I use Claude Code all day and got tired of watching it eat tokens on noisy CLI output. git status on a big repo, find across a project, cargo test with 200 lines of compilation — none of that noise is useful to the model.
So I built RTK. It wraps commands and strips the junk before it reaches your context:
rtk git status # instead of git status
rtk find "*.rs" . # compact results
rtk ls . # token-optimized tree
rtk cargo test # just the test results
My rtk gain -q after 15 days of real usage:
Total commands: 7,061
Input tokens: 29.3M
Output tokens: 4.8M
Tokens saved: 24.6M (83.7%)
Biggest surprise was rtk find — directory listings are insanely wasteful. Run rtk discover on your Claude Code session history to see how many tokens you've been wasting — that's what convinced me to actually build this.
Rust, MIT licensed. Happy to hear what commands are the worst token offenders for you.
- 7,081 commands intercepted, 24.6M chars saved out of 29.4M input → 83.6% average reduction
- Peak efficiency: 96%+ on heavy implementation days (Feb 3-4, ~11.6M input on Feb 4 alone)
- Busiest day: Feb 2 with 1,413 commands (but only 39% savings — likely many non-RTK commands)
- Most productive week: Feb 2-8 → 4,916 cmds, 19.4M chars saved
- This week trending lower (77.5% savings) — likely more complex pipes/unsupported commands
- Bottom line: ~24M characters of context window saved in 2 weeks. That's significant token budget reclaimed.
I use Claude Code all day and got tired of watching it eat tokens on noisy CLI output. git status on a big repo, find across a project, cargo test with 200 lines of compilation — none of that noise is useful to the model.
So I built RTK. It wraps commands and strips the junk before it reaches your context: rtk git status # instead of git status rtk find "*.rs" . # compact results rtk ls . # token-optimized tree rtk cargo test # just the test results
My rtk gain -q after 15 days of real usage: Total commands: 7,061 Input tokens: 29.3M Output tokens: 4.8M Tokens saved: 24.6M (83.7%)
Biggest surprise was rtk find — directory listings are insanely wasteful. Run rtk discover on your Claude Code session history to see how many tokens you've been wasting — that's what convinced me to actually build this. Rust, MIT licensed. Happy to hear what commands are the worst token offenders for you.
https://github.com/rtk-ai/rtk
Love this tool
RTK - 15-Day Summary (Jan 28 → Feb 11)
RTK Token Savings ════════════════════════════════════════
Total commands: 637
Input tokens: 6.3M
Output tokens: 1.3M
Tokens saved: 5.0M (79.3%)
Total exec time: 30m33s (avg 2.9s)
In 1 week. Numbers speak for themselves.
Still in discovery but for the moment, great tool. Hope to have the gain of Florian !!
But currently waiting for quota to reset .... Daaammmm