jbarbier

Auto-generated session titles + per-session colors in the Claude Code statusline.

19
3
100% credibility
Found Apr 23, 2026 at 19 stars -- GitGems finds repos before they trend. Get early access to the next one.
Sign Up Free
AI Analysis
Shell
AI Summary

A plugin for Claude Code that automatically creates concise titles and unique colors for each session, displayed in the status bar to distinguish multiple parallel sessions.

How It Works

1
💡 Discover the Helper

While juggling multiple coding chats in your AI coding app, you find this handy tool that automatically names and colors each chat session for easy spotting.

2
📥 Add the Tool

In your app, you simply tell it to fetch and install this session organizer from the built-in marketplace.

3
🔄 Quick Restart

You close and reopen your coding app to wake up the new tool.

4
⚙️ Set It Up

Run a simple setup command in the app to connect the tool to your status bar at the bottom of the screen.

5
Magic Titles Appear

Restart once more, and after your first message, watch as a short, smart title and unique color pop up in the status bar for that chat.

6
💬 Chat Away

As you send more messages in different chats, the titles update automatically to match what you're working on, each with its own color.

🎉 Sessions Sorted

Now, glance at the colorful status bar to instantly know which chat is fixing bugs, writing tests, or building features—no more confusion!

Sign up to see the full architecture

5 more

Sign Up Free

Star Growth

See how this repo grew from 19 to 19 stars Sign Up Free
Repurpose This Repo

Repurpose is a Pro feature

Generate ready-to-use prompts for X threads, LinkedIn posts, blog posts, YouTube scripts, and more -- with full repo context baked in.

Unlock Repurpose
AI-Generated Review

What is which-claude-code?

which-claude-code is a Shell plugin for Claude Code that auto-generates concise session titles and assigns per-session colors to the statusline. It solves the chaos of running multiple Claude Code sessions in parallel terminals—quickly identifying which tab is fixing auth bugs versus writing tests—by distilling your latest prompts into 3-6 word titles via a Haiku model call. Users get a clean statusline like "Fix Autopublish Bug · Opus 4.7 · opt/vanio-gtm (main)", with stable colors hashed from session IDs for instant visual distinction.

Why is it gaining traction?

It stands out by automating what devs manually label or guess: auto-generated titles refresh after every prompt, paired with unique colors that persist across sessions, making multi-tab workflows glanceable without extra typing. The setup via Claude Code's plugin marketplace (/plugin install which-claude-code@jbarbier) and /which-claude-code:setup is straightforward, despite needing restarts, and it handles which Claude code model, plan, or subscription you're on transparently. Low-cost Haiku usage keeps it negligible even on Pro or API key setups.

Who should use this?

Backend and fullstack devs running Claude Code sessions for parallel tasks like refactoring dashboards, shipping features, or debugging across branches. Ideal for those juggling which Claude code version or which company Claude code instance in terminal-heavy flows, especially on macOS/Linux with claude CLI and jq installed.

Verdict

Try it if you live in Claude Code terminals—solid docs, rigorous recursion defenses, and manual verification tests make it reliable despite 19 stars and 1.0% credibility score. Still early and niche; skip if single-session workflows dominate.

(178 words)

Sign up to read the full AI review Sign Up Free

Similar repos coming soon.