Updated October 2026: new name (Claude Monitor), a usage bar right inside claude.ai, and Free plan support.
If you use Claude daily, you've probably hit a wall mid-task. The reason it's so easy: Claude doesn't have one limit. It has several.
- A rolling 5-hour session window
- A weekly pool shared by all models
- Separate weekly caps for some models
They reset on different schedules, and on Pro and Max, Claude Code draws from the same pool as chat. So you can burn the week without realizing it.
I wanted that state visible at a glance instead of digging through settings, so I built Claude Monitor, a small browser extension for Chrome and Firefox.
What it does
It puts a color-coded % badge in your toolbar, and one click shows the full breakdown:
- Current 5-hour session with a live countdown to reset
- Weekly all-models pool, plus the per-model weekly caps your plan actually has
- Desktop alerts at 80% and 95% (or your own thresholds)
- Daily Claude Code routine runs
- Extra usage credits and prepaid balance, in real money
- 30 days of history with a trend line, exportable to CSV or JSON
- Auto-detects your plan (Free / Pro / Max 5x / Max 20x / Team)
- Six themes and four layouts
New: your limits right where you type
Turn on the optional bar and your session and weekly usage sit right above claude.ai's chat box, so you see them while you write.
It also made the Free plan work. Since August 2026, claude.ai's usage page shows nothing to Free accounts, but every reply still carries the limits. With the bar on, the extension reads them each time you send a message, so the badge, popup and alerts work on Free too.
The privacy part (the part I cared about most)
It's open source (MIT) and runs 100% locally: no backend, no analytics, no servers.
The host permissions are scoped to five read-only claude.ai endpoints (organizations, usage, prepaid credits, spend limit and routine-run budget). It never reads your chats, projects or files. The bar is opt-in: its permissions are requested only when you turn it on and released when you turn it off, and it reads only the usage figures attached to each reply. Narrow permissions = less to trust, and less to exploit.
One honest caveat: it reads claude.ai's own usage endpoints, so it can break if Anthropic changes them. Not affiliated with Anthropic.
Try it
It's free, no account needed (desktop Chrome & Firefox):
Happy to hear what else you'd want tracked, drop a comment.
Top comments (0)