Use Claude Code Inside VS Code and JetBrains with the Official IDE Extensions
If you spend most of your day in an IDE rather than the terminal, you don't have to choose between your editor and Claude Code. The official extensions put Claude Code right inside VS Code and JetBrains IDEs.
# Install the VS Code extension
# Search "Claude Code" in the VS Code Extensions marketplace, or:
code --install-extension anthropic.claude-code
Once installed, open the Claude Code panel with Cmd+Esc (Mac) or Ctrl+Esc (Windows/Linux) and start prompting — same capabilities as the CLI, but integrated into your editor's workflow.
The IDE experience adds some benefits you don't get in the terminal:
- Inline diffs — see exactly what Claude wants to change in a familiar VS Code diff view before accepting
- File context — Claude automatically knows which file you have open and where your cursor is
- Side-by-side workflow — prompt Claude in the panel while viewing code in the editor, no switching windows
- Terminal integration — Claude can still run commands in the IDE's built-in terminal
Everything from the CLI works in the extension too — your CLAUDE.md files, custom commands, MCP servers, hooks, and memory all carry over. The extension uses the same Claude Code engine underneath.
For JetBrains users (IntelliJ, PHPStorm, WebStorm, PyCharm, and others), search "Claude Code" in the JetBrains Marketplace. Same core experience, native to the JetBrains ecosystem.
You can also use both — the CLI for automation and headless scripts, the extension for day-to-day coding. They share the same configuration, so your CLAUDE.md and settings stay consistent across both.
Pick the interface that fits your flow — terminal, IDE, or both. Claude Code works the same everywhere.
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.