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!
Comments URL: https://news.ycombinator.com/item?id=44317012
Points: 12
# Comments: 6
https://github.com/Maciek-roboblog/Claude-Code-Usage-Monitor
Войдите, чтобы добавить комментарий
Другие сообщения в этой группе

Hey HN
We’re the core engineering team at Caudena (which is used globally by investigative and intelligence agencies, including: Europol, Interpol, BKA, DHS, IRS-CI, FBI, NPA and others), and we

Article URL: https://www.howclosetoblackmirror.com/
Comments URL: https://news.y



Article URL: https://zed.dev/blog/debugger
Comments URL: https://news.ycombinator.com/ite