📖About

Create a new Carolverse service - Quality Management - owned by a NEW agent Prometheus (continuous-improvement enhancer; counterpart to Hermione healing, counterbalance to Themis compliance). Prometheus reports to Rhea (Operations); Rhea gains a 5th report - documented span-of-control exception like Cassius. Register: the service + cost center + blocks; 5 droids (Retrospective Analyst, Improvement Proposer, Maturity Assessor, Best-Practice Sweep, App Steward); 3 apps (Improvement Register, Quality Scorecard, Lessons Learned). Two NEW policies: (1) one-agent-one-service (an engaged agent cannot own/join another service); (2) droids scale work, agents scale accountability (volume never justifies a new agent; only a distinct mandate or separation-of-duties does). Economic model: quality is overhead - 1 metric free per service, every additional metric requested by the service owner; until owners can decide, Orion-via-Ninad backfills. Closed-loop: reuse the existing RSI triad (metric->scoreboard->improvement engine). Document open ends: new-metric instrumentation gap + who audits Quality. Immortal info propagated to the Services Catalogue overview, Carolopedia, and the registry descriptions - not just this initiative. Re-home the add-new-service skill from Build/Sage to Strategy/Leo with the new gates; save tacit knowledge to Leo memory.

⚖️Decisions

• Elrond's bypass methodology checklist (a reminder, not a gate -- you've got this): 0. File it requested_mode='bypass' (planner-vs-bypass is a deliberate choice). bypass_start REFUSES a non-bypass initiative (CAROL-INI-1846), and the dispatcher only skips the bypass lane when the mode says bypass -- a 'planner' mistag lets Merlin's pipeline grab the placeholder step and block your finished work. 1. Filed as planned status -- let the bypass claim/activate it; never file active. 2. Open the bypass (bypass_start) with your droid id + the remediation answer (remediates_initiative_id=NNN, or remediates_nothing=True). 3. Work the blocks for your work-type: template -> design -> code -> test -> review. Do the real work; record decisions on the initiative as you make them. 4. Reality is recorded for you at close -- code (files changed), each decision, and the twin-review verdict become real activities tied to this initiative and show in the Activity Tracker like a planner run (CAROL-INI-1840). No dummy rows. 5. Keep the initiative status moving; it parks in 'reviewing' and is tagged uat-pending for you at close (CAROL-INI-1836), so the stuck-watchdog leaves it alone until UAT. 6. Close runs the gates (design/architecture compliance + caller-audit). If a gate flags something pre-existing or unrelated to your change, waive it with a clear written rationale -- audit, don't skip. 7. Bypass skips the planner's auto-orchestration, NOT the standards. Same template checklist, same review, same observability as a planner run. (elrond)
• [status-router] planned -> executing | event=bypass_executing | bypass transition (or-bx-01)
• [status-router] executing -> reviewing | event=bypass_reviewing | bypass transition (or-bx-01)
• [status-router] reviewing -> closed | event=operator_signoff | Auto-accepted (CAROL-INI-1859): Orion-initiated, >2 days in reviewing with no objection. (el-srac-01)