LLMs (Claude Code in particular) will explicitly create token intensive steps, plans and responses - "just to be sure" - "need to check" - "verify no leftovers", will do git diff even tho not asked for, create python scripts for simple tasks, etc.
Absolutely no cache (except the memory which is meh) nor indexing whatsoever.
Pro plan for 20 bucks per month is essentially worthless and, because of this and we are entering new era - the era of $100+ monthly single subscription being something normal and natural.
I'm on the Pro plan. If I run out of tokens, which has only happened 2 or 3 times in months of use, I just work on something else that Claude can't do, or ...write the code myself.
You do have to keep a close eye on it, but I would be doing that anyway given that if it goes haywire it's wasting my time as well as tokens. I'd rather spend an extra minute writing a clearer prompt telling it exactly what I want it to do, than waste time on a slot machine.
>LLMs (Claude Code in particular) will explicitly create token intensive steps, plans and responses - "just to be sure" - "need to check" - "verify no leftovers", will do git diff even tho not asked for, create python scripts for simple tasks, etc. Absolutely no cache (except the memory which is meh) nor indexing whatsoever.
Most of these things can be avoided with a customized CLAUDE.md.
Not in my projects it seems. Perhaps you can share your best practices?
Moreover, avoiding these should be the default behaviour. Currently the default is to drain your pockets.
P.S
CLAUDE.md is sometimes useful but, it's a yet another token drain. Especially that it can grow exponentially.
"A plugin/annotation system where users can teach the agent about custom resource types would scale better than hard-coding each one." - this is a fantastic observation and feedback! Many thanks!
"requiring N consecutive failures before marking down" - I do have the code for it, it's just hidden currently. StatusDude supports 2 types of worker/agents - cloud agents - that will re-verify from multiregion the service status and private agents - the ones we're talking about here - that I might just bring this option back as it makes more sense.
Correlating failures is a bit tricky as usually it requires some sort of manual dependency creation but, I guess for k8s ingress and similar I should be able to figure this out and at least send alerts with appropriate priorities and order.
As for the status page auto generation - currently it's based on namespace - I didn't wanted to bloat the user dashboard too much. Each monitor is tagged with cluster id, namespace and labels. Status Pages pickup monitors based on labels. Users are free to modify these and show exactly what they want :)
and a gift for my friend's birthday.
reply