Token-saving tools for Claude Code, including a Jev browser agent
A list of eight tools to cut Claude Code bills, including jev-ultrafast, which lets Jev decide each click and only wakes a text model when typing is needed.
install these before your next long Claude Code session if your Opus 5.5 bill hurts and you don’t know where to start, copy this: claude-code-router: sits in front of Claude Code and sends each request to the cheapest model that can do it. Haiku does the grep, Opus only gets the hard part. 37k stars https://github.com/musistudio/claude-code-router rtk: shrinks test, build and git output before the model sees it. one binary, up to 90% less bash output in your context. 83k stars https://github.com/rtk-ai/rtk claude-mem: remembers what happened in your past sessions and feeds back only the relevant part, so you stop paying to re-explain your project every morning. 100k stars https://github.com/thedotmack/claude-mem context-mode: a huge tool output goes into a local database instead of your context window, and Claude pulls out only the lines it needs. 18k stars https://github.com/mksglu/context-mode caveman: makes Claude answer in short telegraphic sentences. code stays identical, and output is the expensive side on Opus 5.5 ($20 per million). 51k stars https://github.com/JuliusBrussee/caveman token-optimizer: a local dashboard that shows where your tokens actually went, and keeps your work alive across compactions. 1.9k stars https://github.com/alexgreensh/token-optimizer token-savior: replaces whole-file reads with symbol lookups, so Claude reads the function and not the 2,000 lines around it https://github.com/Mibayy/token-savior code-review-graph: maps your repo as a graph and gives Claude only the code connected to the change you’re reviewing https://github.com/tirth8205/code-review-graph jev-ultrafast: a browser agent where Jev picks every click, and a text model wakes up only when something has to be typed. 16,758 stars https://github.com/browser-use/jev-ultrafast none of them makes Opus smarter. every one stops it from paying for work it never needed to do the full setup with scripts is in the article. do the measuring step first, so you know what you actually saved
This post quotes another post: x.com/rvaniaaaa/status/2109385796751114346