Maybe it's just me but you stand to gain a lot more from reading comprehension than outsourcing the same set of files repeatedly to a machine.
Portal by Spotify cut my Claude Code token usage by 90%
191–193 of 193 posts
Re: Portal by Spotify cut my Claude Code token usage by 90%
#192I use claude code and cursor. Interesting that I use opus 5 in cirsor and claude code, but in cursor i wasted less tokens while i do some tasks. During auto-tests runs, Claude code re-watch tasks and context before start my auto-test. In cursor this problem not reproduce. I use cursor most of the time.
Re: Portal by Spotify cut my Claude Code token usage by 90%
#193No mention of correctness or task success rate. This only works if the subagent model is much cheaper than the one running your session, which means it will probably be mistaken a lot more often [1] about what the code does. Routing purely on size tells you nothing about code complexity. On top of that, saving 90% of input tokens != saving 90% "of tokens", output is wildly more expensive. [1] especially if it's a rea…
Yeah this article is quite shallow after having read it; delegating to a remote sub-agent sounds novel but how does it _actually_ perform?
I'm personally skeptical of optimizing for minimal token consumption, the closer to a vanilla setup I am the more confident I feel I'm always getting the best performance out of my models.
Just look at how JetBrains measured rtk and found that while an individual call saves tokens, agents on average perform *more* turns and use *more* tokens to accomplish one task[1]
[1] https://blog.jetbrains.com/ai/2026/07/rtk-claude-code-token-...