Command-triggered red/blue adversarial review for ANY plan (not quant-specific). /plan-adversarial <plan>: arms a gate that requires the agent to derive two independent subagents (red=attack, blue=defend), have them converge on a consensus plan with NO th
作者： gendui123 · UI 增强 · 目录快照： 2026-09-05Command-triggered red/blue adversarial review for ANY plan (not quant-specific). /plan-adversarial <plan>: arms a gate that requires the agent to derive two independent subagents (red=attack, blue=defend), have them converge on a consensus plan with NO th
第三方目录导入描述，不是 Registry 验证结论。gendui123/dsh-plan-adversarial
— stars · 158 downloads
信号由来源目录提供，不代表质量或安全。 2026-09-05尚无精确版本测试。
尚无 Registry 安全结论。
尚无功能冒烟证据。
尚未解析插件权限。
版本与完整性尚未解析。
在 DSH 对话中描述你的任务，并提到 dsh-plan-adversarial. 插件管理器可通过 Registry 搜索到此候选，再在本地检查实际来源与版本。
dsh-plan-adversarial未解析精确版本github:gendui123/dsh-plan-adversarial未解析精确版本