플러그인

Multi-agent isolated debate for DeepSeek Harness: debaters of different temperaments research independently (no herding), then cross-examine, then judges converge to a conclusion. Runs as a background job with per-agent progress, token accounting, wave-parallel execution, and session-referenced resume.

Hold a DeepSeek Harness agent to a capmark capability manifest: mask its tools and judge every call.

OI 出题工作台：知识点锁定、数据构造、本地评测，打包 Hydro/HOJ 原生题目包，发布/管理 Hydro 与 HOJ OJ，提供 Python 外部管理 UI 与系统斜杠命令。Opt-in skill-first plugin for DeepSeek Harness.

Plugin value auditor: pre-install review (source scan + LLM judge) and post-install audit of installed bundles, with model-switch re-audit reminders.

deepseek-harness 저장소와 dsh-plugin 태그가 붙은 모든 저장소를 탐색해 목표와 관련된 하네스를 발견하고, 각각을 시도할 만함/지켜볼 만함/건너뛸 만함으로 판단