Claude Code Usage Tracker and Dashboard

Connect Claude Code

Start your board Sign in at board.contextbolt.com with your email. Pick a template, or start from a blank canvas.
Link your computer In Connect, open Your AI and copy the one-line command. Run it once in a terminal. The small runner starts with your computer from then on.
Add the AI usage widget Open the gallery and add AI usage, or start from the Agents template, which has it already. It fills the next time Claude Code runs.
Keep working The rings empty as you use your plan and refill when each window resets. No tab to keep checking, no command to type.

Your limits are read on your computer, and only the percentages and reset times reach the board. How the runner works

What to ask your agent

“Arrange this board so my usage and sessions sit at the top” Your agent lays the board out in sections, so the limits sit where you look first.

“Add a note under my usage: switch to Codex when Claude drops under 20%” A sticky note beside the rings. The rule you set for yourself stays in sight at the moment it matters.

“Add a to-do list called Today with the three things I said I'd ship” A task list next to your sessions, so what you planned and what your agents are doing share one screen.

“Give this board a dark theme with the northern lights behind it” Your agent sets the theme. It is your board, and it can look like it.

What you see from Claude Code

See what is left of your current five-hour session, as a ring
See what is left of your week, with the day and time it resets
See a model's own weekly limit when your plan has one
Watch Claude Code and Codex side by side on one widget
Follow every Claude Code session on your computers, working, done or waiting
Add usage from more than one computer, or a server, with the same one line
Keep it next to your revenue, traffic and to-dos, on a board you arrange

Claude Code on Context Board: the full guide

You find out you hit the Claude Code limit the worst way. Mid-task, in the middle of a refactor, when the session stops and tells you to come back in two hours.

The limit itself is fine. Not knowing where you are against it is the problem.

What the board shows

The AI usage widget draws your plan the way you actually think about it. Two rings for Claude Code, one for the current five-hour session and one for the week. Each ring empties as you use it, turns amber under half and red under a fifth, and says when it comes back: “resets in 1h 42m”, “resets Mon 9:00 AM”.

If your plan has a model’s own weekly limit, that shows underneath.

Codex sits beside it in the same widget, read the same way. So when Claude is down to 15% and Codex is at 90%, you can see which one gets the next task.

Where the numbers come from

Claude Code already knows your limits. It hears them from Anthropic every time it runs, and /usage will show them if you stop and ask.

The board’s runner, a small program you set up once with one line, reads what Claude Code last heard and passes the percentages and reset times to your board. The widget says when that was, so a number is never older than it looks. From your sessions, only names, states and percentages leave your computer. Never what you and Claude Code wrote.

Your limits next to the rest of your work

A command answers when you remember to ask. A board answers when you glance at it.

The usage widget lives next to everything else you check in a day. Your Stripe revenue, today’s commits, the sessions still running and the one that is waiting for you to say yes. Start from the Agents template and the usage, sessions and commits are there already. Then ask your agent to add the rest around them.

If you use more than one computer, or run agents on a server, link each one with the same line. Usage and sessions come from all of them.

Frequently asked questions

Something else on your mind? Get in touch.

How does Context Board know my Claude Code usage?

A small program called the runner, which you set up once with one line from Connect, reads what Claude Code last heard from Anthropic about your plan: how much of the current five-hour window and the week you have used, and when each resets. It sends the board those percentages and times. Nothing you said in a session leaves your computer.

Is this the same number as /usage in Claude Code?

It is the same plan limit, read from the same place, so the two should agree. The difference is that /usage tells you when you ask, inside the terminal. The board shows it all the time, next to your other work, and for Codex too.

Does it count tokens or cost like ccusage?

No. ccusage adds up tokens and an estimated cost from Claude Code's local logs, which is useful on the API. On a Pro or Max plan the question that matters is how much of your limit is left and when it comes back, and that is what the board shows.

Does it work with Codex as well?

Yes. The same widget shows Codex's five-hour window and week beside Claude Code's, read the same way. See Codex usage on Context Board.

What does it cost?

Context Board is free for 3 days, then $6 a month. One plan with every connection, widget and theme. The runner and the AI usage widget are part of it.

Does my session content go anywhere?

No. From your sessions, only names, states and percentages leave your computer. That means a session's title and project, whether it is working, and how much of each limit is left. What you and Claude Code wrote stays on your machine.

Go deeper

Keep reading

All integrations