Interesting. I will try some of of those instructions but I don't mind much about the tics.

My actual complaint: end-of-turn summaries that are undecipherable unless you watched the session closely. Both Opus and Fable regularly ends hours of work with status updates phrased in crystal clear terms like:

  "**V2** debug-helper gate (R4d) | Medium-risk | Gate on `?debug=1` URL param at 3 fixture sites — **not** a localStorage flag (`browser_page` clears it every test). 284 debug-API calls ride the fixture, so R4d goes last+alone"

Bit frustrating. any kind of benchmark or even a few examples showing that this produces better outputs would have been nice.

Does this work? Appreciate honest testimonials from anybody unrelated to the OP or author.