CrewTower
Control your agents from the notch
Start new thread

CrewTower Mod for Claude Code - Talk to Claude Code right from your MacBook notch

by
•
A Claude Code mod that links every Claude session to CrewTower in your Mac's notch. Type Claude's next prompt on its card, stop the turn, compact it, and see what fills its context. Terminal and Claude Desktop. Stays on your Mac, off until you turn it on.

Add a comment

Replies

Best
Maker
📌
Hey hunters, Said here, the builder behind CrewTower. When CrewTower launched here in August, it could watch your coding agents from the MacBook notch and answer their permission prompts. It could not talk back. When Claude finished a task and I already knew the next step, I still had to find the right terminal tab and type it there. This month Claude Code shipped mods, a way for other apps to plug into a Claude Code session. So I built a small mod for CrewTower, and now a Claude card in the notch can: ✍️ Take Claude's next prompt. Type it on the card and press Send, and it lands in that same session. If Claude is still working, it runs when the turn ends. ⏹️ Stop the running turn, or compact the conversation, with one press. 📊 Show what fills the context: the same breakdown /context draws, with a hint to compact at a task break. It works in the terminal and in Claude Desktop's Code tab. To turn it on: update to 1.0.33, press Enable on the offer card (or in Settings > Integrations), then start a new session or type /reload-plugins. It needs Claude Code 2.1.287 or newer and macOS 15. Since it touches your sessions: the mod talks only to the CrewTower app, over a local socket on your Mac. Nothing goes to a server. It stays off until you turn it on, and turning it off uninstalls it. It is still in beta, so please tell me what breaks. Everything from the first launch is still there: approvals for Claude Code, Codex, Cursor, Gemini CLI, Qwen Code and opencode, jumping to the right tab, usage limits, and the pixel companions. The price is the same: $9.99 once, one Mac, no subscription. What would you want to tell Claude from the notch that it can't do yet?

  sessions sitting there waiting for me is very real, so this makes a lot of sense. what I'd want from the notch is picking a feature spec file and sending it as the next prompt, instead of retyping the context every time I start a new task.

Maker

 yeah retyping the same context every time gets old fast. right now it's just text you type, but picking a spec file and sending it is a nice idea, gonna think about how that'd work

  Totally agree! Glad the feedback resonated. Thanks for the thoughtful reply, and rooting for your product!

 nice one. my sessions often run long tasks like a video render, and on the card I only see working. would be cool to see what it is doing right now, like last tool call or a progress line. is this possible with the mods?

Maker

 Of course. Actually there is an activity button on the card showing you what your agent is doing at the moment

Being able to send Claude the next message without switching back to the right terminal tab looks useful. Can I edit or cancel that message while Claude is still working? Sometimes its answer changes what I want to ask next.

Maker

 not yet. once you send it, it just waits and goes in when the turn ends. you can hit Stop on the card but you can't edit it from there. had the same thing happen to me actually, so I'll probably add that

This is amazing. I really wished this was made for windows too.

Maker

 People are asking me to build this for Windows and Linux a lot. I'm definitely considering it.

Does it also work if I have several Claude sessions running at once?

Congrats Said on the CrewTower launch and the new Claude Code mod. The context breakdown with a hint to compact at a task break is the part I would lean on most. How does the card decide it is at a task break: just the turn ending, or something like tests passing or a commit? Having it offer the compact right at that moment would be my answer to your question.

Maker

 thanks Gene! right now it's pretty simple, it's just when the turn ends and Claude's waiting on you. and it only suggests compacting once the context gets big, around 300k on 1M. tests passing or a commit would be a much better moment to suggest it tbh, hadn't thought of that