plan: queue cf48 — Opus 4.8 post-cfold coverage-loss review (cross-check of cf55 GPT-5.5)

Second independent review of the cfold custom-folder collapse, by Opus 4.8
instead of GPT-5.5, inserted after cf55 (queue ...cfold;cf55;cf48;pvfix;...).
Per-phase overrides .loop-model[-adv]-cf48=claude-opus-4-8 on the claude backend.

cc-ci-plan/JOURNAL.md

@@ -607,3 +607,14 @@ session cc-ci-orchestrator-stale can be killed; recipe-mirrors org still private
   a manual nudge landed as a shell command, so restarted only `cc-ci-builder` via `start_agent`; it came
   back on OpenCode GPT-5.4 and is actively planning the M2 sweep. Adversary accepted its nudge and wrote
   `WAITING-UNTIL: 2026-06-12T21:55:28Z` while awaiting Builder's formal M2 claim.
+
+## 2026-06-13 ~05:15 — queued cf48 (Opus 4.8 cfold review, second model)
+- Operator: add a second independent post-cfold coverage-loss review by Opus 4.8 (cross-check
+  of the cf55 GPT-5.5 review). Plan: plan-phase-cf48-opus-cfold-review.md — same 7 review
+  categories as cf55, independent verdict + a cf55-vs-cf48 agreement note.
+- Inserted cf48 after cf55: queue = ...cfold;cf55;cf48;pvfix;pvcheck;ghost (15 phases, idx 10=cf55).
+- Per-phase model overrides: .loop-model-cf48 = .loop-model-adv-cf48 = claude-opus-4-8 (claude
+  backend — current .loop-backend=claude, so it'll run on opus; orchestrator must keep backend=claude
+  when cf48 starts since per-phase backend isn't overridable).
+- Also this session: relaunched after a session restart (NOT a host reboot, 13d uptime); loops+watchdog
+  were stopped in a claude-sonnet limit window on cf55 → restarted via RESUME_PHASE=1 launch.py start.