Claude-Code-Usage-Monitor

If the repo was structured as a package e.g. with project.toml and such there would be an even faster one-liner with pipx (https://pipx.pypa.io/latest/): > pipx install git+https://github.com/Maciek-roboblog/Claude-Code-Usage-Monitor > ccusage_monitor I think there is a similar command for uv; uvx? Although, I am not sure if uvx has the same functionality / purpose as pipx.

Incredible, thank you for making this! Can this be installed with uv? https://github.com/astral-sh/uv Edit: # Install uv curl -LsSf https://astral.sh/uv/install.sh | sh # Install the required CLI tool (Node.js) npm install -g ccusage # Clone and setup git clone https://github.com/Maciek-roboblog/Claude-Code-Usage-Monitor.git cd Claude-Code-Usage-Monitor # Install Python deps with uv uv add pytz chmod +x ccusage_monitor.py # Run it uv run python ccusage_monitor.py --plan max20 --timezone America/New_York

If you have some time, feel free to open a pull request — even just with a description or clarification of what's going on! It all sounds super interesting, but I’m still trying to fully grasp the business logic behind it Once I get the idea, I’ll be happy to jump in and implement it. Repo is here if you're curious: https://github.com/Maciek-roboblog/Claude-Code-Usage-Monitor...

Please write for me on github or create issue https://github.com/Maciek-roboblog/Claude-Code-Usage-Monitor... and we can try integrate your tool with usage monitor

I can implement tool like this for Gemini, please create issue https://github.com/Maciek-roboblog/Claude-Code-Usage-Monitor... with this idea

Yes, cache write and read is available to fetch i can add new flag to view this values, please create issue in repository with this idea https://github.com/Maciek-roboblog/Claude-Code-Usage-Monitor...

I kept slamming into Claude Code limits mid-session and couldn’t find a quick way to see how close I was getting, so I hacked together a tiny local tracker. Streams your prompt + completion usage in real time Predicts whether you’ll hit the cap before the session ends Runs 100 % locally (no auth, no server) Presets for Pro, Max × 5, Max × 20 — tweak a JSON if your plan’s different GitHub: https://github.com/Maciek-roboblog/Claude-Code-Usage-Monitor It’s already spared me a few “why did my run just stop?” moments, but it’s still rough around the edges. Feedback, bug reports, and PRs welcome!