cc-sync-execute-loop

# CC Sync Execute Loop Run the execution side of the CC-to-Codex workflow. This skill owns the loop, lock, heartbeat, plan-state update, and bounded execution cycle. It does not audit raw Claude Code drift; `$cc-sync-runner` owns review/planning. ## Boundary - Consume reviewed and approved plan artifacts; do not create the sync plan from scratch unless the user explicitly redirects to planning. - Treat `CC_SYNC_PLAN.md` / `REVISED_CC_SYNC_PLAN.md` as durable state. Conversation context is helpful but not authoritative. - Preserve scan -> approval -> execute boundaries. Do not execute unapproved work. - Keep `.claude/` and `CLAUDE.md` read-only. - Do not copy private course playbooks, real course IDs, private URLs, instructor names, emails, or identity details into Codex artifacts. - Do not submit to Canvas, answer quizzes, upload files, push upstream, or run live external actions from this skill. ## Relationship To cc-sync-runner Use `$cc-sync-runner` for: - generating `runs/codex/<today>/CC_SYNC_PLAN.md` - reviewing raw sync plans - writing `REVISED_CC_SYNC_PLAN.md`, `CAPABILITY_GAPS.md`, `PROPOSED_BATCHES.md`, and `NEW_SKILL_SPECS.md` - deciding public/private sync classification Use `$cc-sync-execute-loop` only after the user approves the reviewed plan or approved batch. If approval or reviewed plan evidence is missing, write a blocker in the loop state and stop. Do not silently fall back into planning. ## Plan Lookup Prefer artifacts in this order: ...