A Korean Claude Code plugin that lets non-developers safely make AI "keep working until it's done." It includes three modes: iterative repair, goal achievement, and scheduled checkup (report-only), with 14 safety guardrails enabled by default (risk confirmation, automatic backups, convergence stopping, plan guidance, startup procedure protection, and more). Slash commands use the /sodam-loop:xxx format. The Codex CLI safety gate is under development in Phase 2 (code complete but unregistered and
Plugin Claude Code
Bundles 9 skills, 9 commands, 1 agent, 4 hooks · 878 tokens together
A Korean-language safety loop for non-developers who ask an AI to keep repairing a task until it works. Its description says it currently supports a single repair mode with 14 safety guardrails enabled by default.