Claude Code Usage Monitor
A real-time terminal monitor for Claude Code usage: tokens, messages and cost in the five-hour window, with forecasts and export
Install
uv tool install claude-monitor
claude-monitorAlso: pip install claude-monitor or pipx install claude-monitor. Short command names: cmonitor, ccmonitor.
This is third-party code. Review the repository files before installing.
What it does
claude-monitor shows a live terminal dashboard of Claude Code token, message and cost usage within the current five-hour window. By default it derives personal limits from recent history, and it also knows the pro, max5, max20 and team plans. Its status line mode captures official rate limit data from Claude Code and labels which numbers are official and which are estimates. It forecasts pace until reset, writes state as JSON for other programs and offers an optional local history store with CSV and JSON reports.
Who it is for. For Claude Code subscribers who often hit limits and want to plan their work.
Good fit when
- You want to see how much is left in the current window
- You want to know if your pace will last until reset
- You need usage history longer than Claude Code keeps
Not a fit when
- You need reports across several agents, not just Claude Code
- You pay per token via API and subscription limits do not matter
Example request
Start the Claude Code usage monitor for the max5 planLimitations
Works only with Claude Code and its local data. Without status line mode limits are estimated from history and may differ from reality. Team plan figures are marked unverified. Requires Python 3.9 or newer.
How to disable. Run uv tool uninstall claude-monitor or pip uninstall claude-monitor. If you enabled status line mode, remove it from Claude Code settings.
Security check
- Only reads local Claude Code data and displays statistics
README in short
The README describes the monitor as a local Claude Code usage tool with a live terminal dashboard. The main install is uv tool install claude-monitor, with pip, pipx and source installs as alternatives. It lists CLI options, supported plans, official limits via status line mode, forecasts, export and the history store. A large section covers install and runtime troubleshooting. MIT licensed.
FAQ
Which plan should I pick?
The default is custom, which adapts limits to your history. Set a plan explicitly with --plan and it is remembered.
Can I feed the data into my own dashboard?
Yes, --once and --write-state output a machine-readable state snapshot.
Related
A CLI for every Google Workspace API with JSON output and agent skills: Drive, Gmail, Calendar, Sheets and more
Local search over Markdown notes, docs and meeting transcripts: keywords, semantic search and reranking, with an MCP server
A task manager for AI-driven development: breaks a PRD into dependent tasks and guides the agent through them via MCP or CLI
Anthropic's official plugins for knowledge work roles: sales, support, product, marketing, legal, finance, data and enterprise search