Re:Tokendoctor – the same Claude Code for up to 38% less
by worried_individ on Tuesday November 17, 2026 @05:16AM
(#50529587)
its crazy to me that people are not even running editorial passes. its trivial to give claude a 5 line instruction about writing style and have it transform the output into something vastly better.
Re:Tokendoctor – the same Claude Code for up to 38% less
by Incipient on Tuesday November 17, 2026 @03:37AM
(#50528949)
All of these token optimiser things...i rarely see any performance analysis. If you're cutting token usage in half, what does that do to the accuracy of the outcome? If you're automatically delegating to cheaper models, what does that do to the outcome?
Personally I've found a HUGE improvement in quality using more context, to the point that it's 'better value' - fewer outcomes I disagree with or have to fix/rework.
I've mostly done this through mechanical documentation links that are enforced and can be 'followed' with some python files that the agents use. Context is higher than just reading code, but it has been a HUGE benefit (as far as I can tell).
Re:Tokendoctor – the same Claude Code for up to 38% less
by pseudosaid on Tuesday November 17, 2026 @03:40AM
(#50528974)
Just use billion context. I customize it to set a slider so I decide how big the context window can ever grow, and it uses models to fold itself in on itself and summarize itself while retaining the entire chat history. I've managed to run chats over three thousand messages long without any negative effect. And overall, I average a seventy-four percent reduction in token usage.
Re:Tokendoctor – the same Claude Code for up to 38% less
by notenchange on Tuesday November 17, 2026 @08:58AM
(#50531452)
So, TL;DR: the claimed 38% decrease was because the user figured out that using too close to the limit context (1M) was costing him about 30K per request.
So, the tool didn’t actually implement any savings, it was just a look into what happened in the past.
Sincerely, you shouldn’t be using near 1M anyway. I usually issue a manual compact between 256K and 500K
For example limiting token usage i think can also be achieved by 'caveman' project. It achieves it differently but the goal is same i suppose
Overall Ai tools I found:
https://github.com/rumca-js/awesome-database-top/blob/main/l...
I'm trying to figure out if I can use multiple of these tools together without conflicts
People throw them in and never think about it. Sure it doesn't BREAK things, but it could degrade them by 15% and you'd never know?
Don't we need to run it on all of the benches those models publish?
This doesn't look very comprehensive. Moreover half of the times factory claude code is better than 'advised' one.
Although I don't discourage such experiments, I feel this one is way complicated for very little or no gain provably.
Claude generates text in my native language perfectly)) it’s strange that it performs poorly for you in English
Personally I've found a HUGE improvement in quality using more context, to the point that it's 'better value' - fewer outcomes I disagree with or have to fix/rework.
I've mostly done this through mechanical documentation links that are enforced and can be 'followed' with some python files that the agents use. Context is higher than just reading code, but it has been a HUGE benefit (as far as I can tell).
So, the tool didn’t actually implement any savings, it was just a look into what happened in the past.
Sincerely, you shouldn’t be using near 1M anyway. I usually issue a manual compact between 256K and 500K