安装Git在Windows机器上安装了Git后Claude code会使用Git自带的Linux bash command。善用plugin写好的代码调用对应编程语言的插件执行代码语法检查要比使用AI更高效可靠。插件可以在插件市场下载如果不想使用在线市场也可以从官方的github[https://github.com/anthropics/claude-plugins-official]下载到本地。所有的插件都需要先安装对应的编程语言服务器比如python使用的是pyright可以使用下面的命令安装 pip install pyright或者 npm install -g pyright然后在claude code启动时执行 clause --plugin-dir path-to-plugin进入claude code后输入/plugin可以选择对应的插件然后选择安装。安装之后使用下面的命令加载 /reload-plugins然后就可以在给claude code的任务中调用比如使用pyright插件对代码进行检查。官方提供的语言插件| Language | Plugin Name | Required Binary ||------------|-------------------|------------------------------|| C/C | clangd-lsp | clangd || C# | csharp-lsp | csharp-ls || Go | gopls-lsp | gopls || Java | jdtls-lsp | jdtls || Kotlin | kotlin-lsp | kotlin-language-server || Lua | lua-lsp | lua-language-server || PHP | php-lsp | intelephense || Python | pyright-lsp | pyright-langserver || Rust | rust-analyzer-lsp| rust-analyzer || Swift | swift-lsp | sourcekit-lsp || TypeScript | typescript-lsp | typescript-language-server |限制claude code访问敏感信息在测试过程中会在配置文件中配置API key等敏感信息不希望被Claude code读取不小心上传到外面的AI服务器可以在全局~/.claude/settings.json或者项目.claude/settings.json级别的settings.json文件中定义访问权限比如json{permissions: {deny: [Read(/secrets/**),Read(*.env),Read(/config/private.json)]}}大师在用的Claude.md[https://raw.githubusercontent.com/multica-ai/andrej-karpathy-skills/refs/heads/main/CLAUDE.md]# CLAUDE.mdBehavioral guidelines to reduce common LLM coding mistakes. Merge with project-specific instructions as needed.**Tradeoff:** These guidelines bias toward caution over speed. For trivial tasks, use judgment.## 1. Think Before Coding**Dont assume. Dont hide confusion. Surface tradeoffs.**Before implementing:- State your assumptions explicitly. If uncertain, ask.- If multiple interpretations exist, present them - dont pick silently.- If a simpler approach exists, say so. Push back when warranted.- If something is unclear, stop. Name whats confusing. Ask.## 2. Simplicity First**Minimum code that solves the problem. Nothing speculative.**- No features beyond what was asked.- No abstractions for single-use code.- No flexibility or configurability that wasnt requested.- No error handling for impossible scenarios.- If you write 200 lines and it could be 50, rewrite it.Ask yourself: Would a senior engineer say this is overcomplicated? If yes, simplify.## 3. Surgical Changes**Touch only what you must. Clean up only your own mess.**When editing existing code:- Dont improve adjacent code, comments, or formatting.- Dont refactor things that arent broken.- Match existing style, even if youd do it differently.- If you notice unrelated dead code, mention it - dont delete it.When your changes create orphans:- Remove imports/variables/functions that YOUR changes made unused.- Dont remove pre-existing dead code unless asked.The test: Every changed line should trace directly to the users request.## 4. Goal-Driven Execution**Define success criteria. Loop until verified.**Transform tasks into verifiable goals:- Add validation → Write tests for invalid inputs, then make them pass- Fix the bug → Write a test that reproduces it, then make it pass- Refactor X → Ensure tests pass before and afterFor multi-step tasks, state a brief plan:1. [Step] → verify: [check]2. [Step] → verify: [check]3. [Step] → verify: [check]Strong success criteria let you loop independently. Weak criteria (make it work) require constant clarification.---**These guidelines are working if:** fewer unnecessary changes in diffs, fewer rewrites due to overcomplication, and clarifying questions come before implementation rather than after mistakes.省钱大法1. 使用claude code进行编码工作记得一定要购买AI服务提供商的包月token计划因为实在太烧token钱了。在模型的选择时一定是要支持长上下文的切记2. 对于不同的任务建立新的会话session。LLM是没有记忆的所以哪怕只是确认一下状态也会把所有的会话历史发送给LLM。随着任务会话轮次的增加token的消耗成倍增长的。3. 使用code graph插件。默认情况下Claude Code会使用grep之类的文本搜索工具来搜寻代码准确性差又消耗token。使用code graph插件会大大降低token的消耗并且提升代码检索的准确性。参考https://github.com/colbymchenry/codegraph#get-started- npm i -g colbymchenry/codegraph - codegraph install - cd your-project codegraph init