Turn any domain folder of skills into a bounded agentic loop: compile a goal into a verifiable task plan, execute tasks with the domain's own tools, verify every task with machine-run checks, retry with caps, escalate to a human when budgets exhaust, and refuse to close until everything is verified or explicitly waived. Use when you want an agent or subagent to pick up a goal and drive it to a verified close across one of this repo's 18 domains ('run this goal through the engineering harness', 'set up an agentic loop for marketing work', 'make the finance domain self-verifying'). NOT for authoring Claude Code Workflow-tool .js scripts (workflow-builder), N-agent tournaments on one task (agenthub), single-file metric optimization (autoresearch-agent), or discovering published loop recipes (loop-library).

>-

Extract quantities from IFC/Revit models for quantity takeoff. Uses DDC converters to get element counts, areas, volumes, lengths with grouping and reporting.

>-

Autonomous skill-prompt optimization — Karpathy-style mutate/score/keep loop on SKILL.md. Triggers "autoresearch", "optimize skill", "tune", "evolve" a skill, "prompt optimization".

Comprehensive pre-release code review assessing test coverage, code duplication, and component interactions

디스코드에 상주하는 대화형 AI 봇을 여러 개 만들고 운영한다. 상시 구동 머신에서 겪는 함정(절전 모드, 설정파일 자동로딩, 사용량 한도)을 함께 정리했다.