docs(hosts): sync public host entrypoints

Align README and Docusaurus Quickstart surfaces with docs/specs/2026-07-30-supported-host-entrypoints.md. Validated with focused entrypoint tests, doc-link graph, and git diff --check.

Co-authored-by: QoderAI <qoder_ai@qoder.com>

Author: phodal

README.md

@@ -31,15 +31,25 @@
   <a href="docs/community.md">Contribute</a>
 </p>
 
-## See it in action
+## Quick start
+
+Review your coding workflow with: [Claude Code](#claude-code), [Codex Desktop](#codex-desktop), [Codex CLI](#codex-cli), [Qoder Desktop/CLI](#qoder), [Cursor](#cursor), [Qwen Code](#qwen-code), or [GitHub Copilot CLI](#github-copilot).
 
-Ask `/better-harness` to review the current task and its surrounding project
-Harness, then generate a durable report:
+Once installed, ask Better Harness to generate the host's durable report:
 
 ```text
 /better-harness review this project's AI coding workflow and generate a report
 ```
 
+Better Harness scopes behavior claims to relevant Task Episodes and the
+surrounding project mechanisms. Qoder produces a Canvas report; Claude Code,
+Codex, Cursor, Qwen Code, and GitHub Copilot produce self-contained HTML with
+paired Markdown. Missing or partial evidence remains explicit. See the
+[Host Adapter Matrix](docs/adapters/README.md) for current coverage and output
+differences.
+
+## See it in action
+
 The report keeps missing evidence explicit and turns supported gaps into
 prioritized findings with an impact, expected output, scoped repair, and
 acceptance checks.
@@ -141,32 +151,6 @@ The architecture keeps the three evidence domains independent until unified
 analysis by the lead agent. Every result retains a visible evidence source,
 owner, and validation route.
 
-## Quick start
-
-Pick your coding agent — you can be looking at your first report in minutes:
-
-| Coding agent | Setup |
-| --- | --- |
-| **Claude Code** | Add the repository marketplace, install `better-harness@better-harness`, start a new session, then use the report prompt below. |
-| **Codex Desktop** | Add the repository under **Settings > Plugins > + Add > From Marketplace**, install Better Harness, start a new task, then invoke `@better-harness`. |
-| **Codex CLI** | Add the Git marketplace, run `codex plugin add better-harness@better-harness`, then invoke `$better-harness:better-harness`. |
-| **Qoder Desktop / CLI** | Nothing to install when Qoder Desktop is installed — Better Harness is built in and available to both. Open your repository and use the report prompt below. |
-| **GitHub Copilot CLI** | Add the repository marketplace, install `better-harness@better-harness`, start a new session, then use the report prompt below. |
-| **Cursor** | Load the plugin from source — see [Installation](#installation). |
-
-Once installed, ask Better Harness to generate the host's durable report:
-
-```text
-/better-harness review this project's AI coding workflow and generate a report
-```
-
-Better Harness scopes behavior claims to relevant Task Episodes and the
-surrounding project mechanisms. Qoder produces a Canvas report; Claude Code,
-Codex, Cursor, Qwen Code, and GitHub Copilot produce self-contained HTML with
-paired Markdown. Missing or partial evidence remains explicit. See the
-[Host Adapter Matrix](docs/adapters/README.md) for current coverage and output
-differences.
-
 ## Installation
 
 Installation differs by coding agent. Install Better Harness separately for
@@ -209,6 +193,8 @@ stays explicit rather than being inferred.
 
 ### Codex
 
+<a id="codex-desktop"></a>
+
 #### Codex Desktop
 
 1. Open **Settings > Plugins**.
@@ -228,6 +214,8 @@ Use `https://github.com/QoderAI/better-harness.git` with Git ref `main`.
 
 ![Codex Add plugin marketplace dialog with repository, Git ref, and optional sparse paths](assets/install/codex-add-marketplace.jpg)
 
+<a id="codex-cli"></a>
+
 #### Codex CLI
 
 Add the repository source:
@@ -336,6 +324,25 @@ transcripts under `~/.copilot/session-state/`. Copilot records no per-response
 token usage, and VS Code Copilot Chat has no supported durable transcript; both
 remain explicit evidence boundaries.
 
+### Qwen Code
+
+Install Better Harness as a Qwen Code extension:
+
+```bash
+qwen extensions install QoderAI/better-harness
+```
+
+Start a new Qwen Code session in the repository you want to review and run the
+report prompt:
+
+```text
+/better-harness review this project's AI coding workflow and generate a report
+```
+
+Qwen Code produces a self-contained `report.html` with paired `report.md` and
+`findings.json`. Session evidence coverage depends on Qwen Code's available
+transcript paths; missing or partial evidence remains explicit.
+
 ## Develop and package from source
 
 Development requires Node.js `>=22.20.0 <25.0.0` and npm

README.zh-CN.md

@@ -29,16 +29,27 @@
   <a href="docs/community.md">参与贡献</a>
 </p>
 
-<a id="see-it-in-action"></a>
+<a id="quick-start"></a>
 
-## 看看实际效果
+## 快速开始
+
+用以下 Coding Agent 审查你的工作流：[Claude Code](#claude-code)、[Codex Desktop](#codex-desktop)、[Codex CLI](#codex-cli)、[Qoder Desktop/CLI](#qoder)、[Cursor](#cursor)、[Qwen Code](#qwen-code)、[GitHub Copilot CLI](#github-copilot)。
 
-让 `/better-harness` 审查当前任务及其所在项目的 Harness，并生成一份可留存的报告：
+安装完成后，让 Better Harness 生成当前宿主支持的持久化报告：
 
 ```text
 /better-harness 审查此项目的 AI 编码工作流并生成报告
 ```
 
+Better Harness 会将行为断言限定在相关的任务过程片段（Task Episode）及其周边项目机制内。
+Qoder 生成 Canvas 报告；Claude Code、Codex、Cursor、Qwen Code 和 GitHub Copilot 生成自包含的 HTML 报告及配套 Markdown。
+缺失或不完整的证据会被明确标注。有关当前覆盖范围和输出差异，请参阅
+[宿主适配器矩阵](docs/adapters/README.md)。
+
+<a id="see-it-in-action"></a>
+
+## 看看实际效果
+
 报告会明确标注证据缺口，并将有证据支撑的问题整理成按优先级排列的发现；
 每项发现都包含影响、预期输出、范围明确的修复方案与验收检查。
 
@@ -133,32 +144,6 @@ Better Harness 开放了三个相互关联的层次，而不只是一个斜杠
 该架构让三个证据域保持独立，直到主智能体进行统一分析。
 每个结果都会保留可见的证据来源、责任归属和验证路径。
 
-<a id="quick-start"></a>
-
-## 快速开始
-
-选择你的编码智能体——几分钟内即可看到第一份报告：
-
-| 编码智能体 | 设置方式 |
-| --- | --- |
-| **Claude Code** | 添加本仓库 Marketplace，安装 `better-harness@better-harness`，启动新会话，然后使用下方的报告提示词。 |
-| **Codex Desktop** | 在 **Settings > Plugins > + Add > From Marketplace** 中添加本仓库，安装 Better Harness，启动新任务，然后调用 `@better-harness`。 |
-| **Codex CLI** | 添加 Git Marketplace，运行 `codex plugin add better-harness@better-harness`，然后调用 `$better-harness:better-harness`。 |
-| **Qoder Desktop / CLI** | 安装 Qoder Desktop 后无需额外安装——Better Harness 已内置，并可在桌面端和 CLI 中使用。打开仓库并使用下方的报告提示词。 |
-| **GitHub Copilot CLI** | 添加本仓库 Marketplace，安装 `better-harness@better-harness`，启动新会话，然后使用下方的报告提示词。 |
-| **Cursor** | 从源码加载插件——参见[安装](#installation)。 |
-
-安装完成后，让 Better Harness 生成当前宿主支持的持久化报告：
-
-```text
-/better-harness 审查此项目的 AI 编码工作流并生成报告
-```
-
-Better Harness 会将行为断言限定在相关的任务过程片段（Task Episode）及其周边项目机制内。
-Qoder 生成 Canvas 报告；Claude Code、Codex、Cursor、Qwen Code 和 GitHub Copilot 生成自包含的 HTML 报告及配套 Markdown。
-缺失或不完整的证据会被明确标注。有关当前覆盖范围和输出差异，请参阅
-[宿主适配器矩阵](docs/adapters/README.md)。
-
 <a id="installation"></a>
 
 ## 安装
@@ -202,6 +187,8 @@ Claude Code 默认会在仓库的 `.claude/better-harness` 报告根目录下生
 
 ### Codex
 
+<a id="codex-desktop"></a>
+
 #### Codex Desktop
 
 1. 打开 **Settings > Plugins**。
@@ -218,6 +205,8 @@ Claude Code 默认会在仓库的 `.claude/better-harness` 报告根目录下生
 
 ![Codex 添加插件 Marketplace 的对话框，包含仓库、Git ref 和可选的 sparse paths](assets/install/codex-add-marketplace.jpg)
 
+<a id="codex-cli"></a>
+
 #### Codex CLI
 
 添加仓库源：
@@ -319,6 +308,23 @@ Copilot 会话证据来自 `~/.copilot/session-state/` 下与工作区匹配的
 Copilot 不记录逐次响应的 token 用量，VS Code Copilot Chat 也没有受支持的持久化会话记录；
 两者均作为明确的证据边界保留。
 
+### Qwen Code
+
+将 Better Harness 安装为 Qwen Code 扩展：
+
+```bash
+qwen extensions install QoderAI/better-harness
+```
+
+在要审查的仓库中启动新的 Qwen Code 会话，然后运行报告提示词：
+
+```text
+/better-harness 审查此项目的 AI 编码工作流并生成报告
+```
+
+Qwen Code 产出自包含的 `report.html`，并配套 `report.md` 与 `findings.json`。
+会话证据覆盖范围取决于 Qwen Code 可用的会话记录路径；缺失或不完整的证据保持显式标注。
+
 <a id="develop-and-package-from-source"></a>
 
 ## 从源码开发和打包

docs/adapters/contributing-new-coding-agent.md

@@ -36,6 +36,21 @@ A shell does not prove configured-asset or session support. A session parser doe
 not prove the Skill is natively discoverable. Do not register one slice merely
 to make another slice appear complete.
 
+### Capability levels
+
+Not every host lands with full end-to-end support. Be explicit about which of
+these levels the contribution reaches, and do not promote a host to the next
+level until the corresponding evidence exists:
+
+| Level | What it means | Minimum evidence | Public visibility |
+| --- | --- | --- | --- |
+| Partial adapter | Some slices work (often shell, configured assets, or sessions) while others are partial or unavailable. | Spec names claimed, partial, and unavailable slices; provider/session tests pass for the claimed subset. | Matrix and docs list the host with explicit limitations; do not add to the public Quickstart list. |
+| Verified install/discovery | The native install, link, or discovery command is smoke-tested and the Skill loads. | Native CLI smoke in an isolated home/config when possible; fallback is a pinned official doc reference plus a recorded evidence boundary. | README Installation section may list the host; still not Quickstart unless the report loop is validated. |
+| Public Quickstart-ready | Full report loop works: install/discovery, configured assets, session evidence (when claimed), output routing, and a validated report render. | End-to-end report generation on a real or representative repository; tests cover the public-entrypoint set. | Host appears in the README Quickstart list, Docusaurus home-page cards, and installation tabs. |
+
+A host can be merged at the partial or verified level and later promoted to
+public Quickstart-ready once the report loop evidence is complete.
+
 ## 2. Verify the Native Host Contract
 
 Do not derive a new host contract by renaming another adapter. Record the host
@@ -119,7 +134,7 @@ sessions, reports, and packaging have different owners. Search for the existing
 host set before editing:
 
 ```bash
-rg -n "qoder|codex|claude|cursor|qwen" scripts test references templates docs package.json
+rg -n "qoder|codex|claude|cursor|qwen|copilot" scripts test references templates docs package.json
 ```
 
 Use the results as an inventory, not a replacement template. Typical registration

docs/docs/concepts/glossary.md

@@ -66,7 +66,7 @@ progressive detail you load when a task needs it.
 | --- | --- |
 | Skill | A repeatable agent workflow defined by `SKILL.md` frontmatter plus a concise workflow. |
 | Host adapter | Per-host discovery and evidence-shape glue; keeps the engine host-neutral. |
-| Host shell | Thin host metadata (`.claude-plugin/`, `.qoder-plugin/`, `.cursor-plugin/`, `.codex-plugin/`) that exposes canonical behavior without owning product logic. |
+| Host shell | Thin host metadata (`.claude-plugin/`, `.qoder-plugin/`, `.cursor-plugin/`, `.codex-plugin/`, `.github/plugin/`, `qwen-extension.json`, or a future lifecycle shell) that exposes canonical behavior without owning product logic; the public npm package ships all six current metadata roots, while the Qoder runtime bundle includes only `.qoder-plugin/`. |
 | Canonical owner | The single directory that owns a behavior's product judgment; host shells and mirrors point back to it. |
 
 The full glossary with owner links lives in

docs/docs/hosts/adapter-matrix.md

@@ -19,17 +19,19 @@ host-neutral.
 | Claude Code | Analysis-capable source-local host | `.claude-plugin/` | Workspace-matching local Claude transcripts when present | Self-contained HTML + Markdown |
 | Codex | Analysis-capable source-local host | `.codex-plugin/` | Codex sessions | Self-contained HTML + Markdown |
 | Cursor | Analysis-capable source-local host | `.cursor-plugin/` | Workspace-matched transcripts, metadata, and audit logs; partial coverage stays explicit | Self-contained HTML + Markdown |
+| Qwen Code | Analysis-capable source-local host | `qwen-extension.json` | Workspace-matching local Qwen transcripts when present | Self-contained HTML + Markdown |
+| GitHub Copilot | Analysis-capable source-local host | `.github/plugin/` | Workspace-matched Copilot CLI transcripts; partial coverage stays explicit | Self-contained HTML + Markdown |
 
-The `@qoderai/better-harness` npm package includes all four plugin metadata
+The `@qoderai/better-harness` npm package includes all six plugin metadata
 roots. The generated Qoder runtime bundle includes only the Qoder shell;
 non-Qoder generated host artifacts remain source-local.
 
 ## Output modes
 
 - **Qoder Canvas** — renderer-owned `findings.json`, Canvas-only
   `canvas.json`, and `report.canvas.tsx`.
-- **HTML visual** — portable Claude Code/Codex/Cursor contract covering
-  `findings.json`, `report.md`, and a self-contained `report.html`
+- **HTML visual** — portable Claude Code/Codex/Cursor/Qwen/Copilot contract
+  covering `findings.json`, `report.md`, and a self-contained `report.html`
   (see the [live demo](pathname:///demo/better-harness-report/)).
 - **Markdown-only** — no visual companion.
 

docs/docs/installation.mdx

@@ -148,6 +148,55 @@ cursor-agent --plugin-dir /path/to/better-harness
 Cursor session evidence is supported through workspace-matched transcripts,
 metadata, and audit logs. Partial or unavailable coverage remains explicit.
 
+</TabItem>
+<TabItem value="qwen-code" label="Qwen Code">
+
+## Qwen Code {#qwen-code}
+
+Install Better Harness as a Qwen Code extension:
+
+```bash
+qwen extensions install QoderAI/better-harness
+```
+
+Start a new Qwen Code session in the repository you want to review and run the
+report prompt:
+
+```text
+/better-harness review this project's AI coding workflow and generate a report
+```
+
+Qwen Code produces a self-contained `report.html` with paired `report.md` and
+`findings.json`. Session evidence coverage depends on Qwen Code's available
+transcript paths; missing or partial evidence remains explicit.
+
+</TabItem>
+<TabItem value="github-copilot" label="GitHub Copilot">
+
+## GitHub Copilot {#github-copilot}
+
+Register this repository as a Copilot plugin marketplace, then install Better
+Harness:
+
+```bash
+copilot plugin marketplace add QoderAI/better-harness
+copilot plugin install better-harness@better-harness
+```
+
+Verify that the Skill loaded:
+
+```bash
+copilot plugin list
+```
+
+Prefer marketplace installs. Direct repository, URL, and local-path installs are
+deprecated in Copilot CLI.
+
+Copilot session evidence is supported through workspace-matched Copilot CLI
+transcripts under `~/.copilot/session-state/`. Copilot records no per-response
+token usage, and VS Code Copilot Chat has no supported durable transcript; both
+remain explicit evidence boundaries.
+
 </TabItem>
 </Tabs>
 

docs/docs/reference/architecture.md

@@ -44,7 +44,7 @@ available after the agent acts:
 | Project evidence | `better-harness core-change-watch` | Project, history, core-path, and diff signals |
 | Change confidence | `hooks/git-scripts/blast-radius` | Symbol-graph blast radius of a change |
 | Dependency governance | `better-harness dependency-governance` | Update automation, audit, stale-dep signals |
-| Session evidence | `better-harness session-analysis` | Normalize Qoder, Codex, Claude, or Cursor session behavior |
+| Session evidence | `better-harness session-analysis` | Normalize Qoder, Codex, Claude, Cursor, Qwen, or Copilot session behavior |
 | Agent assets | `better-harness coding-agent-practices inventory` | Inventory configured agent surfaces |
 | Guardrails | `hooks/`, `scripts/agent-guardrails` | Secret scanning and lifecycle checks |
 

docs/docs/your-first-report.md

@@ -15,8 +15,8 @@ you want to review, start a new session, and run:
 
 Better Harness scopes behavior claims to relevant Task Episodes and the
 surrounding project mechanisms. Qoder produces a Canvas report; Claude Code,
-Codex, and Cursor produce self-contained HTML with paired Markdown. Missing or
-partial evidence remains explicit.
+Codex, Cursor, Qwen Code, and GitHub Copilot produce self-contained HTML with
+paired Markdown. Missing or partial evidence remains explicit.
 
 See the [live demo report](pathname:///demo/better-harness-report/) for
 what the HTML output looks like.

docs/i18n/zh-Hans/code.json

@@ -41,6 +41,12 @@
   "homepage.hosts.cursor.setup": {
     "message": "使用 --plugin-dir 加载源码本地插件。"
   },
+  "homepage.hosts.qwenCode.setup": {
+    "message": "作为 Qwen Code 扩展安装。"
+  },
+  "homepage.hosts.githubCopilot.setup": {
+    "message": "添加 Marketplace 并安装插件。"
+  },
   "homepage.hero.tagline": {
     "message": "看清你的 AI 编码工作流——并一步一步把它变好。"
   },

docs/i18n/zh-Hans/docusaurus-plugin-content-docs/current/concepts/glossary.md

@@ -63,7 +63,7 @@ sidebar_position: 3
 | --- | --- |
 | Skill | 由 `SKILL.md` frontmatter 加简洁工作流定义的可重复智能体工作流。 |
 | 宿主适配层 | 按宿主的发现与证据形态胶水层；保持引擎与宿主无关。 |
-| 宿主 shell | 轻量宿主元数据（`.claude-plugin/`、`.qoder-plugin/`、`.cursor-plugin/`、`.codex-plugin/`），暴露规范行为但不拥有产品逻辑。 |
+| 宿主 shell | 轻量宿主元数据（`.claude-plugin/`、`.qoder-plugin/`、`.cursor-plugin/`、`.codex-plugin/`、`.github/plugin/`、`qwen-extension.json` 或未来的生命周期 shell），暴露规范行为但不拥有产品逻辑；公共 npm 包包含当前六个元数据根目录，而 Qoder 运行时 bundle 只包含 `.qoder-plugin/`。 |
 | 规范负责目录 | 唯一拥有某行为产品判断的目录；宿主 shell 和镜像都指回它。 |
 
 带负责方链接的完整术语表见