# qualixar-os - Doramagic AI Context Pack

> 定位：安装前体验与判断资产。它帮助宿主 AI 有一个好的开始，但不代表已经安装、执行或验证目标项目。

## 充分原则

- **充分原则，不是压缩原则**：AI Context Pack 应该充分到让宿主 AI 在开工前理解项目价值、能力边界、使用入口、风险和证据来源；它可以分层组织，但不以最短摘要为目标。
- **压缩策略**：只压缩噪声和重复内容，不压缩会影响判断和开工质量的上下文。

## 给宿主 AI 的使用方式

你正在读取 Doramagic 为 qualixar-os 编译的 AI Context Pack。请把它当作开工前上下文：帮助用户理解适合谁、能做什么、如何开始、哪些必须安装后验证、风险在哪里。不要声称你已经安装、运行或执行了目标项目。

## Claim 消费规则

- **事实来源**：Repo Evidence + Claim/Evidence Graph；Human Wiki 只提供显著性、术语和叙事结构。
- **事实最低状态**：`supported`
- `supported`：可以作为项目事实使用，但回答中必须引用 claim_id 和证据路径。
- `weak`：只能作为低置信度线索，必须要求用户继续核实。
- `inferred`：只能用于风险提示或待确认问题，不能包装成项目事实。
- `unverified`：不得作为事实使用，应明确说证据不足。
- `contradicted`：必须展示冲突来源，不得替用户强行选择一个版本。

## 它最适合谁

- **AI 研究者或研究型 Agent 构建者**：README 明确围绕研究、实验或论文工作流展开。 证据：`README.md` Claim：`clm_0004` supported 0.86
- **正在使用 Claude/Codex/Cursor/Gemini 等宿主 AI 的开发者**：README 或插件配置提到多个宿主 AI。 证据：`README.md` Claim：`clm_0005` supported 0.86
- **希望把专业流程带进宿主 AI 的用户**：仓库包含 Skill 文档。 证据：`.claude/skills/gitnexus/gitnexus-cli/SKILL.md`, `.claude/skills/gitnexus/gitnexus-debugging/SKILL.md`, `.claude/skills/gitnexus/gitnexus-exploring/SKILL.md`, `.claude/skills/gitnexus/gitnexus-guide/SKILL.md` 等 Claim：`clm_0006` supported 0.86

## 它能做什么

- **AI Skill / Agent 指令资产库**（可做安装前预览）：项目包含可被宿主 AI 读取的 Skill 或 Agent 指令文件，可用于把专业流程带入 Claude、Codex、Cursor 等宿主。 证据：`.claude/skills/gitnexus/gitnexus-cli/SKILL.md`, `.claude/skills/gitnexus/gitnexus-debugging/SKILL.md`, `.claude/skills/gitnexus/gitnexus-exploring/SKILL.md`, `.claude/skills/gitnexus/gitnexus-guide/SKILL.md` 等 Claim：`clm_0001` supported 0.86
- **多宿主安装与分发**（需要安装后验证）：项目包含插件或 marketplace 配置，说明它面向一个或多个 AI 宿主的安装和分发。 证据：`claude-code-plugin/plugin.json`, `packages/qos-claude-code/plugin.json`, `registry-listings/cursor-plugin.json`, `registry-listings/mcp-marketplace.json` Claim：`clm_0002` supported 0.86
- **命令行启动或安装流程**（需要安装后验证）：项目文档中存在可执行命令，真实使用需要在本地或宿主环境中运行这些命令。 证据：`README.md`, `packages/qos-claude-code/README.md` Claim：`clm_0003` supported 0.86

## 怎么开始

- `npx qualixar-os` 证据：`README.md` Claim：`clm_0007` supported 0.86
- `npm install -g qualixar-os` 证据：`README.md` Claim：`clm_0008` supported 0.86
- `git clone https://github.com/qualixar/qualixar-os.git` 证据：`README.md` Claim：`clm_0009` supported 0.86
- `npm install -g qos-claude-code` 证据：`packages/qos-claude-code/README.md` Claim：`clm_0010` supported 0.86

## 继续前判断卡

- **当前建议**：需要管理员/安全审批
- **为什么**：继续前可能涉及密钥、账号、外部服务或敏感上下文，建议先经过管理员或安全审批。

### 30 秒判断

- **现在怎么做**：需要管理员/安全审批
- **最小安全下一步**：先跑 Prompt Preview；若涉及凭证或企业环境，先审批再试装
- **先别相信**：工具权限边界不能在安装前相信。
- **继续会触碰**：命令执行、宿主 AI 配置、本地环境或项目文件

### 现在可以相信

- **适合人群线索：AI 研究者或研究型 Agent 构建者**（supported）：有 supported claim 或项目证据支撑，但仍不等于真实安装效果。 证据：`README.md` Claim：`clm_0004` supported 0.86
- **适合人群线索：正在使用 Claude/Codex/Cursor/Gemini 等宿主 AI 的开发者**（supported）：有 supported claim 或项目证据支撑，但仍不等于真实安装效果。 证据：`README.md` Claim：`clm_0005` supported 0.86
- **适合人群线索：希望把专业流程带进宿主 AI 的用户**（supported）：有 supported claim 或项目证据支撑，但仍不等于真实安装效果。 证据：`.claude/skills/gitnexus/gitnexus-cli/SKILL.md`, `.claude/skills/gitnexus/gitnexus-debugging/SKILL.md`, `.claude/skills/gitnexus/gitnexus-exploring/SKILL.md`, `.claude/skills/gitnexus/gitnexus-guide/SKILL.md` 等 Claim：`clm_0006` supported 0.86
- **能力存在：AI Skill / Agent 指令资产库**（supported）：可以相信项目包含这类能力线索；是否适合你的具体任务仍要试用或安装后验证。 证据：`.claude/skills/gitnexus/gitnexus-cli/SKILL.md`, `.claude/skills/gitnexus/gitnexus-debugging/SKILL.md`, `.claude/skills/gitnexus/gitnexus-exploring/SKILL.md`, `.claude/skills/gitnexus/gitnexus-guide/SKILL.md` 等 Claim：`clm_0001` supported 0.86
- **能力存在：多宿主安装与分发**（supported）：可以相信项目包含这类能力线索；是否适合你的具体任务仍要试用或安装后验证。 证据：`claude-code-plugin/plugin.json`, `packages/qos-claude-code/plugin.json`, `registry-listings/cursor-plugin.json`, `registry-listings/mcp-marketplace.json` Claim：`clm_0002` supported 0.86
- **能力存在：命令行启动或安装流程**（supported）：可以相信项目包含这类能力线索；是否适合你的具体任务仍要试用或安装后验证。 证据：`README.md`, `packages/qos-claude-code/README.md` Claim：`clm_0003` supported 0.86

### 现在还不能相信

- **工具权限边界不能在安装前相信。**（unverified）：MCP/tool 类项目通常会触碰文件、网络、浏览器或外部 API，必须真实检查权限和日志。
- **真实输出质量不能在安装前相信。**（unverified）：Prompt Preview 只能展示引导方式，不能证明真实项目中的结果质量。
- **宿主 AI 版本兼容性不能在安装前相信。**（unverified）：Claude、Cursor、Codex、Gemini 等宿主加载规则和版本差异必须在真实环境验证。
- **不会污染现有宿主 AI 行为，不能直接相信。**（inferred）：Skill、plugin、AGENTS/CLAUDE/GEMINI 指令可能改变宿主 AI 的默认行为。 证据：`.claude/skills/gitnexus/gitnexus-cli/SKILL.md`, `.claude/skills/gitnexus/gitnexus-debugging/SKILL.md`, `.claude/skills/gitnexus/gitnexus-exploring/SKILL.md`, `.claude/skills/gitnexus/gitnexus-guide/SKILL.md` 等
- **可安全回滚不能默认相信。**（unverified）：除非项目明确提供卸载和恢复说明，否则必须先在隔离环境验证。
- **真实安装后是否与用户当前宿主 AI 版本兼容？**（unverified）：兼容性只能通过实际宿主环境验证。 证据：`claude-code-plugin/plugin.json`, `packages/qos-claude-code/plugin.json`, `registry-listings/cursor-plugin.json`, `registry-listings/mcp-marketplace.json`
- **项目输出质量是否满足用户具体任务？**（unverified）：安装前预览只能展示流程和边界，不能替代真实评测。
- **安装命令是否需要网络、权限或全局写入？**（unverified）：这影响企业环境和个人环境的安装风险。 证据：`README.md`

### 继续会触碰什么

- **命令执行**：包管理器、网络下载、本地插件目录、项目配置或用户主目录。 原因：运行第一条命令就可能产生环境改动；必须先判断是否值得跑。 证据：`README.md`, `packages/qos-claude-code/README.md`
- **宿主 AI 配置**：Claude/Codex/Cursor/Gemini/OpenCode 等宿主的 plugin、Skill 或规则加载配置。 原因：宿主配置会改变 AI 后续工作方式，可能和用户已有规则冲突。 证据：`.claude/skills/gitnexus/gitnexus-cli/SKILL.md`, `.claude/skills/gitnexus/gitnexus-debugging/SKILL.md`, `.claude/skills/gitnexus/gitnexus-exploring/SKILL.md`, `.claude/skills/gitnexus/gitnexus-guide/SKILL.md` 等
- **本地环境或项目文件**：安装结果、插件缓存、项目配置或本地依赖目录。 原因：安装前无法证明写入范围和回滚方式，需要隔离验证。 证据：`README.md`, `claude-code-plugin/plugin.json`, `packages/qos-claude-code/README.md`, `packages/qos-claude-code/plugin.json` 等
- **环境变量 / API Key**：项目入口文档明确出现 API key、token、secret 或账号凭证配置。 原因：如果真实安装需要凭证，应先使用测试凭证并经过权限/合规判断。 证据：`README.md`, `adapters/claude_managed_types.py`, `deploy/README.md`, `deploy/azure-container-apps.md` 等
- **宿主 AI 上下文**：AI Context Pack、Prompt Preview、Skill 路由、风险规则和项目事实。 原因：导入上下文会影响宿主 AI 后续判断，必须避免把未验证项包装成事实。

### 最小安全下一步

- **先跑 Prompt Preview**：用安装前交互式试用判断工作方式是否匹配，不需要授权或改环境。（适用：任何项目都适用，尤其是输出质量未知时。）
- **只在隔离目录或测试账号试装**：避免安装命令污染主力宿主 AI、真实项目或用户主目录。（适用：存在命令执行、插件配置或本地写入线索时。）
- **先备份宿主 AI 配置**：Skill、plugin、规则文件可能改变 Claude/Cursor/Codex 的默认行为。（适用：存在插件 manifest、Skill 或宿主规则入口时。）
- **不要使用真实生产凭证**：环境变量/API key 一旦进入宿主或工具链，可能产生账号和合规风险。（适用：出现 API、TOKEN、KEY、SECRET 等环境线索时。）
- **安装后只验证一个最小任务**：先验证加载、兼容、输出质量和回滚，再决定是否深用。（适用：准备从试用进入真实工作流时。）

### 退出方式

- **保留安装前状态**：记录原始宿主配置和项目状态，后续才能判断是否可恢复。
- **准备移除宿主 plugin / Skill / 规则入口**：如果试装后行为异常，可以把宿主 AI 恢复到试装前状态。
- **记录安装命令和写入路径**：没有明确卸载说明时，至少要知道哪些目录或配置需要手动清理。
- **准备撤销测试 API key 或 token**：测试凭证泄露或误用时，可以快速止损。
- **如果没有回滚路径，不进入主力环境**：不可回滚是继续前阻断项，不应靠信任或运气继续。

## 哪些只能预览

- 解释项目适合谁和能做什么
- 基于项目文档演示典型对话流程
- 帮助用户判断是否值得安装或继续研究

## 哪些必须安装后验证

- 真实安装 Skill、插件或 CLI
- 执行脚本、修改本地文件或访问外部服务
- 验证真实输出质量、性能和兼容性

## 边界与风险判断卡

- **把安装前预览误认为真实运行**：用户可能高估项目已经完成的配置、权限和兼容性验证。 处理方式：明确区分 prompt_preview_can_do 与 runtime_required。 Claim：`clm_0011` inferred 0.45
- **宿主 AI 插件或 Skill 规则冲突**：新规则可能改变用户现有宿主 AI 的工作方式。 处理方式：安装前先检查插件 manifest 和 Skill 文件，必要时隔离测试。 证据：`claude-code-plugin/plugin.json`, `packages/qos-claude-code/plugin.json`, `registry-listings/cursor-plugin.json`, `registry-listings/mcp-marketplace.json` Claim：`clm_0012` supported 0.86
- **命令执行会修改本地环境**：安装命令可能写入用户主目录、宿主插件目录或项目配置。 处理方式：先在隔离环境或测试账号中运行。 证据：`README.md`, `packages/qos-claude-code/README.md` Claim：`clm_0013` supported 0.86
- **待确认**：真实安装后是否与用户当前宿主 AI 版本兼容？。原因：兼容性只能通过实际宿主环境验证。
- **待确认**：项目输出质量是否满足用户具体任务？。原因：安装前预览只能展示流程和边界，不能替代真实评测。
- **待确认**：安装命令是否需要网络、权限或全局写入？。原因：这影响企业环境和个人环境的安装风险。

## 开工前工作上下文

### 加载顺序

- 先读取 how_to_use.host_ai_instruction，建立安装前判断资产的边界。
- 读取 claim_graph_summary，确认事实来自 Claim/Evidence Graph，而不是 Human Wiki 叙事。
- 再读取 intended_users、capabilities 和 quick_start_candidates，判断用户是否匹配。
- 需要执行具体任务时，优先查 role_skill_index，再查 evidence_index。
- 遇到真实安装、文件修改、网络访问、性能或兼容性问题时，转入 risk_card 和 boundaries.runtime_required。

### 任务路由

- **AI Skill / Agent 指令资产库**：先基于 role_skill_index / evidence_index 帮用户挑选可用角色、Skill 或工作流。 边界：可做安装前 Prompt 体验。 证据：`.claude/skills/gitnexus/gitnexus-cli/SKILL.md`, `.claude/skills/gitnexus/gitnexus-debugging/SKILL.md`, `.claude/skills/gitnexus/gitnexus-exploring/SKILL.md`, `.claude/skills/gitnexus/gitnexus-guide/SKILL.md` 等 Claim：`clm_0001` supported 0.86
- **多宿主安装与分发**：先说明这是安装后验证能力，再给出安装前检查清单。 边界：必须真实安装或运行后验证。 证据：`claude-code-plugin/plugin.json`, `packages/qos-claude-code/plugin.json`, `registry-listings/cursor-plugin.json`, `registry-listings/mcp-marketplace.json` Claim：`clm_0002` supported 0.86
- **命令行启动或安装流程**：先说明这是安装后验证能力，再给出安装前检查清单。 边界：必须真实安装或运行后验证。 证据：`README.md`, `packages/qos-claude-code/README.md` Claim：`clm_0003` supported 0.86

### 上下文规模

- 文件总数：459
- 重要文件覆盖：40/459
- 证据索引条目：80
- 角色 / Skill 条目：6

### 证据不足时的处理

- **missing_evidence**：说明证据不足，要求用户提供目标文件、README 段落或安装后验证记录；不要补全事实。
- **out_of_scope_request**：说明该任务超出当前 AI Context Pack 证据范围，并建议用户先查看 Human Manual 或真实安装后验证。
- **runtime_request**：给出安装前检查清单和命令来源，但不要替用户执行命令或声称已执行。
- **source_conflict**：同时展示冲突来源，标记为待核实，不要强行选择一个版本。

## Prompt Recipes

### 适配判断

- 目标：判断这个项目是否适合用户当前任务。
- 预期输出：适配结论、关键理由、证据引用、安装前可预览内容、必须安装后验证内容、下一步建议。

```text
请基于 qualixar-os 的 AI Context Pack，先问我 3 个必要问题，然后判断它是否适合我的任务。回答必须包含：适合谁、能做什么、不能做什么、是否值得安装、证据来自哪里。所有项目事实必须引用 evidence_refs、source_paths 或 claim_id。
```

### 安装前体验

- 目标：让用户在安装前感受核心工作流，同时避免把预览包装成真实能力或营销承诺。
- 预期输出：一段带边界标签的体验剧本、安装后验证清单和谨慎建议；不含真实运行承诺或强营销表述。

```text
请把 qualixar-os 当作安装前体验资产，而不是已安装工具或真实运行环境。

请严格输出四段：
1. 先问我 3 个必要问题。
2. 给出一段“体验剧本”：用 [安装前可预览]、[必须安装后验证]、[证据不足] 三种标签展示它可能如何引导工作流。
3. 给出安装后验证清单：列出哪些能力只有真实安装、真实宿主加载、真实项目运行后才能确认。
4. 给出谨慎建议：只能说“值得继续研究/试装”“先补充信息后再判断”或“不建议继续”，不得替项目背书。

硬性边界：
- 不要声称已经安装、运行、执行测试、修改文件或产生真实结果。
- 不要写“自动适配”“确保通过”“完美适配”“强烈建议安装”等承诺性表达。
- 如果描述安装后的工作方式，必须使用“如果安装成功且宿主正确加载 Skill，它可能会……”这种条件句。
- 体验剧本只能写成“示例台词/假设流程”：使用“可能会询问/可能会建议/可能会展示”，不要写“已写入、已生成、已通过、正在运行、正在生成”。
- Prompt Preview 不负责给安装命令；如用户准备试装，只能提示先阅读 Quick Start 和 Risk Card，并在隔离环境验证。
- 所有项目事实必须来自 supported claim、evidence_refs 或 source_paths；inferred/unverified 只能作风险或待确认项。

```

### 角色 / Skill 选择

- 目标：从项目里的角色或 Skill 中挑选最匹配的资产。
- 预期输出：候选角色或 Skill 列表，每项包含适用场景、证据路径、风险边界和是否需要安装后验证。

```text
请读取 role_skill_index，根据我的目标任务推荐 3-5 个最相关的角色或 Skill。每个推荐都要说明适用场景、可能输出、风险边界和 evidence_refs。
```

### 风险预检

- 目标：安装或引入前识别环境、权限、规则冲突和质量风险。
- 预期输出：环境、权限、依赖、许可、宿主冲突、质量风险和未知项的检查清单。

```text
请基于 risk_card、boundaries 和 quick_start_candidates，给我一份安装前风险预检清单。不要替我执行命令，只说明我应该检查什么、为什么检查、失败会有什么影响。
```

### 宿主 AI 开工指令

- 目标：把项目上下文转成一次对话开始前的宿主 AI 指令。
- 预期输出：一段边界明确、证据引用明确、适合复制给宿主 AI 的开工前指令。

```text
请基于 qualixar-os 的 AI Context Pack，生成一段我可以粘贴给宿主 AI 的开工前指令。这段指令必须遵守 not_runtime=true，不能声称项目已经安装、运行或产生真实结果。
```

## 角色 / Skill 索引

- 共索引 6 个角色 / Skill / 项目文档条目。

- **gitnexus-cli**（skill）：Use when the user needs to run GitNexus CLI commands like analyze/index a repo, check status, clean the index, generate a wiki, or list indexed repos. Examples: \"Index this repo\", \"Reanalyze the codebase\", \"Generate a wiki\ 激活提示：当用户任务与“gitnexus-cli”描述的流程高度相关时，先用它做安装前体验，再决定是否安装。 证据：`.claude/skills/gitnexus/gitnexus-cli/SKILL.md`
- **gitnexus-debugging**（skill）：Use when the user is debugging a bug, tracing an error, or asking why something fails. Examples: \"Why is X failing?\", \"Where does this error come from?\", \"Trace this bug\ 激活提示：当用户任务与“gitnexus-debugging”描述的流程高度相关时，先用它做安装前体验，再决定是否安装。 证据：`.claude/skills/gitnexus/gitnexus-debugging/SKILL.md`
- **gitnexus-exploring**（skill）：Use when the user asks how code works, wants to understand architecture, trace execution flows, or explore unfamiliar parts of the codebase. Examples: \"How does X work?\", \"What calls this function?\", \"Show me the auth flow\ 激活提示：当用户任务与“gitnexus-exploring”描述的流程高度相关时，先用它做安装前体验，再决定是否安装。 证据：`.claude/skills/gitnexus/gitnexus-exploring/SKILL.md`
- **gitnexus-guide**（skill）：Use when the user asks about GitNexus itself — available tools, how to query the knowledge graph, MCP resources, graph schema, or workflow reference. Examples: \"What GitNexus tools are available?\", \"How do I use GitNexus?\ 激活提示：当用户任务与“gitnexus-guide”描述的流程高度相关时，先用它做安装前体验，再决定是否安装。 证据：`.claude/skills/gitnexus/gitnexus-guide/SKILL.md`
- **gitnexus-impact-analysis**（skill）：Use when the user wants to know what will break if they change something, or needs safety analysis before editing code. Examples: \"Is it safe to change X?\", \"What depends on this?\", \"What will break?\ 激活提示：当用户任务与“gitnexus-impact-analysis”描述的流程高度相关时，先用它做安装前体验，再决定是否安装。 证据：`.claude/skills/gitnexus/gitnexus-impact-analysis/SKILL.md`
- **gitnexus-refactoring**（skill）：Use when the user wants to rename, extract, split, move, or restructure code safely. Examples: \"Rename this function\", \"Extract this into a module\", \"Refactor this class\", \"Move this to a separate file\ 激活提示：当用户任务与“gitnexus-refactoring”描述的流程高度相关时，先用它做安装前体验，再决定是否安装。 证据：`.claude/skills/gitnexus/gitnexus-refactoring/SKILL.md`

## 证据索引

- 共索引 80 条证据。

- **Qualixar OS**（documentation）：! License: FSL-1.1 https://img.shields.io/badge/License-FSL--1.1-blue.svg https://fsl.software ! Tests: 2,936 passing https://img.shields.io/badge/Tests-2%2C936 passing-brightgreen https://github.com/qualixar/qualixar-os ! TypeScript https://img.shields.io/badge/TypeScript-5.7-3178C6?logo=typescript&logoColor=white https://www.typescriptlang.org/ ! Node.js 22+ https://img.shields.io/badge/Node.js-22%2B-339933?logo=node.js&logoColor=white https://nodejs.org/ ! arXiv https://img.shields.io/badge/arXiv-2604.06392-b31b1b https://arxiv.org/abs/2604.06392 ! DOI https://img.shields.io/badge/DOI-10.5281%2Fzenodo.19454219-blue https://doi.org/10.5281/zenodo.19454219 证据：`README.md`
- **Qualixar OS Python Adapters**（documentation）：Python client and framework adapters for the Qualixar OS agent operating system. 证据：`adapters/README.md`
- **Qualixar OS — Claude Code Plugin**（documentation）：The Universal OS for AI Agents, integrated into Claude Code. 证据：`claude-code-plugin/README.md`
- **Qualixar OS Deployment Guide**（documentation）：Platform Complexity Cost Best For ---------- ----------- ------ ---------- Docker Compose ../docker-compose.yml Low Free local Development, self-hosted Fly.io ./fly-io.md Low Free tier available Quick public deploy Railway ./railway.md Lowest Free tier available 1-click deploy Azure Container Apps ./azure-container-apps.md Medium Pay-as-you-go Enterprise, scaling Kubernetes ./kubernetes.md High Varies Large-scale production 证据：`deploy/README.md`
- **QOS Claude Code Plugin**（documentation）：Integrates Qualixar OS with Claude Code CLI for native agent orchestration. 证据：`packages/qos-claude-code/README.md`
- **Package**（package_manifest）：{ "name": "@qualixar-os/dashboard", "private": true, "version": "2.0.0", "type": "module", "scripts": { "dev": "vite", "build": "vite build", "preview": "vite preview" }, "dependencies": { "d3": "^7.9.0", "d3-force": "^3.0.0", "framer-motion": "^12.0.0", "lucide-react": "^1.7.0", "react": "^19.0.0", "react-dom": "^19.0.0", "recharts": "^2.15.0", "zustand": "^5.0.0" }, "devDependencies": { "@types/d3": "^7.4.0", "@types/react": "^19.0.0", "@types/react-dom": "^19.0.0", "@vitejs/plugin-react": "^4.3.0", "tailwindcss": "^4.0.0", "vite": "^6.2.0" } } 证据：`dashboard/package.json`
- **Package**（package_manifest）：{ "name": "qualixar-os", "version": "2.2.3", "description": "Qualixar OS: The Universal OS for AI Agents. One platform, every model, every framework, every transport.", "type": "module", "main": "./dist/index.js", "types": "./dist/index.d.ts", "exports": { ".": { "import": "./dist/index.js", "types": "./dist/index.d.ts" } }, "files": "dist", "bin", "README.md", "LICENSE", "scripts" , "bin": { "qos": "./bin/qos.js", "qualixar-os": "./bin/qos.js" }, "scripts": { "build": "tsc && npm run build:dashboard", "build:dashboard": "cd dashboard && npm run build", "dev": "tsx src/channels/cli.ts", "test": "vitest run", "test:watch": "vitest", "test:coverage": "vitest run --coverage", "test:e2e": "vite… 证据：`package.json`
- **Contributing to Qualixar OS**（documentation）：Thank you for considering contributing to Qualixar OS! This guide will help you get started. 证据：`CONTRIBUTING.md`
- **Package**（package_manifest）：{ "name": "create-qualixar-os", "version": "0.1.0", "description": "Create a new Qualixar OS project — The Universal Agent Orchestration Layer", "type": "module", "bin": { "create-qualixar-os": "./dist/index.js" }, "files": "dist" , "scripts": { "build": "tsc", "dev": "tsx src/index.ts", "test": "vitest run", "test:watch": "vitest" }, "dependencies": { "@clack/prompts": "^0.9.0", "chalk": "^5.4.0", "yaml": "^2.7.0" }, "devDependencies": { "typescript": "^5.7.0", "tsx": "^4.19.0", "vitest": "^3.0.0", "@types/node": "^22.0.0" }, "engines": { "node": " =22.0.0" }, "keywords": "qos", "qualixar", "agent", "orchestration", "mcp", "ai" , "license": "MIT" } 证据：`packages/create-qos/package.json`
- **Package**（package_manifest）：{ "name": "qos-claude-code", "version": "2.1.1", "description": "Claude Code plugin for Qualixar OS — submit tasks, browse workspaces, manage agents", "keywords": "qualixar-os", "claude-code", "ai-agents", "orchestration", "qos-compatible", "openclaw", "claw-compatible" , "license": "FSL-1.1-ALv2", "author": "qualixar", "repository": { "type": "git", "url": "https://github.com/qualixar/qualixar-os" }, "homepage": "https://qualixar.com", "files": "plugin.json", "commands/", "skills/", "agents/", "README.md" } 证据：`packages/qos-claude-code/package.json`
- **GitNexus CLI Commands**（skill_instruction）：All commands work via npx — no global install required. 证据：`.claude/skills/gitnexus/gitnexus-cli/SKILL.md`
- **Debugging with GitNexus**（skill_instruction）：- "Why is this function failing?" - "Trace where this error comes from" - "Who calls this method?" - "This endpoint returns 500" - Investigating bugs, errors, or unexpected behavior 证据：`.claude/skills/gitnexus/gitnexus-debugging/SKILL.md`
- **Exploring Codebases with GitNexus**（skill_instruction）：- "How does authentication work?" - "What's the project structure?" - "Show me the main components" - "Where is the database logic?" - Understanding code you haven't seen before 证据：`.claude/skills/gitnexus/gitnexus-exploring/SKILL.md`
- **GitNexus Guide**（skill_instruction）：Quick reference for all GitNexus MCP tools, resources, and the knowledge graph schema. 证据：`.claude/skills/gitnexus/gitnexus-guide/SKILL.md`
- **Impact Analysis with GitNexus**（skill_instruction）：- "Is it safe to change this function?" - "What will break if I modify X?" - "Show me the blast radius" - "Who uses this code?" - Before making non-trivial code changes - Before committing — to understand what your changes affect 证据：`.claude/skills/gitnexus/gitnexus-impact-analysis/SKILL.md`
- **Refactoring with GitNexus**（skill_instruction）：- "Rename this function safely" - "Extract this into a module" - "Split this service" - "Move this to a new file" - Any task involving renaming, extracting, splitting, or restructuring code 证据：`.claude/skills/gitnexus/gitnexus-refactoring/SKILL.md`
- **Plugin**（structured_config）：{ "name": "qualixar-os", "displayName": "Qualixar OS", "version": "2.2.0", "description": "The Universal OS for AI Agents. Design multi-agent teams with Forge, browse skills, monitor costs, and integrate with Claude Code Agent Teams — all from Claude Code.", "author": "qualixar", "license": "FSL-1.1-ALv2", "homepage": "https://qualixar.com", "repository": "https://github.com/qualixar/qualixar-os", "provides": { "skills": "skills/forge-design.md", "skills/code-review.md", "skills/research.md", "skills/marketplace.md", "skills/agent-teams.md", "skills/task-orchestrator.md" , "hooks": { "PreToolUse": "hooks/cost-tracker.sh" , "PostToolUse": "hooks/cost-tracker.sh", "hooks/audit-log.sh" , "Team… 证据：`claude-code-plugin/plugin.json`
- **Plugin**（structured_config）：{ "name": "qos-claude-code", "displayName": "QOS Claude Code", "version": "2.1.1", "description": "Claude Code plugin for Qualixar OS — submit tasks, design agent teams with Forge, browse workspaces, and manage the skill marketplace.", "author": "qualixar", "license": "FSL-1.1-ALv2", "homepage": "https://qualixar.com", "repository": "https://github.com/qualixar/qualixar-os", "provides": { "skills": "skills/task-orchestrator.md" , "commands": "commands/qos-task.md", "commands/qos-forge.md", "commands/qos-status.md", "commands/qos-workspace.md", "commands/qos-marketplace.md" , "agents": { "name": "qos-orchestrator", "description": "Manages Qualixar OS tasks — submit, monitor, and inspect agen… 证据：`packages/qos-claude-code/plugin.json`
- **Functional Source License, Version 1.1, ALv2 Future License**（source_file）：Functional Source License, Version 1.1, ALv2 Future License 证据：`LICENSE`
- **Attribution**（documentation）：Qualixar OS — The Universal OS for AI Agents 证据：`ATTRIBUTION.md`
- **Changelog**（documentation）：All notable changes to Qualixar OS will be documented in this file. 证据：`CHANGELOG.md`
- **Contributor Covenant Code of Conduct**（documentation）：Contributor Covenant Code of Conduct 证据：`CODE_OF_CONDUCT.md`
- **Commercial License**（documentation）：This software is available under a dual license model. 证据：`COMMERCIAL-LICENSE.md`
- **Governance**（documentation）：Qualixar OS uses a BDFL Benevolent Dictator for Life governance model during its early growth phase. 证据：`GOVERNANCE.md`
- **Roadmap**（documentation）：This roadmap reflects our current plans. Priorities may shift based on community feedback and usage patterns. 证据：`ROADMAP.md`
- **Security Policy**（documentation）：If you discover a security vulnerability in Qualixar OS, please report it responsibly. 证据：`SECURITY.md`
- **Deploy Qualixar OS to Azure Container Apps**（documentation）：Deploy Qualixar OS to Azure Container Apps 证据：`deploy/azure-container-apps.md`
- **Deploy Qualixar OS to Fly.io**（documentation）：- Fly CLI installed: curl -L https://fly.io/install.sh sh - Logged in: fly auth login 证据：`deploy/fly-io.md`
- **Deploy Qualixar OS to Kubernetes**（documentation）：Apply the following manifests to your cluster. Adjust namespace, image, and resource limits as needed. 证据：`deploy/kubernetes.md`
- **Deploy Qualixar OS to Railway**（documentation）：- Railway CLI installed: npm install -g @railway/cli - Logged in: railway login 证据：`deploy/railway.md`
- **Qualixar OS Code Reviewer**（documentation）：You are a multi-perspective code reviewer powered by Qualixar OS's debate topology. 证据：`claude-code-plugin/agents/qos-code-reviewer.md`
- **Qualixar OS Cost Optimizer**（documentation）：You are a budget-aware task routing specialist powered by Qualixar OS's cost engine. 证据：`claude-code-plugin/agents/qos-cost-optimizer.md`
- **Qualixar OS Forge Architect**（documentation）：You are a team design specialist powered by Qualixar OS Forge. 证据：`claude-code-plugin/agents/qos-forge-architect.md`
- **Qualixar OS Quality Judge**（documentation）：You are a quality gating specialist powered by Qualixar OS's judge pipeline. 证据：`claude-code-plugin/agents/qos-quality-judge.md`
- **Qualixar OS Research Agent**（documentation）：You are a deep research specialist powered by Qualixar OS's 10+ provider routing. 证据：`claude-code-plugin/agents/qos-research-agent.md`
- **Qualixar OS Topology Designer**（documentation）：You are a topology selection expert for multi-agent systems. 证据：`claude-code-plugin/agents/qos-topology-designer.md`
- **/qos-forge**（documentation）：Design a multi-agent team. Forge analyzes your task and creates a specialized team. 证据：`claude-code-plugin/commands/qos-forge.md`
- **/qos-marketplace**（documentation）：Browse the skill marketplace from Claude Code. 证据：`claude-code-plugin/commands/qos-marketplace.md`
- **/qos-status**（documentation）：Quick status check of your Qualixar OS instance. 证据：`claude-code-plugin/commands/qos-status.md`
- **/qos-task**（documentation）：Submit a task to the running Qualixar OS server. 证据：`claude-code-plugin/commands/qos-task.md`
- **/qos-workspace**（documentation）：Browse the workspace files of a completed task. 证据：`claude-code-plugin/commands/qos-workspace.md`
- **Qualixar OS Agent Teams Designer**（documentation）：You are guiding the user to design and optimize a multi-agent team using Qualixar OS within Claude Code Agent Teams. 证据：`claude-code-plugin/skills/agent-teams.md`
- **Multi-Agent Code Review**（documentation）：Use Qualixar OS to review code with a debate topology — two agent perspectives, one judge verdict. 证据：`claude-code-plugin/skills/code-review.md`
- **Forge Agent Team Designer**（documentation）：You are using Qualixar OS Forge to design a multi-agent team. 证据：`claude-code-plugin/skills/forge-design.md`
- **Qualixar OS Marketplace**（documentation）：Browse and install agent skills, tools, and plugins from the global registry. 证据：`claude-code-plugin/skills/marketplace.md`
- **Web Research Agent**（documentation）：Use Qualixar OS web-researcher agent to perform deep research with cited sources. 证据：`claude-code-plugin/skills/research.md`
- **QOS Task Orchestrator**（documentation）：You are managing Qualixar OS tasks from within Claude Code. 证据：`claude-code-plugin/skills/task-orchestrator.md`
- **Server Connection**（documentation）：You are the QOS Orchestrator agent. You help users interact with a running Qualixar OS instance. 证据：`packages/qos-claude-code/agents/qos-orchestrator.md`
- **/qos-forge**（documentation）：Design a multi-agent team. Forge analyzes your task and creates a specialized team. 证据：`packages/qos-claude-code/commands/qos-forge.md`
- **/qos-marketplace**（documentation）：Browse the skill marketplace from Claude Code. 证据：`packages/qos-claude-code/commands/qos-marketplace.md`
- **/qos-status**（documentation）：Quick status check of your Qualixar OS instance. 证据：`packages/qos-claude-code/commands/qos-status.md`
- **/qos-task**（documentation）：Submit a task to the running Qualixar OS server. 证据：`packages/qos-claude-code/commands/qos-task.md`
- **/qos-workspace**（documentation）：Browse the workspace files of a completed task. 证据：`packages/qos-claude-code/commands/qos-workspace.md`
- **QOS Task Orchestrator**（documentation）：You are managing Qualixar OS tasks from within Claude Code. 证据：`packages/qos-claude-code/skills/task-orchestrator.md`
- **Tsconfig**（structured_config）：{ "compilerOptions": { "target": "ES2022", "module": "ESNext", "moduleResolution": "bundler", "jsx": "react-jsx", "strict": true, "esModuleInterop": true, "skipLibCheck": true, "forceConsistentCasingInFileNames": true, "lib": "ES2022", "DOM", "DOM.Iterable" , "outDir": "../dist/dashboard", "declaration": false, "sourceMap": true, "isolatedModules": true, "resolveJsonModule": true }, "include": "../src/dashboard/app/ / " , "exclude": "node modules" } 证据：`dashboard/tsconfig.json`
- **Cursor Plugin**（structured_config）：{ "name": "qualixar-os", "displayName": "Qualixar OS", "description": "The Universal OS for AI Agents. Works with Cursor's Composer for multi-agent orchestration, Forge team design, and skill marketplace.", "version": "2.1.1", "publisher": "qualixar", "type": "mcp", "mcp": { "command": "npx", "args": "qualixar-os", "--mcp" }, "tools": "qos task — Run, pause, cancel, steer agent tasks", "qos agents — Forge team design, list agents, topologies", "qos system — Config, models, cost tracking", "qos context — Workspace management, file context", "qos quality — Judge verdicts, memory search", "qos workspace — Import agents from OpenClaw/NemoClaw/DeerFlow" , "keywords": "agent-os", "forge", "multi-… 证据：`registry-listings/cursor-plugin.json`
- **Glama**（structured_config）：{ "name": "qualixar-os", "displayName": "Qualixar OS — Universal Agent OS", "description": "The complete operating system for AI agents. Design multi-agent teams with Forge AI, browse a skill marketplace, monitor costs, run 13 execution topologies. Compatible with OpenClaw, NemoClaw, DeerFlow, LangChain, CrewAI.", "author": "Qualixar", "version": "2.1.1", "license": "FSL-1.1-ALv2", "homepage": "https://qualixar.com", "sourceUrl": "https://github.com/qualixar/qualixar-os", "category": "developer-tools", "subcategories": "orchestration", "multi-agent", "ai-agents" , "transport": "stdio", "command": "npx qualixar-os --mcp", "authentication": "none", "tools": 6, "toolNames": "qos task", "qos ag… 证据：`registry-listings/glama.json`
- **Mcp Marketplace**（structured_config）：{ "name": "qualixar-os", "title": "Qualixar OS — The Universal OS for AI Agents", "description": "Complete agent operating system. Forge auto-designs multi-agent teams. 13 topologies. Skill marketplace. Cost routing. Judge pipeline. 24-tab dashboard. Compatible with OpenClaw, NemoClaw, DeerFlow, LangChain, CrewAI, AutoGen.", "author": "qualixar", "version": "2.1.1", "license": "FSL-1.1-ALv2", "install": { "claude-code": "claude mcp add qualixar-os -- npx qualixar-os --mcp", "cursor": "npx qualixar-os --mcp", "vscode": "npx qualixar-os --mcp", "windsurf": "npx qualixar-os --mcp", "cline": "npx qualixar-os --mcp" }, "pricing": "free", "category": "developer-tools", "tags": "agent-os", "multi-… 证据：`registry-listings/mcp-marketplace.json`
- **Smithery**（structured_config）：{ "$schema": "https://smithery.ai/schemas/server-listing-v1.json", "name": "qualixar-os", "displayName": "Qualixar OS", "description": "The Universal OS for AI Agents. Forge auto-designs multi-agent teams. 13 topologies. Skill marketplace. Cost routing. Judge pipeline. Claw-compatible.", "author": "qualixar", "version": "2.1.1", "license": "FSL-1.1-ALv2", "homepage": "https://qualixar.com", "repository": "https://github.com/qualixar/qualixar-os", "categories": "orchestration", "multi-agent", "developer-tools" , "tags": "agent-os", "forge", "multi-agent", "orchestration", "claw-compatible", "openclaw", "marketplace", "judge", "quality", "cost-routing", "mcp" , "installation": { "local": { "c… 证据：`registry-listings/smithery.json`
- **Server**（structured_config）：{ "$schema": "https://static.modelcontextprotocol.io/schemas/2025-12-11/server.schema.json", "name": "io.github.qualixar/qualixar-os", "description": "The Universal OS for AI Agents. Forge auto-designs multi-agent teams. 13 topologies. Skill marketplace. Cost routing. Claw-compatible.", "vendor": "Qualixar", "sourceUrl": "https://github.com/qualixar/qualixar-os", "homepage": "https://qualixar.com", "license": "FSL-1.1-ALv2", "packages": { "type": "npm", "package": "qualixar-os", "transport": "stdio" } } 证据：`server.json`
- 其余 20 条证据见 `AI_CONTEXT_PACK.json` 或 `EVIDENCE_INDEX.json`。

## 宿主 AI 必须遵守的规则

- **把本资产当作开工前上下文，而不是运行环境。**：AI Context Pack 只包含证据化项目理解，不包含目标项目的可执行状态。 证据：`README.md`, `adapters/README.md`, `claude-code-plugin/README.md`
- **回答用户时区分可预览内容与必须安装后才能验证的内容。**：安装前体验的消费者价值来自降低误装和误判，而不是伪装成真实运行。 证据：`README.md`, `adapters/README.md`, `claude-code-plugin/README.md`

## 用户开工前应该回答的问题

- 你准备在哪个宿主 AI 或本地环境中使用它？
- 你只是想先体验工作流，还是准备真实安装？
- 你最在意的是安装成本、输出质量、还是和现有规则的冲突？

## 验收标准

- 所有能力声明都能回指到 evidence_refs 中的文件路径。
- AI_CONTEXT_PACK.md 没有把预览包装成真实运行。
- 用户能在 3 分钟内看懂适合谁、能做什么、如何开始和风险边界。

---

## Doramagic Context Augmentation

下面内容用于强化 Repomix/AI Context Pack 主体。Human Manual 只提供阅读骨架；踩坑日志会被转成宿主 AI 必须遵守的工作约束。

## Human Manual 骨架

使用规则：这里只是项目阅读路线和显著性信号，不是事实权威。具体事实仍必须回到 repo evidence / Claim Graph。

宿主 AI 硬性规则：
- 不得把页标题、章节顺序、摘要或 importance 当作项目事实证据。
- 解释 Human Manual 骨架时，必须明确说它只是阅读路线/显著性信号。
- 能力、安装、兼容性、运行状态和风险判断必须引用 repo evidence、source path 或 Claim Graph。

- **项目概述与核心价值**：importance `high`
  - source_paths: README.md, docs/getting-started.md, ROADMAP.md, CHANGELOG.md
- **核心引擎与任务执行管道**：importance `high`
  - source_paths: src/engine/orchestrator.ts, src/engine/orchestrator-types.ts, src/engine/auto-orchestrator.ts, src/engine/degradation.ts, src/engine/budget-gate.ts
- **智能体系统、Forge AI 与 13 种拓扑**：importance `high`
  - source_paths: src/agents/forge.ts, src/agents/agent-registry.ts, src/agents/swarm-engine.ts, src/agents/scheduler.ts, src/agents/handoff-router.ts
- **SLM-Lite 四层记忆系统**：importance `high`
  - source_paths: src/memory/store.ts, src/memory/index.ts, src/memory/auto-invoker.ts, src/memory/embeddings.ts, src/memory/belief-graph.ts
- **判定管道、共识与质量保障**：importance `high`
  - source_paths: src/quality/judge-pipeline.ts, src/quality/consensus.ts, src/quality/judge-profile.ts, src/quality/behavioral-contracts.ts, src/quality/drift-detector.ts
- **协议、传输与框架适配器**：importance `high`
  - source_paths: src/channels/mcp-server.ts, src/compatibility/a2a-client.ts, src/compatibility/a2a-server.ts, src/compatibility/converter.ts, src/compatibility/openclaw-reader.ts
- **仪表盘、CLI 与市场**：importance `medium`
  - source_paths: src/dashboard/app/App.tsx, src/dashboard/app/main.tsx, src/dashboard/server.ts, src/dashboard/app/tabs/OverviewTab.tsx, src/dashboard/app/tabs/ForgeTab.tsx
- **部署、配置、安全与模型路由**：importance `high`
  - source_paths: src/router/model-router.ts, src/router/model-catalog.ts, src/router/model-discovery.ts, src/router/model-call.ts, src/router/local-provider.ts

## Repo Inspection Evidence / 源码检查证据

- repo_clone_verified: true
- repo_inspection_verified: true
- repo_commit: `eee934b5942bfff2fa5543a39e64a78905640a0c`
- inspected_files: `Dockerfile`, `README.md`, `package.json`, `docker-compose.yml`, `docs/getting-started.md`, `docs/memory/overview.md`, `docs/memory/superlocalmemory.md`, `docs/memory/slm-integration.md`, `docs/providers/anthropic.md`, `docs/providers/overview.md`, `docs/providers/openai.md`, `docs/providers/ollama.md`, `docs/providers/ollama-cloud.md`, `docs/providers/lmstudio.md`, `docs/providers/custom.md`, `docs/providers/openrouter.md`, `docs/providers/azure.md`, `docs/cli/overview.md`, `docs/cli/cli-vs-mcp.md`, `docs/dashboard/gate.md`

宿主 AI 硬性规则：
- 没有 repo_clone_verified=true 时，不得声称已经读过源码。
- 没有 repo_inspection_verified=true 时，不得把 README/docs/package 文件判断写成事实。
- 没有 quick_start_verified=true 时，不得声称 Quick Start 已跑通。

## Doramagic Pitfall Constraints / 踩坑约束

这些规则来自 Doramagic 发现、验证或编译过程中的项目专属坑点。宿主 AI 必须把它们当作工作约束，而不是普通说明文字。

### Constraint 1: 能力判断依赖假设

- Trigger: README/documentation is current enough for a first validation pass.
- Host AI rule: 将假设转成下游验证清单。
- Why it matters: 假设不成立时，用户拿不到承诺的能力。
- Evidence: capability.assumptions | github_repo:1201841278 | https://github.com/qualixar/qualixar-os | README/documentation is current enough for a first validation pass.
- Hard boundary: 不要把这个坑点包装成已解决、已验证或可忽略，除非后续验证证据明确证明它已经关闭。

### Constraint 2: 维护活跃度未知

- Trigger: 未记录 last_activity_observed。
- Host AI rule: 补 GitHub 最近 commit、release、issue/PR 响应信号。
- Why it matters: 新项目、停更项目和活跃项目会被混在一起，推荐信任度下降。
- Evidence: evidence.maintainer_signals | github_repo:1201841278 | https://github.com/qualixar/qualixar-os | last_activity_observed missing
- Hard boundary: 不要把这个坑点包装成已解决、已验证或可忽略，除非后续验证证据明确证明它已经关闭。

- Trigger: no_demo
- Evidence: downstream_validation.risk_items | github_repo:1201841278 | https://github.com/qualixar/qualixar-os | no_demo; severity=medium
- Hard boundary: 不要把这个坑点包装成已解决、已验证或可忽略，除非后续验证证据明确证明它已经关闭。

### Constraint 4: 存在评分风险

- Trigger: no_demo
- Why it matters: 风险会影响是否适合普通用户安装。
- Evidence: risks.scoring_risks | github_repo:1201841278 | https://github.com/qualixar/qualixar-os | no_demo; severity=medium
- Hard boundary: 不要把这个坑点包装成已解决、已验证或可忽略，除非后续验证证据明确证明它已经关闭。

### Constraint 5: issue/PR 响应质量未知

- Trigger: issue_or_pr_quality=unknown。
- Host AI rule: 抽样最近 issue/PR，判断是否长期无人处理。
- Why it matters: 用户无法判断遇到问题后是否有人维护。
- Evidence: evidence.maintainer_signals | github_repo:1201841278 | https://github.com/qualixar/qualixar-os | issue_or_pr_quality=unknown
- Hard boundary: 不要把这个坑点包装成已解决、已验证或可忽略，除非后续验证证据明确证明它已经关闭。

### Constraint 6: 发布节奏不明确

- Trigger: release_recency=unknown。
- Host AI rule: 确认最近 release/tag 和 README 安装命令是否一致。
- Why it matters: 安装命令和文档可能落后于代码，用户踩坑概率升高。
- Evidence: evidence.maintainer_signals | github_repo:1201841278 | https://github.com/qualixar/qualixar-os | release_recency=unknown
- Hard boundary: 不要把这个坑点包装成已解决、已验证或可忽略，除非后续验证证据明确证明它已经关闭。