repo-harness 0.2.2 → 0.2.3

package/README.es.md

@@ -187,13 +187,11 @@ npx -y repo-harness init
 ```
 
 La npm package release line es ahora `0.2.x`; el workflow compatibility model line
-generado se rastrea por separado como `5.x`. `repo-harness@0.2.1` separa el
-bootstrap global inicial (`repo-harness init`) del refresco repo-local
-(`repo-harness update`), conserva el instalador global de plugin/hook
-(`scripts/setup-plugins.sh`), el centinela de seguridad de configuración de solo
-lectura (`repo-harness security scan`), el ciclo de vida draft-plan explícito de
-Claude/Codex y añade inicialización no bloqueante del índice CodeGraph para el
-routing estructural de prompts.
+generado se rastrea por separado como `5.x`. `repo-harness init` es el bootstrap
+global y `repo-harness update` es el refresco repo-local. `repo-harness init`
+configura el CLI, los hook adapters de nivel usuario, Waza, Mermaid, el brain
+root y CodeGraph MCP; el viejo camino Claude plugin `scripts/setup-plugins.sh`
+queda retirado.
 
 Si trabajas desde un checkout del código fuente:
 
@@ -237,9 +235,9 @@ Aplica solo después de que el reporte del dry-run sea correcto:
 npx -y repo-harness update
 ```
 
-Para un proyecto o módulo nuevo, usa el command skill `repo-harness-scaffold`. Para
-un repositorio existente, usa `repo-harness-init`; este instala o refresca el
-harness y no crea el stack tecnológico de la aplicación.
+Para un proyecto o módulo nuevo, usa la branch command `repo-harness-scaffold`.
+Para un repositorio existente, usa `repo-harness update`; este instala o refresca
+el harness y no crea el stack tecnológico de la aplicación.
 
 ### Cómo se ve el éxito
 
@@ -346,22 +344,23 @@ Guards habituales:
 - `repo-harness update` refresca las runtime pieces:
   - los `repo-harness` skill aliases
   - los global Codex/Claude hook adapters
-  - las Waza skills: `check`, `design`, `health`, `hunt`, `learn`, `read`, `think`, `write`
-  - sincroniza `diagram-design` si existe la source copy
+  - las Waza skills: `think`, `hunt`, `check`, `health`
+  - Mermaid
 - El resto del external tooling se mantiene advisory-only:
   - `bash scripts/check-agent-tooling.sh --host both --check-updates`
   - no configura automáticamente gstack, gbrain, CodeGraph MCP, daemon ni provider
 
 ## Action Command Skills
 
-Los command skill facades públicos están en `assets/skill-commands/`:
+Los command facades públicos están en `assets/skill-commands/`; preservan la
+compatibilidad de discovery por skills, mientras el CLI y los hooks ejecutan:
 
 - Planning / review: `repo-harness-plan`, `repo-harness-review`, `repo-harness-autoplan`
 - Repo workflow actions: `repo-harness-ship`, `repo-harness-init`, `repo-harness-migrate`, `repo-harness-upgrade`, `repo-harness-capability`, `repo-harness-architecture`, `repo-harness-handoff`, `repo-harness-deploy`, `repo-harness-repair`, `repo-harness-check`
-- Project creation: `repo-harness-scaffold`
+- Branch project creation: `repo-harness-scaffold`
 
-`repo-harness-init` se usa para repositorios existentes; `repo-harness-scaffold` se
-usa para crear proyectos o módulos nuevos. `hooks-init`, `docs-init` y
+`repo-harness update` se usa para repositorios existentes; `repo-harness-scaffold`
+queda como branch command para crear proyectos o módulos nuevos. `hooks-init`, `docs-init` y
 `create-project-dirs` son pasos internos, no commands públicos.
 
 ## Maintainer Reference

package/README.fr.md

@@ -191,18 +191,11 @@ npx -y repo-harness init
 ```
 
 La release line du package npm est désormais `0.2.x` ; la generated workflow
-compatibility model line est suivie séparément en `5.x`. `repo-harness@0.2.1`
-sépare le bootstrap global initial (`repo-harness init`) du rafraîchissement
-repo-local (`repo-harness update`), conserve l'installateur global de plugin/hook
-(`scripts/setup-plugins.sh`), la sentinelle de sécurité en lecture seule
-(`repo-harness security scan`), le cycle de vie draft-plan explicite de
-Claude/Codex, et ajoute l'initialisation non bloquante de l'index CodeGraph pour
-le routing structurel des prompts. Ces capacités reposent sur le CLI renommé, le
-bootstrap de l'adapter de hook de niveau utilisateur, les AI-native scaffold
-overlays, le typed prompt-guard decision engine, le nommage des task artifacts par
-plan-stem, les runtime aliases
-`REPO_HARNESS_*`, la Waza runtime skill sync, et le release gate que le maintainer
-utilise avant de publier sur npm.
+compatibility model line est suivie séparément en `5.x`. `repo-harness init`
+sert au bootstrap global et `repo-harness update` sert au rafraîchissement
+repo-local. `repo-harness init` configure le CLI, les hook adapters de niveau
+utilisateur, Waza, Mermaid, le brain root et CodeGraph MCP ; l'ancien chemin
+Claude plugin `scripts/setup-plugins.sh` est retiré.
 
 Si vous travaillez depuis un checkout source :
 
@@ -246,9 +239,9 @@ Appliquez seulement une fois que le rapport du dry-run est correct :
 npx -y repo-harness update
 ```
 
-Pour un nouveau projet ou un nouveau module, utilisez la command skill
-`repo-harness-scaffold`. Pour un dépôt existant, utilisez `repo-harness-init` ; il
-installe ou rafraîchit le harness sans créer de stack applicatif.
+Pour un nouveau projet ou un nouveau module, utilisez la branch command
+`repo-harness-scaffold`. Pour un dépôt existant, utilisez `repo-harness update` ;
+il installe ou rafraîchit le harness sans créer de stack applicatif.
 
 ### À quoi ressemble le succès
 
@@ -355,22 +348,24 @@ Guards courants :
 - `repo-harness update` rafraîchit les runtime pieces :
   - les `repo-harness` skill aliases
   - les global Codex/Claude hook adapters
-  - les Waza skills : `check`, `design`, `health`, `hunt`, `learn`, `read`, `think`, `write`
-  - synchronise `diagram-design` si la source copy existe
+  - les Waza skills : `think`, `hunt`, `check`, `health`
+  - Mermaid
 - Les autres outils externes restent advisory-only :
   - `bash scripts/check-agent-tooling.sh --host both --check-updates`
   - pas de configuration automatique de gstack, gbrain, CodeGraph MCP, daemon ou provider
 
 ## Action Command Skills
 
-Les command skill facades publics se trouvent dans `assets/skill-commands/` :
+Les command facades publics se trouvent dans `assets/skill-commands/` ; ils
+préservent la découverte par skills, tandis que l'exécution appartient au CLI et
+aux hooks :
 
 - Planning / review : `repo-harness-plan`, `repo-harness-review`, `repo-harness-autoplan`
 - Repo workflow actions : `repo-harness-ship`, `repo-harness-init`, `repo-harness-migrate`, `repo-harness-upgrade`, `repo-harness-capability`, `repo-harness-architecture`, `repo-harness-handoff`, `repo-harness-deploy`, `repo-harness-repair`, `repo-harness-check`
-- Project creation : `repo-harness-scaffold`
+- Branch project creation : `repo-harness-scaffold`
 
-`repo-harness-init` sert aux dépôts existants ; `repo-harness-scaffold` sert à
-créer un nouveau projet ou module. `hooks-init`, `docs-init` et
+`repo-harness update` sert aux dépôts existants ; `repo-harness-scaffold` sert de
+branch command pour créer un nouveau projet ou module. `hooks-init`, `docs-init` et
 `create-project-dirs` sont des étapes internes, pas des commands publiques.
 
 ## Maintainer Reference

package/README.ja.md

@@ -77,7 +77,7 @@ product boundary は意図的に地味です。対象リポジトリを検査し
 
 設計は 3 層に分かれます。
 
-1. **ソースパッケージ層**：本リポジトリが CLI、command skill facades、templates、hook assets、
+1. **ソースパッケージ層**：本リポジトリが CLI、CLI-backed command facades、templates、hook assets、
    workflow contract、tests、release gate を所有します。
 2. **対象リポジトリ contract 層**：`repo-harness update` または migration が、`docs/spec.md`、
    `plans/`、`tasks/`、`.ai/context/`、`.ai/harness/`、helper scripts、`.ai/hooks/` といった
@@ -160,11 +160,9 @@ npx -y repo-harness init
 ```
 
 npm package の release line は現在 `0.2.x` です。生成される workflow compatibility model line は
-別途 `5.x` として追跡されます。`repo-harness@0.2.1` は、初回 global bootstrap
-（`repo-harness init`）と repo-local refresh（`repo-harness update`）を分離し、グローバルな
-plugin/hook インストールスクリプト（`scripts/setup-plugins.sh`）、読み取り専用の設定セキュリティ哨兵
-（`repo-harness security scan`）、明示的な Claude/Codex draft-plan ライフサイクルを保ち、
-構造的 prompt routing 用の非ブロッキング CodeGraph index 初期化を追加します。
+別途 `5.x` として追跡されます。`repo-harness init` は global bootstrap、`repo-harness update` は
+repo-local refresh です。`repo-harness init` は CLI、user-level hook adapters、Waza、Mermaid、
+brain root、CodeGraph MCP を設定し、退役した `scripts/setup-plugins.sh` の Claude plugin path は使いません。
 
 ソースの checkout から作業する場合：
 
@@ -206,8 +204,8 @@ dry-run のレポートが正しいことを確認してから適用します。
 npx -y repo-harness update
 ```
 
-新しいプロジェクトやモジュールには `repo-harness-scaffold` command skill を使います。既存リポジトリには
-`repo-harness-init` を使います。これは harness をインストールまたはリフレッシュするもので、アプリケーション
+新しいプロジェクトやモジュールには支線 command `repo-harness-scaffold` を使います。既存リポジトリには
+`repo-harness update` を使います。これは harness をインストールまたはリフレッシュするもので、アプリケーション
 スタックは作成しません。
 
 ### 成功した状態
@@ -313,21 +311,21 @@ hook がブロックしたときは、まず terminal の構造化された出
 - `repo-harness update` は runtime pieces をリフレッシュします：
   - `repo-harness` skill aliases
   - global Codex/Claude hook adapters
-  - Waza skills：`check`、`design`、`health`、`hunt`、`learn`、`read`、`think`、`write`
-  - source copy が存在すれば `diagram-design` を同期
+  - Waza skills：`think`、`hunt`、`check`、`health`
+  - Mermaid
 - その他の外部ツールは advisory-only のままです：
   - `bash scripts/check-agent-tooling.sh --host both --check-updates`
   - gstack、gbrain、CodeGraph MCP、daemon、provider を自動設定しない
 
 ## Action Command Skills
 
-公開 command skill facades は `assets/skill-commands/` にあります。
+公開 command facades は `assets/skill-commands/` にあります。host skill discovery との互換性を残しつつ、実行は CLI と hooks が担います。
 
 - Planning / review：`repo-harness-plan`、`repo-harness-review`、`repo-harness-autoplan`
 - Repo workflow actions：`repo-harness-ship`、`repo-harness-init`、`repo-harness-migrate`、`repo-harness-upgrade`、`repo-harness-capability`、`repo-harness-architecture`、`repo-harness-handoff`、`repo-harness-deploy`、`repo-harness-repair`、`repo-harness-check`
-- Project creation：`repo-harness-scaffold`
+- Branch project creation：`repo-harness-scaffold`
 
-`repo-harness-init` は既存リポジトリ向け、`repo-harness-scaffold` は新しいプロジェクトやモジュールの作成向けです。
+`repo-harness update` は既存リポジトリ向け、`repo-harness-scaffold` は支線 command として新しいプロジェクトやモジュールを作成します。
 `hooks-init`、`docs-init`、`create-project-dirs` は内部ステップであり、公開 commands ではありません。
 
 ## Maintainer Reference

package/README.md

@@ -34,16 +34,15 @@ This repository now dogfoods its own tasks-first contract. It is both:
   read a 1KB capability contract or query the index instead of spending thousands of
   tokens rediscovering structure.
 
-## What's New in 0.2.2
-
-- **Safer global init defaults.** `repo-harness init` now streams setup progress
-  directly to the terminal and no longer installs the Superpowers Claude
-  marketplace plugin by default. Use `repo-harness init --with-superpowers` only
-  when you explicitly want that marketplace plugin.
-- **Global init command (`repo-harness init`).** One command bootstraps the global
-  Claude environment: essential plugins, configurable policy hooks (worktree guard,
-  atomic commit/pending), optional LSP plugins by project type, and four hook profiles
-  (`standard`, `minimal`, `biome`, `biome-strict`).
+## What's New in 0.2.3
+
+- **Safer global init defaults.** `repo-harness init` no longer calls the legacy
+  Claude plugin setup script or any Superpowers marketplace installer path.
+- **Global init command (`repo-harness init`).** One command installs the
+  `repo-harness` CLI globally, refreshes repo-harness skill aliases, installs
+  user-level Codex/Claude hook adapters, configures Waza
+  (`think`, `hunt`, `check`, `health`) plus Mermaid, persists the brain root, and
+  configures CodeGraph MCP.
   Run `npx -y repo-harness init`; no source checkout is required.
 - **Repo refresh command (`repo-harness update`).** Existing-repo install and
   refresh now has its own command surface, preserving the previous repo-local
@@ -91,7 +90,7 @@ workflow surfaces stay consistent.
 
 The design has three layers:
 
-1. **Source package**: this repository owns the CLI, command skill facades,
+1. **Source package**: this repository owns the CLI, CLI-backed command facades,
    templates, hook assets, workflow contract, tests, and release gate.
 2. **Target repo contract**: `repo-harness update` or migration writes repo-local
    files such as `docs/spec.md`, `plans/`, `tasks/`, `.ai/context/`,
@@ -177,10 +176,11 @@ safe to adopt in a real repo.
 npx -y repo-harness init
 ```
 
-`init` is the first-run global bootstrap path. It runs the packaged
-`scripts/setup-plugins.sh`, installs global Claude plugins and hook profiles, and
-defaults to `--hooks standard`. Use `--hooks <profile>` or `--no-hooks` when you
-need a different hook profile.
+`init` is the first-run global bootstrap path. It installs the current npm
+package as the global CLI, refreshes repo-harness skill aliases, installs
+user-level hook adapters, configures Waza runtime skills, persists a brain root
+under `~/.repo-harness/config.json`, and configures CodeGraph MCP. It does not
+apply repo-local workflow files to the current directory.
 
 ### Install or refresh a repo-local harness
 
@@ -194,13 +194,13 @@ repository to install or refresh workflow files, hook assets, host adapters,
 skill aliases, and repo-local verification surfaces from the current npm package.
 
 The npm package release line is now `0.2.x`; generated workflow compatibility is
-tracked separately as the `5.x` model line. The `0.2.2` package splits first-run
+tracked separately as the `5.x` model line. The `0.2.3` package splits first-run
 global bootstrap (`repo-harness init`) from repo-local refresh
-(`repo-harness update`), keeps the global plugin/hook installer
-(`scripts/setup-plugins.sh`), the read-only config security sentinel
+(`repo-harness update`), replaces the legacy global plugin installer path with
+typed CLI/hook/dependency bootstrap, keeps the read-only config security sentinel
 (`repo-harness security scan`), the explicit Claude/Codex draft-plan lifecycle,
-adds non-blocking CodeGraph index initialization for structural prompt routing,
-and keeps Superpowers behind the explicit `--with-superpowers` opt-in flag.
+and adds non-blocking CodeGraph index initialization for structural prompt
+routing.
 These sit on top of the renamed `repo-harness` CLI, user-level hook
 adapter bootstrap, AI-native scaffold overlays, the typed prompt-guard decision
 engine, plan-stem task artifact naming, `REPO_HARNESS_*` runtime aliases, Waza
@@ -250,8 +250,8 @@ Apply only after the dry-run report looks correct:
 npx -y repo-harness update
 ```
 
-For a new project or module, use the `repo-harness-scaffold` command skill. For
-an existing repo, use `repo-harness-init`; it installs or refreshes the harness
+For a new project or module, use the branch command `repo-harness-scaffold`. For
+an existing repo, use `repo-harness update`; it installs or refreshes the harness
 without creating an application stack.
 
 ### Success looks like this
@@ -340,7 +340,7 @@ Most common guards:
 
 ## Current Release
 
-- npm package: `repo-harness@0.2.2`
+- npm package: `repo-harness@0.2.3`
 - Generated workflow compatibility: `5.2.3`
 - GitHub repository: `Ancienttwo/repo-harness`
 - Release history: [`docs/CHANGELOG.md`](docs/CHANGELOG.md)
@@ -371,16 +371,17 @@ Most common guards:
   - `complex -> gstack`
   - `simple -> Waza` with Codex-first runtime copies in `~/.codex/skills`
   - `knowledge -> gbrain`
-- `repo-harness update` bootstraps the Codex/Claude runtime pieces needed for the
+- `repo-harness init` bootstraps the Codex/Claude runtime pieces needed for the
   default workflow:
   - refreshes `repo-harness` skill aliases
   - installs global Codex/Claude hook adapters
-  - installs Waza skills (`think`, `hunt`, `check`, `health`) through the skills CLI
-  - installs `mermaid` into Codex/Claude skill roots through the skills CLI
+  - installs Waza skills (`think`, `hunt`, `check`, `health`) and Mermaid through the skills CLI
+  - persists the brain root in `~/.repo-harness/config.json`
+  - configures CodeGraph MCP for selected host agents
 - Other external tooling stays advisory-only:
   - `bash scripts/check-agent-tooling.sh --host both --check-updates`
   - Waza update checks compare upstream `tw93/Waza` `SKILL.md` hashes without running `npx skills check`
-  - no automatic gstack, gbrain, CodeGraph MCP, daemon, or provider setup
+  - no automatic gstack, gbrain MCP, CodeGraph daemon, or provider setup
 - Manual distillation stays repo-local:
   - repeated corrections -> `tasks/lessons.md`
   - deep findings and hidden contracts -> `tasks/research.md`
@@ -407,17 +408,16 @@ are not all bundled product dependencies.
 
 ## Action Command Skills
 
-Source-owned command skill facades live in `assets/skill-commands/`. They keep
-the public surface action-style while sharing the same router, contract, scripts,
-and tests:
+Source-owned command facades live in `assets/skill-commands/`. They keep host
+skill discovery compatible while the CLI and hooks own execution:
 
 - Planning and review: `repo-harness-plan`, `repo-harness-review`, `repo-harness-autoplan`
 - Repo workflow actions: `repo-harness-ship`, `repo-harness-init`, `repo-harness-migrate`, `repo-harness-upgrade`, `repo-harness-capability`, `repo-harness-architecture`, `repo-harness-handoff`, `repo-harness-deploy`, `repo-harness-repair`, `repo-harness-check`
-- Project creation: `repo-harness-scaffold`
+- Branch project creation command: `repo-harness-scaffold`
 
-`repo-harness-init` is for an existing repo; `repo-harness-scaffold` creates a new
-project or module scaffold. `hooks-init`, `docs-init`, and `create-project-dirs`
-are internal steps, not public commands.
+`repo-harness update` is for an existing repo; `repo-harness-scaffold` creates a
+new project or module scaffold as a side command. `hooks-init`, `docs-init`, and
+`create-project-dirs` are internal steps, not public commands.
 
 `repo-harness-scaffold` keeps the A-K plan catalog as the project-type authority
 and adds AI-native app structure through an optional `ai_native_profile` overlay.

package/README.zh-CN.md

@@ -23,14 +23,14 @@ repo-local workflow 的自托管样例。
   做渐进式上下文加载：一份小而稳定的 root context（约 12KB），加上只在改到对应文件时才加载的
   capability 块。agent 读一份 1KB 的 capability 合约或查索引，而不是花上千 token 重新摸清结构。
 
-## 0.2.2 新特性
-
-- **更安全的全局初始化默认值。** `repo-harness init` 现在会把 setup 进度直接输出到终端，
-  不再默认安装 Superpowers Claude marketplace plugin。只有你明确需要它时，才使用
-  `repo-harness init --with-superpowers`。
-- **全局初始化命令（`repo-harness init`）。** 一条命令引导全局 Claude 环境：essential plugins、
-  可配置 policy hooks（worktree guard、atomic commit/pending）、按项目类型可选的 LSP plugins，以及
-  四档 hook profile（`standard`、`minimal`、`biome`、`biome-strict`）。运行
+## 0.2.3 新特性
+
+- **更安全的全局初始化默认值。** `repo-harness init` 不再调用旧 Claude plugin setup
+  脚本，也没有 Superpowers marketplace installer 路径。
+- **全局初始化命令（`repo-harness init`）。** 一条命令安装全局 `repo-harness` CLI、
+  刷新 repo-harness skill aliases、安装 Codex/Claude user-level hook adapters、
+  配置 Waza（`think`、`hunt`、`check`、`health`）和 Mermaid、持久化 brain root，并配置
+  CodeGraph MCP。运行
   `npx -y repo-harness init`，不需要 clone 源码仓库。
 - **仓库刷新命令（`repo-harness update`）。** 已有仓库的安装/刷新入口独立成命令，继续复用
   原 repo-local harness migration 路径，同时让 `init` 专注于全局 runtime setup。
@@ -68,7 +68,7 @@ repo-local hooks，然后验证这些 workflow surfaces 仍然一致。
 
 整体分三层：
 
-1. **源码包层**：本仓库维护 CLI、command skill facades、templates、hook assets、
+1. **源码包层**：本仓库维护 CLI、CLI-backed command facades、templates、hook assets、
    workflow contract、tests 和 release gate。
 2. **目标仓库合约层**：`repo-harness update` 或 migration 会写入 `docs/spec.md`、
    `plans/`、`tasks/`、`.ai/context/`、`.ai/harness/`、helper scripts 和
@@ -149,9 +149,10 @@ flowchart TD
 npx -y repo-harness init
 ```
 
-`init` 是首次全局引导入口。它运行 npm 包里自带的 `scripts/setup-plugins.sh`，
-安装全局 Claude plugins 和 hook profiles，默认等价于 `--hooks standard`。
-需要不同 hook profile 时再传 `--hooks <profile>` 或 `--no-hooks`。
+`init` 是首次全局引导入口。它把当前 npm 包安装成全局 CLI，刷新 repo-harness
+skill aliases，安装 user-level hook adapters，配置 Waza runtime skills，把 brain
+root 持久化到 `~/.repo-harness/config.json`，并配置 CodeGraph MCP。它不会把当前目录
+默认迁移成 repo-local workflow。
 
 ### 安装或刷新 repo-local harness
 
@@ -165,11 +166,11 @@ npx -y repo-harness update
 repo-local verification surfaces。
 
 npm package release line 现在是 `0.2.x`；生成的 workflow compatibility model line
-单独以 `5.x` 追踪。`repo-harness@0.2.2` 把首次全局引导（`repo-harness init`）
-和 repo-local 刷新（`repo-harness update`）拆开，同时保留全局 plugin/hook 安装脚本
-（`scripts/setup-plugins.sh`）、只读配置安全哨兵（`repo-harness security scan`）、
-显式 Claude/Codex draft-plan 生命周期，新增 prompt hook 的非阻塞 CodeGraph index 初始化，
-并把 Superpowers 放到显式 `--with-superpowers` opt-in 后面。这些能力叠加在改名后的 CLI、user-level hook adapter bootstrap、AI-native scaffold overlays、
+单独以 `5.x` 追踪。`repo-harness@0.2.3` 把首次全局引导（`repo-harness init`）
+和 repo-local 刷新（`repo-harness update`）拆开，同时用 typed CLI/hook/dependency
+bootstrap 替换旧全局 plugin installer 路径，保留只读配置安全哨兵（`repo-harness security scan`）、
+显式 Claude/Codex draft-plan 生命周期，并新增 prompt hook 的非阻塞 CodeGraph index 初始化。
+这些能力叠加在改名后的 CLI、user-level hook adapter bootstrap、AI-native scaffold overlays、
 typed prompt-guard decision engine、plan-stem task artifact 命名、`REPO_HARNESS_*`
 runtime aliases、Waza runtime skill sync，以及 maintainer 发布 npm 前使用的 release gate 之上。
 
@@ -213,8 +214,8 @@ dry-run 报告正确后再应用：
 npx -y repo-harness update
 ```
 
-新项目或新模块使用 `repo-harness-scaffold` command skill。已有仓库使用
-`repo-harness-init`；它会安装或刷新 harness，不会创建应用技术栈。
+新项目或新模块使用支线 command `repo-harness-scaffold`。已有仓库使用
+`repo-harness update`；它会安装或刷新 harness，不会创建应用技术栈。
 
 ### 成功长什么样
 
@@ -301,7 +302,7 @@ hook block 工作时，先看 terminal 里的结构化输出。核心字段是
 
 ## 当前 Release
 
-- npm package：`repo-harness@0.2.2`
+- npm package：`repo-harness@0.2.3`
 - Generated workflow compatibility：`5.2.3`
 - GitHub repository：`Ancienttwo/repo-harness`
 - Release history：[`docs/CHANGELOG.md`](docs/CHANGELOG.md)
@@ -316,24 +317,26 @@ hook block 工作时，先看 terminal 里的结构化输出。核心字段是
   - `assets/workflow-contract.v1.json`
 - Generated repos 默认使用 repo-local harness flow：
   - `docs/spec.md -> plans/ -> tasks/contracts/ -> tasks/reviews/ -> .ai/context/context-map.json -> .ai/harness/*`
-- `repo-harness update` 会刷新 runtime pieces：
+- `repo-harness init` 会刷新 runtime pieces：
   - `repo-harness` skill aliases
   - global Codex/Claude hook adapters
-  - Waza skills：`check`、`design`、`health`、`hunt`、`learn`、`read`、`think`、`write`
-  - 如果 source copy 存在，同步 `diagram-design`
+  - Waza skills：`think`、`hunt`、`check`、`health`
+  - 持久化 brain root 到 `~/.repo-harness/config.json`
+  - 配置 CodeGraph MCP
 - 其他外部工具保持 advisory-only：
   - `bash scripts/check-agent-tooling.sh --host both --check-updates`
-  - 不自动设置 gstack、gbrain、CodeGraph MCP、daemon 或 provider
+  - 不自动设置 gstack、gbrain MCP、CodeGraph daemon 或 provider
 
 ## Action Command Skills
 
-公共 command skill facades 在 `assets/skill-commands/`：
+公共 command facades 在 `assets/skill-commands/`；它们保留 host skill discovery
+兼容性，真正执行由 CLI 和 hooks 负责：
 
 - Planning / review：`repo-harness-plan`、`repo-harness-review`、`repo-harness-autoplan`
 - Repo workflow actions：`repo-harness-ship`、`repo-harness-init`、`repo-harness-migrate`、`repo-harness-upgrade`、`repo-harness-capability`、`repo-harness-architecture`、`repo-harness-handoff`、`repo-harness-deploy`、`repo-harness-repair`、`repo-harness-check`
-- Project creation：`repo-harness-scaffold`
+- 支线项目创建 command：`repo-harness-scaffold`
 
-`repo-harness-init` 用于已有仓库；`repo-harness-scaffold` 用于创建新项目或模块。
+`repo-harness update` 用于已有仓库；`repo-harness-scaffold` 作为支线 command 创建新项目或模块。
 `hooks-init`、`docs-init` 和 `create-project-dirs` 是内部步骤，不是公共 commands。
 
 ## Maintainer Reference

package/SKILL.md

@@ -1,22 +1,23 @@
 ---
 name: repo-harness
-description: routes repo-harness requests to action-style init, scaffold, migrate, audit, repair, and ship workflows
+description: routes repo-harness requests through the CLI and hook automation plugin for init, update, scaffold, migrate, audit, repair, and ship workflows
 when_to_use: "repo-harness, repo-harness-skill compatibility, initialize repo-local agentic development harness, scaffold new project with repo-harness, migrate repo-local agentic development harness, audit repo-local agentic development harness, repair repo-local agentic development harness"
 ---
 
 # repo-harness
 
-`repo-harness` is the repo-local agentic development harness skill. It is a thin
-router over a versioned workflow engine and action-style command facades.
+`repo-harness` is the CLI and hook automation plugin for repo-local agentic
+development. The skill entrypoint is a compatibility router over the versioned
+workflow engine and CLI command facades.
 
 Compatibility boundary:
 
-- internal engine: tasks-first harness
+- internal engine: CLI plus hook-backed tasks-first harness
 - contract ID: tasks-first-harness-v1
 - canonical skill, CLI, and package name: `repo-harness`
 - compatibility trigger/runtime fallback: `repo-harness-skill`
 - retired legacy alias: `project-initializer`
-- new-project creation surface: `repo-harness-scaffold`
+- new-project creation surface: `repo-harness-scaffold` (secondary generator)
 
 `repo-harness-skill` may still route old prompts and runtime fallback lookups.
 It must not expose duplicate Codex command facades. `project-initializer` is a
@@ -34,8 +35,8 @@ The skill should not carry the whole workflow contract in prose. It should:
 
 ## When to use
 
-- initialize a new repo with Codex/Codex-compatible workflow scaffolding
-- create a new project or module scaffold, then attach the harness
+- install or refresh the CLI+hooks workflow in an existing repo
+- create a new project or module scaffold only when the user asks for a new product/module skeleton, then attach the harness
 - migrate an older repo to the current tasks-first harness
 - audit drift between prompts, hooks, scripts, and repo-local contract files
 - repair broken task-sync, workflow-contract, or handoff surfaces
@@ -115,10 +116,12 @@ The main engine entrypoints are:
 - `scripts/check-task-workflow.sh`
 - `scripts/create-project-dirs.sh`
 
-## Action Command Surface
+## CLI Command Facade Surface
 
-The public command skills live in `assets/skill-commands/` as thin facades over
-the same engine. Use action-style names for discoverability:
+The command facades live in `assets/skill-commands/` as compatibility wrappers
+over the same CLI and hook engine. Use them for routing when the host discovers
+skills; the implementation authority stays in the CLI, scripts, hooks, and
+contract files:
 
 - `repo-harness-plan`: interactive planning; no repo mutation by default
 - `repo-harness-review`: plan review across product, engineering, design, and DevEx
@@ -275,7 +278,10 @@ Migration defaults:
 - distill repeated corrections into `tasks/lessons.md`
 - merge missing `external_tooling` defaults into `.ai/harness/policy.json` without overwriting explicit user values
 - keep gstack/gbrain/CodeGraph detection advisory-only; do not auto-install, auto-upgrade, auto-sync, or auto-enable MCP
-- let `repo-harness init` bootstrap required Codex/Claude runtime skills in one pass: Waza (`think`, `hunt`, `check`, `health`) plus `mermaid` through the skills CLI
+- let `repo-harness init` bootstrap the required global runtime in one pass:
+  CLI install, repo-harness runtime alias sync, user-level hook adapters, Waza
+  (`think`, `hunt`, `check`, `health`), Mermaid, brain root persistence, and
+  CodeGraph CLI/MCP configuration
 - treat Waza as Codex-first: `~/.codex/skills` is the Codex runtime source, `~/.agents/skills` is only skills CLI staging/cache, and updates require stage -> copy to Codex -> `cmp` verification
 
 ## Repo-Local Contract

package/assets/reference-configs/agentic-development-flow.md

@@ -17,7 +17,7 @@ root prompt concise; this file owns the detailed routing.
 
 ## repo-harness Command Surface
 
-Use these action-style command skills when the work is about installing,
+Use these CLI-backed command facades when the work is about installing,
 migrating, repairing, or verifying this repo-local harness:
 
 | Work type | Command | Boundary |

package/assets/reference-configs/external-tooling.md

@@ -14,16 +14,17 @@ source, while `~/.agents/skills` is only the skills CLI staging/cache path used
 to receive upstream `tw93/Waza` updates before syncing verified copies into
 Codex.
 
-`repo-harness init` is allowed to bootstrap the workflow-owned runtime skills in
-one pass: Waza (`think`, `hunt`, `check`, `health`) plus `mermaid` for Codex and/or Claude, plus the bundled
-cross-review skills `codex-review` (Claude host) and `claude-review` (Codex host).
-It must not silently install unrelated toolchains.
+`repo-harness init` is allowed to bootstrap the workflow-owned global runtime in
+one pass: the `repo-harness` CLI, repo-harness runtime aliases, user-level
+Codex/Claude hook adapters, Waza (`think`, `hunt`, `check`, `health`), brain
+root persistence, Mermaid, and CodeGraph CLI/MCP configuration. It must not
+silently install unrelated toolchains or Claude marketplace plugins.
 
 The cross-review skills are **harness-owned and self-contained** — their source
 lives in `assets/skills/<skill>/` and they wrap the peer CLI (`codex exec` /
 `claude -p`) in a read-only sandbox with no gstack dependency, so installing them
-is a workflow-owned runtime concern, not an unrelated toolchain. They install
-host-aware: `codex-review` only into `~/.claude/skills` (a Claude session asking
+is a workflow-owned repo-local update concern, not an unrelated toolchain. They
+install host-aware during `repo-harness update`: `codex-review` only into `~/.claude/skills` (a Claude session asking
 Codex for an independent review) and `claude-review` only into `~/.codex/skills`
 (a Codex session asking Claude). When gstack is present, its `/codex` and
 `gstack-claude` skills are a more featureful superset; the harness skills are the
@@ -36,8 +37,8 @@ changes, and untracked files are all in scope. A timeout or missing peer CLI is
 reported as unavailable review evidence, not as a pass.
 
 The Codex automation profile is a runtime reference, not a vendored copy. It
-requires Waza `health`, Waza `check`, and the standalone `mermaid` skill
-to exist under `~/.codex/skills`; the skill bodies stay owned by their original
+requires Waza `health`, Waza `check`, and the standalone `mermaid` skill to
+exist under `~/.codex/skills`; the skill bodies stay owned by their original
 installations.
 
 ## Detect Safely

package/assets/skill-commands/manifest.json

@@ -1,6 +1,6 @@
 {
   "version": 1,
-  "surface": "repo-harness-action-style-skill-commands",
+  "surface": "repo-harness-cli-hooks-command-facades",
   "source": "assets/skill-commands",
   "router": "repo-harness",
   "commands": [
@@ -41,10 +41,10 @@
     },
     {
       "name": "repo-harness-scaffold",
-      "class": "project-scaffolding",
+      "class": "branch-project-scaffolding",
       "mutatesRepoByDefault": true,
       "engine": "init-project.sh plus workflow install",
-      "summary": "Creates a new project or module scaffold from plan catalog A-K and attaches the harness."
+      "summary": "Branch command that creates a new project or module scaffold from plan catalog A-K and attaches the harness."
     },
     {
       "name": "repo-harness-migrate",

package/assets/skill-commands/repo-harness-architecture/SKILL.md

@@ -20,7 +20,7 @@ architecture documentation, drift-request, or diagram pass.
    - module or snapshot docs under `docs/architecture/`
    - Mermaid fenced block in the relevant module or snapshot Markdown when a visual flow materially helps
    - optional human-readable diagram artifact under `docs/architecture/diagrams/`
-5. Use Markdown Mermaid as the semantic diagram source; use `mermaid` only for human-readable HTML renderings grounded in observed repo files.
+5. Use Markdown Mermaid as the semantic diagram source; use `mermaid` only for optional human-readable HTML renderings grounded in observed repo files.
 6. Archive handled requests with:
    - `bash scripts/archive-architecture-request.sh --request <request> --status <resolved|superseded|rejected|no-change> --artifact <path> --note <text>`
 7. Verify with:

package/assets/skill-commands/repo-harness-init/SKILL.md

@@ -11,11 +11,11 @@ Use this command for an existing repository that needs the repo-local agentic wo
 ## Protocol
 
 1. Confirm the target repo path.
-2. If running from the target repo root, use `repo-harness init`; do not require `--repo .`.
+2. If running from the target repo root, use `repo-harness update`; do not require `--repo .`.
 3. Run `bun scripts/inspect-project-state.ts --repo <repo> --format text`.
 4. If the repo is legacy, route to `repo-harness-migrate`.
-5. Otherwise run the safe path through `repo-harness init` or `bash scripts/migrate-project-template.sh --repo <repo> --apply`.
-6. Bootstrap the expected host runtime skills in the same pass: Waza (`think`, `hunt`, `check`, `health`) and `mermaid` for Codex/Claude when source copies are available.
+5. Otherwise run the safe path through `repo-harness update` or `bash scripts/migrate-project-template.sh --repo <repo> --apply`.
+6. Bootstrap the expected host runtime dependencies in the same pass: Waza (`think`, `hunt`, `check`, `health`) and the bundled cross-review skills when source copies are available.
 7. Verify with `bash scripts/check-task-workflow.sh --strict` inside the target repo when the helper exists.
 
 ## Boundaries

package/assets/skill-commands/repo-harness-scaffold/SKILL.md

@@ -1,12 +1,12 @@
 ---
 name: repo-harness-scaffold
-description: Creates a new project or module scaffold from the repo-harness plan catalog A-K, then attaches the repo-local workflow harness.
+description: Branch command that creates a new project or module scaffold from the repo-harness plan catalog A-K, then attaches the repo-local workflow harness.
 when_to_use: "repo-harness-scaffold, scaffold new project, create new app with agentic workflow, Plan A, Plan B, Plan C, Plan D, Plan E, Plan F, Plan G, Plan H, Plan I, Plan J, Plan K"
 ---
 
 # repo-harness-scaffold
 
-Use this command when the user asks to create a new project, app, or module skeleton.
+Use this branch command when the user asks to create a new project, app, or module skeleton.
 
 ## Protocol