From 6c0fe8517d887ad708bb96178df64e89096a3628 Mon Sep 17 00:00:00 2001 From: garrytan Date: Sat, 3 Oct 2026 22:31:38 +0000 Subject: [PATCH] I3: plan-ceo-review defines the closing sequence's cleanup step Two of three judge samples for 'plan-ceo-review/SKILL.md modes' in periodic run 37151477069 (actionability at the 4.0 gate) flag 'perform permitted cleanup' as never defined. The only cleanup the skill has is archiving old CEO plans, which needs approval; step 5 now says so. --- plan-ceo-review/sections/review-sections.md.tmpl | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/plan-ceo-review/sections/review-sections.md.tmpl b/plan-ceo-review/sections/review-sections.md.tmpl index af7173743..febb2d202 100644 --- a/plan-ceo-review/sections/review-sections.md.tmpl +++ b/plan-ceo-review/sections/review-sections.md.tmpl @@ -331,7 +331,7 @@ Continue through the blocks below in file order: 2. **Resolve remaining TODO choices:** use the selected mode's scope rules. 3. **Approval readiness:** check the ledger and record PASS before writing outputs. Its complete checklist is immediately after the TODO choices; no report or log is needed yet. 4. **Required Outputs:** follow the three stages below: prepare the plan body and summary, save and verify the terminal report, then publish the summary in chat. -5. **Cleanup and history:** perform permitted cleanup, attempt Review Log under the Artifact outcomes policy, then display the dashboard with the actual logging outcome. +5. **Cleanup and history:** archive old CEO plans only if the user approved it (otherwise skip cleanup), attempt Review Log under the Artifact outcomes policy, then display the dashboard with the actual logging outcome. 6. **Navigation:** choose Next Steps and any docs/designs promotion; queue the next skill. For a substantive answer, call 0D for only that change, repeat Approval readiness and Required Outputs, then repeat step 5. Resume navigation without asking settled choices again. Navigation alone does not reopen decisions. 7. **Learnings:** finish learning and brain write-back. Return to this skill's main `SKILL.md`, at **Section self-check**. Its EXIT gate verifies completed work and saved readiness without asking again. After a passing gate, refresh the cache, run telemetry last, then exit or return to the caller.