50 Claude Code Tips and Best Practices For Daily Use You've been using Claude Code long enough to know it works, and now you're hunting for every edge you can find. I put together 50 Claude Code best practices and tips that help whether you're one week in or several months deep, sourced from Anthropic's official docs, Boris Cherny (the person who built it), community experience, and a year of my own daily usage. 1. Set up the cc alias This is how I start every Claude Code session. Add this to your ~/.zshrc (or ~/.bashrc): bash alias cc='claude --dangerously-skip-permissions' Run source ~/.zshrc to load it. Now you type cc instead of claude, and you skip every permission prompt. The flag name is intentionally scary. Only use it after you fully understand what Claude Code can and will do to your codebase. I covered this and more aliases in customizing Claude Code. 2. Prefix ! to run bash commands inline Type !git status or !npm test and the command runs immediately. The command and its output land in context, so Claude can see the result and act on it. It's faster than asking Claude to run a command. 3. Hit Esc to stop Claude. Hit Esc+Esc to rewind anything. Esc stops Claude mid-action without losing context. You can redirect immediately. Esc+Esc (or /rewind) opens a scrollable menu of every checkpoint Claude has created. You can restore the code, the conversation, or both. "Undo that" works too. Four restore options: code and conversation, conversation only, code only, or summarize from a checkpoint forward. This means you can try the approach you're only 40% sure about. If it works, great. If not, rewind. Zero damage done. One caveat: checkpoints only track file edits. Changes from bash commands (migrations, database operations) aren't captured. To pick up where you left off, claude --continue resumes your most recent conversation and claude --resume opens a session picker. 4. Give Claude a way to check its own work Give Claude a feedback loop so it catches its own mistakes. Include test commands, linter checks, or expected outputs in your prompt. markdown Refactor the auth middleware to use JWT instead of session tokens. Run the existing test suite after making changes. Fix any failures before calling it done. Claude runs the tests, sees failures, and fixes them without you stepping in. Boris Cherny says this alone gives a 2-3x quality improvement. For UI changes, set up the Playwright MCP server so Claude can open a browser, interact with the page, and verify the UI works as expected. That feedback loop catches issues that unit tests miss. 5. Install a code intelligence plugin for your language LSP plugins give Claude automatic diagnostics after every file edit. Type errors, unused imports, missing return types. Claude sees and fixes issues before you even notice them. This is the single highest-impact plugin you can install. Pick yours and run the install command: bash /plugin install typescript-lsp@claude-plugins-official /plugin install pyright-lsp@claude-plugins-official /plugin install rust-analyzer-lsp@claude-plugins-official /plugin install gopls-lsp@claude-plugins-official Plugins for C#, Java, Kotlin, Swift, PHP, Lua, and C/C++ are also available. Run /plugin and go to the Discover tab to browse the full list. You'll need the corresponding language server binary installed on your system (the plugin will tell you if it's missing). 6. Use the gh CLI and teach Claude any CLI tool The gh CLI handles PRs, issues, and comments without a separate MCP server. CLI tools are more context-efficient than MCP servers because they don't load tool schemas into your context window. Same applies to jq, curl, and other standard CLI tools. For tools Claude doesn't know yet: "Use 'sentry-cli --help' to learn about it, then use it to find the most recent error in production." Claude reads the help output, figures out the syntax, and runs the commands. Even niche internal CLIs w