Impeccable's critique runs two isolated assessments. design-critique-a
runs the design-director review on Claude Opus 5.5 at xhigh, with Fable
5.1 behind it; Opus 5.5 has the top Design Arena website score of the
models in this config. design-critique-b runs the detector and browser
pass on GPT-6.1 Sol at high, with Sonnet 5.5 behind it so the second
assessment still runs without a ChatGPT login. critique.md sends each
assessment to its category.
- Raise main Opus 5.5 to xhigh and its Sol fallback to high
- Raise deep-low Sonnet 5.5 and Sol to high for coding work
- Route quick, explore and librarian to GLM-5.3-Flash low with Sonnet low fallback
- Replace unsupported GLM medium thinking with high in unspecified-low and writing
- Remove the unused [opencode] block
Adds /owt-done (close Linear issues after merge, then owt done) and
/linear-sync (progress comment and status, no cleanup), linked into omo
as ~/.omo/agent/prompts.
David Ibia