Monitor your Claude Code usage in real time, with full limit information.
No more 'Surprise! You've hit your Claude Code weekly limit and it resets in 3 days you lucky, lucky person!'
- Token context usage
- Session limits
- Weekly limits
- Limit consumption and reset times
- Claude session and login all local to device
- Open source https://github.com/hypersec-io/claudemeter
- VS Code 1.80.0 or higher
- A Chromium-based browser (Chrome, Chromium, Brave, or Edge)
The extension will automatically fetch usage data when VS Code starts. If you haven't logged in before:
- A browser window will appear (the extension detected you need to log in)
- Log in to Claude.ai with your credentials
- Once logged in, the extension automatically fetches your usage data
- Your session is saved locally - you won't need to log in again
Open VS Code Settings and search for "Claudemeter" to configure:
- Type: Boolean
- Default:
true - Description: Automatically fetch usage data when VS Code starts
- Type: Boolean
- Default:
true - Description: Run browser in headless (hidden) mode. Browser will show automatically if login is needed.
- Type: Number
- Default:
5 - Range:
1-60minutes - Description: Auto-refresh interval in minutes
- Type: Number
- Default:
200000 - Range:
1000-2000000 - Description: Context window token limit used to calculate usage percentage
- Type: Boolean
- Default:
false - Description: Token-only mode - only track Claude Code tokens, skip Claude.ai web usage scraping entirely
- Type: String
- Default:
default - Options:
default,minimal,compact - Description: Status bar display mode:
- default: Full display with reset times (separate panels)
- minimal: Percentages only (separate panels)
- compact: All metrics in a single panel
- Type: Boolean
- Default:
false - Description: Show Sonnet weekly usage in status bar (default/minimal modes only)
- Type: Boolean
- Default:
false - Description: Show Opus weekly usage in status bar (Max plans only, default/minimal modes)
- Type: Boolean
- Default:
false - Description: Show extra usage (spending cap) in status bar (default/minimal modes only)
- Type: Boolean
- Default:
false - Description: Enable debug logging to output channel (for troubleshooting)
Configure warning and error thresholds globally or per-gauge:
{
"claudemeter.thresholds.warning": 80,
"claudemeter.thresholds.error": 90,
"claudemeter.thresholds.tokens.warning": 65
}All commands are available via the Command Palette (Ctrl+Shift+P / Cmd+Shift+P):
Claudemeter: Fetch Claude Usage Now- Manually fetch current usage dataClaudemeter: Open Claude Settings Page- Open claude.ai/settings in your default browserClaudemeter: Start New Claude Code Session- Start a new token tracking sessionClaudemeter: Show Debug Output- Open debug output channelClaudemeter: Reset Browser Connection- Reset browser connection if stuckClaudemeter: Clear Browser Session (Re-login)- Force re-loginClaudemeter: Open Browser for Login- Manually open browser for login
- Ensure you have enough disk space (~500MB for Chromium)
- Check that no antivirus is blocking Puppeteer
- Try running VS Code as administrator (Windows)
- Delete the session folder:
- macOS:
~/Library/Application Support/claudemeter/ - Linux:
~/.config/claudemeter/ - Windows:
%APPDATA%\claudemeter\
- macOS:
- Log in again - session should persist this time
- Claude.ai may have changed their settings page layout
- Check if you can see your usage at claude.ai/settings
- Report an issue for the extension to be updated
- No credentials stored: The extension never stores or transmits your credentials
- Local session only: Your authentication session is saved locally by Chromium
- No data transmission: Usage data stays on your machine
- Open source: All code is available for review
If you encounter any issues or have suggestions:
- Check the troubleshooting section above
- Review open issues on GitHub
- Submit a new issue with:
- VS Code version
- Extension version
- Error messages from the Output panel (View → Output → Claudemeter - Token Monitor)
- Steps to reproduce
Paying it forward by the hoopy froods at HyperSec https://hypersec.io
MIT License - See LICENSE file for details.
Originally inspired and based on claude-usage-monitor by Mark Campbell. If you find this useful, please consider sponsoring the original author.
Note: This is an unofficial extension and is not affiliated with Anthropic or Claude.ai.









