Run Parallel Claude Sessions on the Same Repo Using Git Worktrees
When you need to work on two features at once, running multiple Claude sessions in the same directory causes file conflicts. Git worktrees give each session its own working copy while sharing the same repo.
# Create a worktree for each feature
git worktree add ../my-project-feature-auth feature/auth
git worktree add ../my-project-feature-search feature/search
Each worktree is a full checkout on its own branch, backed by the same .git directory. Open a separate terminal for each and launch Claude Code:
# Terminal 1
cd ../my-project-feature-auth && claude
# Terminal 2
cd ../my-project-feature-search && claude
Both sessions run completely independently — different branches, different file states, no merge conflicts mid-work. When you're done, clean up:
# Remove worktrees after merging
git worktree remove ../my-project-feature-auth
git worktree remove ../my-project-feature-search
A few things to know:
- Each worktree shares your git history and stash, but has its own index and working tree.
- You can't check out the same branch in two worktrees simultaneously.
- CLAUDE.md lives in the worktree root, so project instructions carry over automatically.
Two terminals, two features, zero conflicts — worktrees turn Claude Code into a parallel workforce.
via Claude Code
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.