sub-codex
structurally validOne provider, differentiated by task — the max-reasoning tier for planning, the standard tier for the everyday, a cheaper tier for chores. All OpenAI Codex, so it runs in a single-provider harness (Codex) as well as omp/pi. Reach for it when you are all-in on one provider but still want per-task model selection.
Providers
Source
The indexed metadata matched the source at the last check.
oompf add https://oompf.run/p/prof_8d14c0854bfdd11cf75a5f0226b6441aInstalls as a native OMP profile. Nothing is overwritten — a name collision fails instead. How installing works
Models
Friendly name first; exact selector beneath. Model resolution
openai-codex/gpt-5.6-luna- GPT-5.6 Luna ↗thinking max
openai-codex/gpt-5.6-luna:max openai-codex/gpt-5.5
Behavior
Model roles
- defaultGPT-5.6 Luna
- taskGPT-5.6 Luna
- planGPT-5.6 Lunathinking max
- slowGPT-5.6 Lunathinking max
- smolGPT-5.5
- commitGPT-5.5
Advisor
- Advisor
- enabled
Settings
- Symbol preset
- default
- Default thinking level
- medium