jared 5b399d5614 Record Eval A and Eval B grid results in status docs ... Eval A grid ran clean across all scenarios/tiers. Eval B grid (1 rep/cell) shows a real gap: haiku never unprompted-consults the ADR system in any scenario, while sonnet passes 5/8 (misses W3 write-trigger and R1 direct- conflict retrieval). Updates CLAUDE.md component status and the eval-b README so the next session picks up from here instead of re-running blind. Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>		2026-07-03 17:36:37 -04:00
..
os-adr	Record Eval A and Eval B grid results in status docs	2026-07-03 17:36:37 -04:00
os-doc-hygiene	Align os-doc-hygiene skill naming and invocation with marketplace convention	2026-07-03 11:23:24 -04:00
os-orchestration	Migrate os-orchestration plugin from cc-plugins into cc-os	2026-07-03 10:14:35 -04:00
os-vault	Rename memory plugin to os-vault; fix marketplace registration	2026-07-03 09:43:18 -04:00