This sounds psychotic. An over-controlling fedora's approximation of what good academic parenting looks like. You just want to create your D&D partner. You'll probably succeed lol.
"i really wish this thing in my non native language was easier to decipher"
huh? if you dont know the words then read them in your native language. Sol/Terra/Luna are immediately unambiguous to an english speaker with any sense.
I'll correct myself. 1 Skill for helping refine your plan/spec with propositional yes/no questions. After that no more skills needed to emulate superpowers honestly. Workflows do the rest and claude will do that for you. ultracode is 90% of superpowers
Codex has been comparable for a while. 5.1-5.5 have competed closely with 4.5-4.8. Fable blew them all out, now Sol comparable to Fable again. Some slight tooling differences with skills and hooks but for the most part I think if people are so engineered into one CLI that swapping to another inhibits them, then that is an error in usage habits.
Codex historically will follow tasks more closely with less creativity, whereas Opus will do more than you specify. I wouldnt consider either one better due to this fact, just makes them useful for different situations. Generally they'll perform similarly for most tasks.
Opus and Fable dominate 5.5 in artistic design (pixel art, ascii art), and edge out 5.5 slightly in general UI design taste. Have not tested Sol in that regard yet.
So far in my usage Sol has been superior to Fable at graphics rendering engine optimization.
Codex will work longer, and in single sessions without as much subagent usage.
Codex only has 256k context but its compaction is absolutely next level. You will not notice compactions and they will happen multiple times during a complex task or set of tasks without you ever having to notice or care. Claude code on the other hand still has fairly poor compaction.
Codex has more generous usage limits, and they also give you usage resets (weekly+5h resets) that you can bank for a month or so. Not sure how often they give these out.
Codex also seemingly never has outages or weird delays like Claude code does.
OpenAI randomly resets usage just like Anthropic does
No thats probably because you misread what you were replying to and your comment was out of left field. They didnt imply models get better intra-releasally at all.
It does not make LLM work predictable. Try it on the same type of project twice and see. You think you're saving time but youd accomplish similar results with 2 or 3 skills.