Eight makers on one tab
Claude, Codex, GitHub Copilot, Cursor, Antigravity, Grok, Ollama and OpenCode each get a ring in their maker’s colour, with what is left inside it. Every account signed in on the Mac has its own rings, and so does each Claude Code profile.
The plans do not work alike. Claude has a 5-hour session and a week, and Codex has windows of its own. GitHub Copilot counts premium requests by the month. Cursor has a billing cycle. A model can have a limit of its own on top of the plan’s.
Each tool shows its own number in a command, a settings page or a web dashboard, and none shows the others. You tend to find the limit in the middle of a task, when the agent stops and tells you to come back in two hours.
Every window a plan has, with its reset
One plan can stop you in several ways. Vitals shows each on its own: the 5-hour session, the week, the month, and a model’s own limit, such as Opus this week. Each has how much is left and when it resets, down to the minute.
On pace, or running out first
Vitals compares what you have used with how far through the window you are, and says the result in words: on pace with 10% to spare, or runs out in four days at this rate.
For Claude Code and Codex it also counts tokens: how many were used today and this week, where they went and which models took them. The counts come from the logs those tools keep on your Mac.
A plan in the menu bar
Any plan can be a menu bar item: a number after its maker’s mark, with the 5-hour session beside it if you want it. The dropdown’s Agents tab has the plans, the tokens and the running sessions.
How it reads your plans
The feature is off until you turn it on. Vitals then uses the sign-in each tool already keeps on your Mac and asks the maker the way the tool itself does. There is no password or API key to paste, Vitals keeps no copy of the sign-in, and nothing else is sent.
A tool you are not signed in to is left out until you sign in with it. For Claude Code inside the Claude app, macOS asks once whether Vitals may read it.
How to use it
- 1
Turn it on
Go to Settings → Integrations and switch on Show Usage Limits of Your AI Plans.
- 2
Read the rings
Open the Agents tab. Each plan has a ring with what is left, when it resets and whether you are on pace.
- 3
Add a plan to the menu bar
In Settings → Integrations, choose which providers show in the menu bar, with the 5-hour session beside the number if you like.
- 4
Check the tokens
For Claude Code and Codex, the Agents tab shows the tokens used today and this week, by model.
The details
- Plans read
- Claude, Codex, GitHub Copilot, Cursor, Antigravity, Grok, Ollama and OpenCode
- Limits shown
- The 5-hour session, the week, the month and a model’s own limit
- Accounts
- Every account signed in on the Mac, each Claude Code profile included
- Token counts
- Claude Code and Codex, today and this week, by model
- Turn it on in
- Settings → Integrations → Show Usage Limits of Your AI Plans
- In Terminal
- vitals limits
Questions
Does Vitals need my password or an API key?
No. It uses the sign-in each tool already keeps on your Mac, the way the tool does. There is nothing to paste in, and Vitals keeps no copy.
Does it work with more than one account?
Yes. Every account signed in on the Mac gets its own rings, and so does each Claude Code profile.
Can I see my limits without opening the window?
Yes. Any plan can be its own menu bar item, and the dropdown shows them all.
What if I am not signed in to one of the tools?
That tool is left out. Sign in with it and its plan appears.
Can it warn me before I run out?
Each ring says whether you are on pace or will run out first. With a plan in the menu bar the figure is always in view.
The same feature on the app's own site: vitalsmac.com/features/ai-usage-limits