Trevin Chow 2760f28e85 refactor: merge deepen-plan into ce:plan as automatic confidence check ...

The deepen-plan skill's confidence-gap evaluation and targeted research
agent dispatching are now an automatic phase (5.3) inside ce:plan. The
agent decides whether deepening is needed and reports what it's
strengthening — the user no longer makes that choice.

- Add Phase 5.3 (Confidence Check and Deepening) to ce:plan with the
  full scoring checklist, agent mapping, and synthesis rules from
  deepen-plan
- Add re-deepen fast path in Phase 0.1 for resume mode
- Add pipeline-mode gate in Phase 5.4 so lfg/slfg don't stall
- Remove deepen-plan skill directory
- Remove deepen-plan step from lfg and slfg orchestrators
- Update README, AGENTS.md, learnings-researcher, document-review
- Replace deepen-plan references in converter/writer tests

2026-03-26 20:35:14 -07:00

..

brainstorms

refactor: merge deepen-plan into ce:plan as automatic confidence check

2026-03-26 20:35:14 -07:00

plans

refactor: merge deepen-plan into ce:plan as automatic confidence check

2026-03-26 20:35:14 -07:00

solutions

feat: add project-standards-reviewer as always-on ce:review persona (#402)

2026-03-26 19:20:15 -07:00

specs

feat: migrate repo releases to manual release-please (#293)

2026-03-17 17:58:13 -07:00