Use Claude Code Inside VS Code Without Switching to a Terminal
If you spend most of your time in VS Code, switching to a terminal for Claude Code adds friction. The official VS Code extension brings Claude Code right into your editor.
# Install from the VS Code marketplace
# Search "Claude Code" in Extensions, or:
code --install-extension anthropic.claude-code
Once installed, open the Claude Code panel from the sidebar or press Cmd+Shift+P and type "Claude Code". You get the same conversational interface as the CLI, but integrated into your editor.
The key advantage: tighter context. Claude sees what you see:
- Open files — Claude knows which files you have open in your editor tabs
- Selection context — select code before asking and Claude focuses on that specific block
- Inline diffs — edits appear as VS Code diffs you can accept or reject per-file
- Terminal integration — command output flows through VS Code's built-in terminal
Everything from the CLI works here too — slash commands, MCP servers, hooks, CLAUDE.md files. Your project settings carry over automatically.
The extension is also available for JetBrains IDEs (IntelliJ, WebStorm, PHPStorm, etc.) if that's your editor of choice.
A few things that make the IDE experience different:
- You can highlight code and right-click to send it to Claude with context
- File edits show as VS Code change reviews — easier to diff than terminal output
- Claude Code runs in the background while you continue editing other files
- Your editor's git integration stays in sync with Claude's changes
The best tool is the one you don't have to switch to — Claude Code in your IDE means AI assistance without breaking your flow.
via Claude Code
Log in to leave a comment.
When Claude writes error messages, button labels, validation text, or onboarding flows, it defaults to generic developer-speak. Add a "Users" section to your CLAUDE.md describing who your actual users are — their technical level, industry jargon, and what they care about — so Claude writes copy that makes sense to THEM, not to developers.
Use the --agent flag with custom markdown files in .claude/agents/ to launch purpose-built Claude sessions with restricted tools and scoped system prompts.
Every project has traps — the billing module that silently fails if you forget to queue the job, the legacy table with column names that don't match the model, the config value that must be set before tests run. Document these gotchas in your CLAUDE.md so Claude avoids the same mistakes your team spent days debugging.