News for hackers. Stuff that matters.
Re:Tokendoctor – the same Claude Code for up to 38% less by renegat0x0 on Tuesday November 17, 2026 @12:55AM (#50527928)
I have a list of ai related tools. There is so many of them

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...

Re:Tokendoctor – the same Claude Code for up to 38% less by kristopolous on Tuesday November 17, 2026 @03:03AM (#50528715)
well then don't go https://neuronary.org/ or https://www.neuronpedia.org/ you'll never be done.
Re:Tokendoctor – the same Claude Code for up to 38% less by relyks on Tuesday November 17, 2026 @01:02AM (#50527971)
I use this and it works well: https://github.com/rtk-ai/rtk

I'm trying to figure out if I can use multiple of these tools together without conflicts

Re:Tokendoctor – the same Claude Code for up to 38% less by shitloadofbooks on Tuesday November 17, 2026 @01:19AM (#50528064)
Can you define "well" at all? I personally think a lot of these are absolute snake oil.

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?

Re:Tokendoctor – the same Claude Code for up to 38% less by rsaryev1997 on Tuesday November 17, 2026 @11:30AM (#50533857)
https://github.com/rtk-ai/rtk - I ran some benchmarks, and to be honest, it’s almost useless
Re:Tokendoctor – the same Claude Code for up to 38% less by mkagenius on Tuesday November 17, 2026 @01:07AM (#50528009)
> https://github.com/localixai/tokendoctor/tree/main/bench

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.

Re:Tokendoctor – the same Claude Code for up to 38% less by ralph84 on Tuesday November 17, 2026 @01:59AM (#50528321)
These tricks last at most one model dot release.
Re:Tokendoctor – the same Claude Code for up to 38% less by fullstackwife on Tuesday November 17, 2026 @02:05AM (#50528371)
Also not measuring cost per task is one of the sins. It's easy to get penny wise and pound foolish on this matter.
Re:Tokendoctor – the same Claude Code for up to 38% less by pinkyclouds on Tuesday November 17, 2026 @02:16AM (#50528450)
why not having a tiny fast model summarize tool output instead, maybe with a threshold or something.
Re:Tokendoctor – the same Claude Code for up to 38% less by urig on Tuesday November 17, 2026 @03:05AM (#50528734)
Please don't let AI write your README.md. It's illegible to humans.
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 rsaryev1997 on Tuesday November 17, 2026 @11:26AM (#50533784)
Could you please tell me what the prompt is? English is not my native language

Claude generates text in my native language perfectly)) it’s strange that it performs poorly for you in English

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