Hacker News
Tokendoctor – See what your Claude Code use overpays
Incipient
|next
[-]
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).
urig
|next
|previous
[-]
relyks
|next
|previous
[-]
I'm trying to figure out if I can use multiple of these tools together without conflicts
rsaryev1997
|root
|parent
|next
[-]
thatwasunusual
|root
|parent
|next
|previous
[-]
"rtk advertised saving: 60–90%. Measured on real agent work: +7.6% more expensive at low reasoning effort (p=0.004), ±0% at high effort."
[0] https://blog.jetbrains.com/ai/2026/07/rtk-claude-code-token-...
mkagenius
|next
|previous
[-]
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.
renegat0x0
|next
|previous
[-]
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...
kristopolous
|root
|parent
|previous
[-]
pseudosaid
|next
|previous
[-]
notenchange
|next
|previous
[-]
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
peter_d_sherman
|next
|previous
[-]
What a setting saves depends on how you work: how long your sessions run, which models you use, what the work is. A number from someone else's sessions, mine included, says little about yours. So tokendoctor starts by looking back at your own."
This is a great idea, that is, save a user's agents' previous AI conversations, then compare that usage against what would have been saved if various token compression/"tokenmaxxing" strategies were to have been used (then the user can tweak their settings for better future token used based on that knowledge)...
Another step forward in AI optimization!