Claude Code can create and resume sessions on the web, letting you start work from the terminal and pick it up in a browser, or the other way around.
# Launch a task as a web session on claude.ai
claude --remote "Fix the login bug in the auth service"
This creates a new web session with your task description and opens it in your browser. The session runs on claude.ai with full access to your codebase context.
Going the other direction, --teleport pulls a web session back into your local terminal:
# Resume a web session locally
claude --teleport
This is useful when you started a task on the web but need local tool access, or when you want to hand off a complex investigation to run in the cloud while you step away.
You can also enable bidirectional control with --remote-control (or --rc), which starts a local interactive session that can also be controlled from claude.ai or the Claude app:
# Start with remote control enabled
claude --remote-control "My Project"
# or shorter
claude --rc
This gives you the flexibility to switch between your terminal and the web interface mid-session, depending on what is more convenient at the moment.
Your Claude Code sessions are not locked to where you started them.
Log in to leave a comment.
Set up Claude Code as an automated reviewer in your CI pipeline — on every pull request, it reads the diff, checks for bugs, security issues, missing tests, and convention violations, then posts its findings as a PR comment. Your human reviewers get a head start because the obvious issues are already flagged before they look.
Before deploying, tell Claude to read your project — migrations, environment variables, queue workers, scheduled tasks, caching, third-party integrations — and generate a deployment checklist that's specific to your app. Not a generic "did you run migrations?" list, but one that knows YOUR infrastructure and catches the things YOUR deploy can break.
Instead of writing a README from memory or copying a template, tell Claude to read your project and generate one that's actually accurate — real setup instructions from your config, real architecture from your directory structure, real API examples from your routes, and real prerequisites from your dependency files.