Skip to content

claude-code

rtk promised 60-90% fewer tokens. JetBrains measured 7.6% more spend

Claude News

rtk ("Rust Token Killer") is a Claude Code add-on that uses a PreToolUse hook to intercept shell commands and hand the model a compressed version of the output. The pitch: 60-90% token savings. JetBrains ran a paired A/B test to check it. Setup: Claude Code 2.1.201, claude-sonnet-5, the SkillsBench benchmark, 86 tasks.

At low reasoning effort, rtk came out 7.6% more expensive per task at the median (p=0.004); at high effort the difference was roughly zero. Output quality matched across both branches. Why: the hook sees only about a third of Bash calls and under 20% of output characters, while most of the cost comes from cached re-reads that are billed at one tenth the price.

Meanwhile rtk's own analytics claimed 96.2 million tokens saved, measured against the full raw output as its baseline. An earlier entry in the series tested the caveman skill: promised -65%, measured -8.5%.

Related stories

  1. ponytail's token savings: 10.3% off the bill, not the promised 20%
  2. Claude Code sends 33k tokens before it even reads your prompt; OpenCode uses 7k
  3. pxpipe hides text in PNGs to cut token costs by up to 70%
  4. Context compression cut 39% of tokens and saved almost nothing
  5. ctx2img packs whole repos into image tiles, cutting token use 60-75%
  6. Context7 cuts Claude Code input tokens by roughly 99%

Comments

No comments yet. Be the first.

Join the conversation

Sign in with Google to leave a comment. Your name and avatar come from your Google profile, and the comment appears after moderation.

We only use your name and avatar from Google. We never store your email address.