JuliusBrussee/caveman

Same. I use this to fix claudespeak. Any hypothetical token savings are just gravy. https://github.com/JuliusBrussee/caveman/blob/main/skills/caveman/SKILL.md

Along similar lines, a coworker told me about Caveman and it has made my Claude experience vastly better. I'm already a programmer, Claude shouldn't need to tell me like I'm 5. https://github.com/JuliusBrussee/caveman

I recently started using caveman, and it’s been great. It doesn’t just cut down on overuse of specific terms; it cuts down on time spent digesting slop in general. https://github.com/JuliusBrussee/caveman

> Opus 4.7 uses an updated tokenizer that improves how the model processes text. The tradeoff is that the same input can map to more tokens—roughly 1.0–1.35× depending on the content type. caveman[0] is becoming more relevant by the day. I already enjoy reading its output more than vanilla so suits me well. [0] https://github.com/JuliusBrussee/caveman/tree/main

Just saying, I simply copied from https://github.com/JuliusBrussee/caveman Beyond the cost of tokens, I found it's very good at doing more with a limited context window before OpenCode hits context compaction.

Neither, just be neutral and use caveman speak. It saves tokens. Being polite consumes extra tokens, and being rude can risk you getting banned. So use caveman speak, save tokens. The best part is, you'll get curt responses as well, without any cringy flowery language that LLMs are known for. In fact, there's even a skill for it: https://github.com/juliusbrussee/caveman

caveman mode good https://github.com/JuliusBrussee/caveman

This is what you want: https://github.com/juliusbrussee/caveman

My criteria is "do they measure performance, or at least even try to?". Caveman [1], RTK [2] and more recently ponytail [3] don't or use a few trivial tests. Those projects don't measure performance on widely used benchmarks (like SWE Pro and stuff), that have their issues but at least it would give some indication. They also don't measure "big model + caveman vs smaller model". I've had a few times where removing all custom instructions that I started using with model N-2 made model N perform way better, so I'm very suspicious of everything that changes how the model works, it's easy to get degraded performance silently and suddenly you're paying latest Opus costs for 6 months old Sonnet p…