SEMANTIC DIRECTORY · plugin-directory-semantic-v3-19
代理行为与范围守卫
通过钩子、提示注入或确定性规则约束代理运行时行为和修改边界，包括阻止高危命令或测试削弱、强制先调研、文档同步、范围锚定和保守修改。排除单纯方法论指导及交付结果审计。
叶子目录成员
21 个插件
project-change-router-skillWeirdSky924/project-change-router-skill目录 已分析Project-level change routing and reuse governance for AI coding agents. Helps Codex and Claude Code find the right capability boundary, avoid duplicate implementations, respect write constraints, and calibrate routing decisions for large full-stack repositories.兼容性DSH 0.1.6-alpha.2 · web依赖审计未测试制品未解析证据更新2026-09-27公开信号2 starsstupid-commentsstupid-comments目录 已分析Enforces your comment policy at write time, inside DeepSeek Harness. Reads the policy from your AGENTS.md or CLAUDE.md, blocks violating writes, and re-injects the policy verbatim so the model stops drifting from it.兼容性DSH 0.1.6-alpha.2 · web依赖审计有限审计报告 0 项制品0.2.1证据更新2026-09-24公开信号454 downloadszerotoken-skillphoenixlucky/zerotoken-skill目录 已分析让 Agent 高效又守纪律 — 不止省 token：ZeroToken 压缩无效上下文/推理/输出；尉缭子十原则约束权限边界、单一指令、先谋后动、验证先于结束；附 Unicode 编码规范、搜索规范、六种任务模式。More than token savings: ZeroToken efficiency + AI coding discipline for Reasonix / Codex / OpenCode / Hermes兼容性DSH 0.1.6-alpha.2 · web依赖审计未测试制品未解析证据更新2026-09-27公开信号16 stars
分类属于公开语义索引事实，不是最终推荐；兼容性、权限与来源证据仍需分别核对。