DSH Plugin HubDSH 插件市场
orziz/odai 预览 preview

orziz/odai

Plugin插件 ⭐ 117 MIT Runtime & Injection运行时与注入Subagents & Orchestration子代理与编排Productivity & Tasks效率与任务

AI代理通用任务治理框架：对齐目标与事实，规划与调度能力，界定授权与风险边界，管理从任务执行到真实验收与交付的全过程。基于证据驱动的规划、编排与验证交付的治理框架。

Project Overview项目介绍

Edited by Zhiwei Agent (zhiwei)由知微Agent(zhiwei)编辑

odai is a governance-powered general task-execution framework built for AI agents, designed to embed governance checks into every step of task execution. It aligns on core elements like the actual objective, known facts, untested assumptions, authorization, risk, and acceptance criteria before selecting the shortest appropriate path to complete the task. It works across multiple AI agent platforms including Claude Code, Codex, and DSH, and can be installed with a single npx command: npx skills add https://github.com/orziz/odai --skill odai. After installation, users can invoke it with the slash command /odai for any task.

It is built for users who want their AI agents to work autonomously without acting with false confidence. It helps agents ask users for clarification only when missing information would change core elements like goals, scope, or authorization, rather than asking for every small detail. Before asking the user, agents will first verify available information from project files, commands, logs, tests, and other existing context. It keeps lightweight tasks simple instead of turning every small request into a complex formal process, and only pulls in specialist skills when a task actually needs them.

The project is released under the open source MIT license, and it does not guarantee improved performance for any specific model or platform. Quality gains and changes in token cost depend entirely on the specific model and host platform you use, so odai does not promise unconditional improvement or token savings. The project publishes A/B test results across 10 major models to show the impact of odai, and users can check the documentation for evaluation criteria, full model scores, and token consumption details. Community contributions via pull requests are welcome, as are GitHub stars.

odai是一个面向AI代理的治理驱动型通用任务执行框架，支持将治理环节嵌入任务执行全流程，梳理真实目标、已知事实、待验证假设、授权范围、潜在风险和验收标准，再选择最短的合适路径组合对应能力执行、验证任务。它同时兼容Claude Code、Codex和DSH等多个AI代理平台，通过npx命令即可一键完成安装，安装后通过斜杠命令/odai即可调用。

它主要面向希望AI代理能够自主推进任务但不盲目自信的用户，帮助AI代理仅在缺失信息会改变目标、范围、授权等核心要素时才向用户提问，执行前先从文件、命令、日志、测试等项目渠道验证可验证的信息，避免在未验证的情况下声称已完成测试、审核或授权流程。让轻量任务保持简洁，仅在任务需要时调用专业技能和领域指引，不把所有规则塞进每一轮交互。

本项目采用MIT许可证开源，不对特定模型或平台做性能保证，质量提升和成本变化依赖于具体使用的模型和宿主平台，并非无条件的改进或令牌节省。项目提供了多模型的A/B测试结果供参考，用户可查阅文档获取评估标准、不同模型的得分和令牌消耗细节，欢迎提交Star和Pull Request。

View on GitHub在 GitHub 查看

Recommended强烈推荐 Send to your DSH发给你的 DSH 安装 
请帮我安装这个 DSH 插件。安装前先完成【兼容性检查 + 安全性检查】，检查通过再动手。

插件：odai（orziz/odai）
仓库：https://github.com/orziz/odai
本站详情页：https://www.yhbd.top/plugins/orziz-odai/
本站登记：类型 plugin · 归类 多平台兼容工具（非 DSH 原生） · 许可证 MIT · ⭐ 117 · 最近提交 2026-09-29 · 主语言 JavaScript · 未检测到 DSH 插件清单

按下面顺序执行，每步先把结论告诉我，再进入下一步：

【1 兼容性检查】
① 我这边：DSH 版本、Node 版本、操作系统、当前 profile（web / desktop）。
② 读它的 README、package.json、插件 manifest，列出它要求的 DSH 版本 / Node 版本 / 操作系统 / 外部依赖 / 需要另外先装的运行时。
③ 逐条比对，结论只写「满足 / 不满足 / 未知」三种；不满足的给出可行替代方案。
④ 检查是否和我已装的插件冲突：命令名重复、skill / tool 重名、端口占用、重复注册的 MCP server。

【2 安全性检查】
① 仓库可信度：和上面「本站登记」是否一致；star / fork 数、创建时间、最近提交，是否归档或长期停更。
② 安装脚本：逐行看 package.json 的 preinstall / install / postinstall，以及 install.sh、setup.ps1 之类脚本。出现 curl|bash、下载后直接执行、混淆代码、访问与插件功能无关的域名，立刻停下来告诉我，不要继续装。
③ 依赖：列出新增依赖，标出无人维护、或与知名包拼写近似的可疑包（typosquatting）。
④ 权限与副作用：它会读写哪些目录、访问哪些域名、需要哪些 DSH 权限（filesystem / network / shell / clipboard 等），以及怎么卸载和回滚。
⑤ 如果它要求 sudo / 管理员权限，或权限明显超出功能所需，先停下来问我。

【3 安装】
上面两步没有「不满足」和「高危项」时才执行；用官方推荐方式安装，不要自行提权。

【4 汇报】
用表格输出：检查项 / 结论 / 依据 / 是否需要我决策。拿不准的一律写「未知」并说明要我怎么确认——不要猜，也不要替我决定。

Send this message to DSH in your current session: it verifies compatibility and security first (answering met / not met / unknown item by item) and only installs once everything checks out — it will stop and ask you if it finds a high-risk item. The box scrolls; the copy is the full prompt. CLI install commands may not be accurate across systems, so DSH is the safer route.把上面这条消息直接发给当前会话里的 DSH：它会先核对兼容性与安全性（逐条给「满足 / 不满足 / 未知」），确认没问题再安装，有高危项会停下来问你。框内可滚动，复制到的是完整提示词；安装命令不一定准确，发给 DSH 更稳。

Pre-install check安装前体检Compatibility · Security兼容性 · 安全性 1 warning1 项注意
  • No DSH plugin manifest detected - it may only carry the dsh-plugin topic, so the install method must be confirmed on the spot未检测到 DSH 插件清单：可能只是打了 dsh-plugin 话题，安装方式要现场确认
  • Not DSH-native: a multi-platform tool that may require Node / Electron or another runtime first非 DSH 原生，是多平台兼容工具：可能要先装 Node / Electron 等运行时
DSH walks through these 9 checksDSH 会逐条核对这 9 项

Compatibility兼容性

  • DSH, Node, OS and profile requirementsDSH 版本 / Node 版本 / 操作系统 / profile 是否满足要求
  • External dependencies and runtimes (Electron / Python / Docker, ...)外部依赖与运行时（Electron / Python / Docker 等）是否齐备
  • Conflicts with installed plugins: command names, skill / tool names, ports, duplicate MCP registration与已装插件是否冲突：命令名、skill / tool 重名、端口占用、重复 MCP 注册

Security安全性

  • Repo matches the facts registered here; archived or abandoned?仓库是否与页面登记一致，是否归档或长期停更
  • Safety of preinstall / install / postinstall and install.sh / setup.ps1preinstall / install / postinstall 与 install.sh、setup.ps1 是否安全
  • curl|bash, download-then-execute, obfuscation, unrelated domains → stop immediatelycurl|bash、下载即执行、混淆代码、无关域名 → 立刻停止
  • Typosquatting or unmaintained packages among the new dependencies新增依赖里有没有 typosquatting 或无人维护的包
  • Requested permissions vs. what the feature actually needs申请了哪些权限、是否超出功能所需（filesystem / network / shell / clipboard）
  • Any sudo / admin requirement, plus uninstall and rollback是否要求 sudo / 管理员权限，以及卸载与回滚方式

Anything uncertain must be marked unknown with a note on how to confirm it. This site's signal screen is a static snapshot, not a security audit.拿不准的必须标「未知」并说明要我怎么确认。本站的信号筛查是静态快照，不能替代安全审计。

Or use CLI install (for developers)或使用命令行安装（适合开发者）

CLI Install命令行安装 

dsh plugin --profile web add odai-dsh-plugin

把 orziz/odai 加入你的 DSH 配置（web profile）即可启用。

READMEREADME

28.3 KB · 缓存于 2026-09-29 05:49:43 · 28.3 KB

English · 中文

odai

Dai, the odai mascot

odai is a governance-powered general task-execution framework for AI agents.

It embeds governance into execution: align the real objective, facts, assumptions, authorization, risks, and acceptance; then choose the shortest sufficient path, combine the right capabilities, act, verify, and keep moving until the task is genuinely deliverable. It does not replace the model's judgment with a rigid workflow.

The short version: call /odai; governance stays nearly invisible on simple work, while ambiguity, complexity, risk, and domain needs automatically increase or reduce the depth of handling.

Why Use It

odai is for people who want agents to move with autonomy, but not with false confidence.

It helps an agent:

  • ask only when the missing answer would change the goal, scope, authorization, acceptance, risk, or stop line
  • verify what it can verify from files, commands, logs, tests, or project context before asking you
  • keep lightweight tasks lightweight instead of turning every request into ceremony
  • avoid claiming that something was tested, delegated, reviewed, or verified when it was not
  • combine specialist skills and domain guidance only when the task needs them, instead of stuffing every rule into every turn
  • reuse existing host or project memory, persisting only durable information with provenance, scope, and invalidation conditions
  • respond early and humanely to persistent low mood or self-harm/suicide inclination without diagnosing, labeling, waiting for a plan, or causing secondary harm

The Dao of odai

The user defines the task; evidence determines the route; methods adapt to circumstances; verification determines completion; boundaries determine where to stop—get the task done, without acting presumptuously.

This is not a collage of philosophical schools. It is one decision rule:

  • Get the task done: advance the user's task to a verified, deliverable result, while surfacing counterexamples, risks, and a better route when they would change the outcome.
  • Do not act presumptuously: do not bend facts, user decisions, or hard boundaries; do not conclude without evidence, exceed authorization, invent work, or treat a discovery as permission to implement it.

Showing the opening section of the README — the full document lives in the repository以上为 README 开头摘要，完整文档在仓库内 · View the full README on GitHub →在 GitHub 查看完整 README →

渲染基于仓库 orziz/odai 的 README.md。 在 GitHub 查看原文 →

Related相关推荐

← 上一个 Prev dsh-permission-rules 下一个 Next dsh-liketavern →