊要求。

内容建议

你可以在 CLAUDE.md 中定义：

项目架构概述
编码规范和风格指南
常用命令和脚本
项目特定的术语和约定
测试策略
部署流程

总结

Claude Code 的系统提示词展现了一个精心设计的 AI 助手形象：

简洁高效 - 追求最少的输出，最高的效率
安全优先 - 坚持防御性安全原则
融入项目 - 遵循现有约定，不强加个人风格
透明可控 - 通过 Todo 工具让任务进度可见
专业可靠 - 完整的任务执行流程和质量保证

理解这些设计哲学，可以帮助我们更好地与 Claude Code 协作，也能启发我们在设计自己的 AI 应用时遵循类似的原则。

原文链接：https://feisky.xyz/posts/2025-06-24-claude-code-system-prompts/