@mstar-harness/dsh 3.6.2 → 3.7.0

package/harness-skills/mstar-coding-behavior/SKILL.md

@@ -1,11 +1,11 @@
 ---
 name: mstar-coding-behavior
-description: Morning Star 跨角色通用编码行为准则 —— 任何实现、调试、重构、审查任务动手前必读。约束 Think Before Coding（先读懂再改、显式假设、不静默猜测）、Simplicity First（YAGNI、The Ladder、`simplify:` 标记、最小耐久切片）、Surgical Changes（改动可追溯、Bug 修根因先 grep 所有调用点、不 piggyback）、Debugging（先复现、一步一测、修前写复现测试）、Review Feedback Handling（先核实再改、证据反驳）、Goal-Driven Execution（非平凡逻辑留可运行检查、Step→verify）、Communication。`@fullstack-dev*` / `@frontend-dev` / `@architect` / `@qa-engineer` / `@ops-engineer` / `@prompt-engineer` 必读；QC 核对手术范围时必读。不覆盖分支门禁、QC/QA 路由、Assignment 权限。
+description: Morning Star 跨角色通用编码行为准则 —— 任何实现、调试、重构、审查任务动手前必读。约束 Think Before Coding（先读懂再改、显式假设、不静默猜测）、Simplicity First（YAGNI、The Ladder、`simplify:` 标记、最小耐久切片）、Surgical Changes（改动可追溯、Bug 修根因先 grep 所有调用点、不 piggyback）、Debugging（先复现、一步一测、修前写复现测试）、Review Feedback Handling（先核实再改、证据反驳）、Goal-Driven Execution（非平凡逻辑留可运行检查、Step→verify）。`@fullstack-dev*` / `@frontend-dev` / `@architect` / `@qa-engineer` / `@ops-engineer` / `@prompt-engineer` 必读；QC 核对手术范围时必读。不覆盖分支门禁、QC/QA 路由、Assignment 权限。
 ---
 
 ## Load order（必读顺序）
 
-**在同一会话或任务中首次 Read 本 skill 时：必须先 Read `mstar-harness-core` skill（SKILL.md）。** 本 skill 只约束 **编码与改动风格**（Think / Simplicity / Surgical / Debugging / Goal-Driven / Communication）；**Done 所有权、状态机** 仍以 **`mstar-harness-core`** 为准；**分支 / worktree / QC-QA 检出字段** → **`mstar-branch-worktree`**；**调度防串扰** → **`mstar-dispatch-gates`**。冲突时 **以 `mstar-harness-core` 为准**。
+**在同一会话或任务中首次 Read 本 skill 时：必须先 Read `mstar-harness-core` skill（SKILL.md）。** 本 skill 只约束 **编码与改动风格**（Think / Simplicity / Surgical / Debugging / Goal-Driven）；**Done 所有权、状态机** 仍以 **`mstar-harness-core`** 为准；**分支 / worktree / QC-QA 检出字段** → **`mstar-branch-worktree`**；**调度防串扰** → **`mstar-dispatch-gates`**。冲突时 **以 `mstar-harness-core` 为准**。
 
 **摘要**：`mstar-harness-core` — 不变量与门禁；本 skill — 实现与审查时的工程习惯，不替代 harness。
 
@@ -21,14 +21,10 @@ Lightweight, host-agnostic coding-behavior principles that reduce common agent m
 
 Do not silently choose an interpretation when ambiguity exists. State assumptions explicitly when material; if multiple plausible interpretations exist, present options and ask. Surface tradeoffs affecting scope/risk/maintainability. If critical context is missing, pause and clarify instead of guessing.
 
-Quick check: can another reviewer see the assumptions made? If assumptions are wrong, will the user detect it before large edits happen?
-
 **Never lazy about understanding.** Shorten the solution, never the reading. Read the task and every file the change touches fully first; trace the actual flow end to end. A small diff in the wrong place is not efficiency — it is a second bug shipped with confidence.
 
 **Read before you write.** Before generating code in an existing project: inspect imports (which libraries the project actually uses — do not introduce a different library for the same purpose); look at nearby tests (they document expected behavior more precisely than comments); follow existing patterns (API routes, file structure, error handling — match it, do not silently introduce a different one). If no precedent exists, say so and ask. If not 100% sure a signature/parameter exists, check source/docs before using it — confidently calling a non-existent API may compile then fail at runtime.
 
-The failure mode: "correct" code that is alien to the codebase — works but looks like a different person wrote it, forcing a rewrite or permanent inconsistency.
-
 ## 2) Simplicity First
 
 **Upstream invariants**: the global engineering rules live in `mstar-harness-core`（核心研发守则）——no backward-compat layers, simplest implementation, layered growth, modularity, dependency discipline, long-term architecture; this section is their implementation-level playbook.
@@ -94,11 +90,6 @@ When something does not work, investigate; do not guess.
 - **Run existing tests before and after changes.** If they passed before and fail after, you broke something. If they were already failing, say so.
 - **If stuck, say so.** "I tried X and Y; neither worked. I'm seeing Z. I think it might be W but am not sure" is infinitely more useful than silently trying random things for 20 iterations.
 
-**Dataflow-directed diagnosis — how to locate, verify, and falsify** (for where to fix, see Surgical Changes · bug=root-cause; for the pre-fix repro test, see the bullets above):
-- **Map the data flow before judging.** Trace input → processing → storage → output, noting who writes and who reads at each step. A bug is a state deviation from expectation at some point in that flow (expected state vs observed state) — locate it from the data, not by static code reading.
-- **Four verifiable cross-checks.** Every hypothesis must be cross-checkable: re-run the repro / log comparison / input-output comparison / dual-path comparison. A hypothesis that cannot be verified on the spot is not a conclusion.
-- **Falsify the fix.** After the fix, re-run the original repro and compare output with expectation. If the problem did not disappear, the root cause was wrong — report "verification failed" explicitly; never pretend success.
-
 ## 5) Goal-Driven Execution
 
 Convert vague requests into verifiable outcomes and iterate until verified. Define concrete success criteria before major edits; use brief `Step -> verify` checkpoints for multi-step tasks; for split delivery, maintain a durable roadmap (current slice, later slices, dependencies, owner/trigger, completion condition); prefer evidence-backed completion (tests, command output, reproducible checks). If verification fails, loop on diagnosis and fix before declaring completion. Do not finish with "next plan / later / follow-up" only in prose — remaining work must be written to the plan/status artifact or the task reports `Partial` / `Blocked`.
@@ -131,14 +122,6 @@ Feedback priority:
 
 Do not perform agreement. State the technical action, the verification result, or the technical reason for disagreement.
 
-## 7) Communication
-
-- **Say what you did and why** — not just a code dump ("moved validation into a separate function because it was duplicated in three places and this makes it testable independently").
-- **Flag concerns proactively** ("this works but makes a DB call per item — if the list grows large this will be slow; want me to batch it?").
-- **Be precise about uncertainty** ("I'm not sure if this library supports streaming responses" is useful; "I think this should work" is not — tell the reviewer exactly what to verify).
-- **Match explanation to context** — do not explain REST to someone who asked for a REST endpoint, or indexes to someone who asked for an index.
-- **Write specific commit messages** — "Fix null pointer in user lookup when email contains uppercase chars", not "Fix bug".
-
 ## Integration Notes
 
 - **SDD implementer reports** (`mstar-sdd`): completion evidence must include TDD triple — test file(s), command, output — in `task-N-report.md`; fix rounds add the same for new/changed tests.
@@ -155,7 +138,7 @@ Do not perform agreement. State the technical action, the verification result, o
 
 ## Workflow
 
-Apply the seven sections in reading order: **1) Think Before Coding**（读懂再改）→ **2) Simplicity First**（最小耐久切片）→ **3) Surgical Changes**（可追溯改动 / 根因修复）→ **4) Debugging**（先复现、一步一测）→ **5) Goal-Driven Execution**（Step → verify）→ **6) Review Feedback Handling**（先核实再改、证据反驳）→ **7) Communication**（说明做了什么与为什么）。
+Apply the six sections in reading order: **1) Think Before Coding**（读懂再改）→ **2) Simplicity First**（最小耐久切片）→ **3) Surgical Changes**（可追溯改动 / 根因修复）→ **4) Debugging**（先复现、一步一测）→ **5) Goal-Driven Execution**（Step → verify）→ **6) Review Feedback Handling**（先核实再改、证据反驳）。
 
 ## Evidence
 

package/harness-skills/mstar-dispatch-gates/SKILL.md

@@ -13,21 +13,15 @@ description: Morning Star 派发与委派门禁 —— 仅 PM 可增派 subagent
 >
 > **先回到你 Assignment 最顶部的 `**IDENTITY**` 块重读一遍** —— 那里已经告诉你：你是谁、你不是谁、Task 工具不属于你。本节是那个身份断言的加固版。
 
-**身份断言（牢记，不动摇）：**
-- **你就是** `Execute as` 写的那个角色。你**不是 PM**，不是调度者，不是 parallel-agent dispatch 的使用者。
-- Task/subagent 工具即使在你的工具列表里出现，它**不属于你**。把它当作你没见过的工具 —— 不是"不能用"，是"你没有"。
-- 所有工作由你**本人**在当前会话内完成（Read / Write / Edit / Shell / Grep / Glob）。任何"这样做更高效"的想法都不构成 dispatch 的理由。
-- 遇到超出能力范围的需求 → 写 `## Blocked` 回报 PM，**不是**尝试 dispatch。Blocked 是你能发出的正确信号，dispatch 不是。
+你是 `Execute as` 写的那个角色，不是 PM / 调度者；所有工作由你**本人**在当前会话内完成（Read / Write / Edit / Shell / Grep / Glob）；超出能力范围 → 写 `## Blocked` 回报 PM，**不是**尝试 dispatch。
 
 ## 承接方反递归红线（NEVER / DO NOT；leaf executor 必读）
 
-下列行为易触发递归误派；`project-manager` 之外的角色一旦命中，须立即停止并改为本会话内可交付物，或 **`Blocked`** 回报 PM。**禁止**以「更高效」「Assignment 像 PM 编排」等理由绕开：
+下列行为易触发递归误派；`project-manager` 之外的角色一旦命中，须立即停止并改为本会话内可交付物，或 **`Blocked`** 回报 PM。**禁止**以「更高效」「Assignment 像 PM 编排」等理由绕开。
 
-- **NEVER** 在本会话内调用 Task / subagent，且其 `subagent_type` **等于**你当前的 **`Execute as`** 角色 id。
-- **NEVER** 把 Assignment 里出现的 **任何** plain `role-id` 提及、反引号 `` `<role-id>` ``、**Handoff**、**QA gate**、**Completion Report** 模板里的角色名、路由表下游角色当成「立刻 invoke」的指令；这些是**叙事 / 路由文档 / 后续 PM 编排意图**，不是命令。
-- **NEVER** 把「分解为多个计划 / 多 phase / 多 track」等**设计产物层面**的并行或拆分读成「应 invoke 与子会话数量对应的多个 subagent」。**纸面产物**由本会话写盘完成；并行**调度**由 PM 在后续轮次决定。
-- **NEVER** 因宿主**暴露**了 `Task` 或若干 `subagent_type` 名称就推断可以调用。**工具可用 ≠ 授权使用**；授权只来自 **`Delegation: allowed (...)`**。
-- **NEVER**（非 PM）主动执行 parallel-agent dispatch 来分派子代理；需要并行时回报 PM。
+**共享红线**（doc-level 并行拆分 ≠ N 个 subagent；Handoff / 路由措辞 / 角色提及 ≠ invoke；工具可用 ≠ 授权；仅 PM 可分派；非 `Delegation: allowed` 不得调用同角色 / 兄弟角色）以 **`mstar-roles/references/_shared/leaf-executor-core.md`**「Shared anti-recursion NEVER」+「Non-Recursive Dispatch Rule (shared shape)」为唯一权威清单（standard preset 下已随角色 ref 在上下文中；explicit `none` 下该 leaf 边界仍可达）。本节保留 dispatch 专属条目：
+
+- **NEVER** 在本会话内调用 Task / subagent，且其 `subagent_type` **等于**你当前的 **`Execute as`** 角色 id（同角色递归）。
 - **DO NOT** 在 Assignment 缺少 `Execute as` / `Delegation` / `Who runs this turn` 时自行「补齐」为 PM；缺字段时按 **leaf executor** 解释：亲自完成或 **`Blocked`**。
 - **DO NOT** 用「Assignment 太长 / 像编排稿」当作分派依据；先交付本会话任务再回报，分派由 PM 下一轮决定。
 
@@ -109,12 +103,12 @@ When **`Execution mode: sdd`** (`mstar-sdd`):
 - **1 Assignment ⇒ 1 invoke**。
 - **Phase 1 Review & Edit chain**（`mstar-iteration` §1.6）：主产出 **`{SPECS_DIR}/`** + **`{ITERATION_DIR}/<iteration-id>/`** package；**禁止** start 链向 `{KNOWLEDGE_DIR}/` 新增。close 时 **`mstar-compound`** 提升 package → knowledge。
 - 其他彼此独立、无先后依赖的文档编辑任务：可并行（同条消息发满 N），见 **`parallel-dispatch.md`**。
-- PM 线程代做全部专业编辑 = **反模式**（`mstar-iteration` §1.6、`mstar-harness-core` 反模式索引）。
+- PM 线程代做全部专业编辑 = **反模式**（`mstar-iteration` §1.6、`mstar-roles/references/_shared/leaf-executor-core.md`「Shared anti-recursion NEVER」）。
 - PM merge / lock（如 compass `status: locked`）在链末 subagent 返回后于 PM 线程完成。**不得**在 review-and-edit 链完成前 commit integration 分支。
 
 ## 反模式（派发）
 
-完整反模式索引见 **`mstar-harness-core`**；lease / worktree / Phase 相关反模式见 **`mstar-branch-worktree`** 与 **`mstar-iteration`**。本节仅列派发机制专属：
+共享反递归红线全清单见 **`mstar-roles/references/_shared/leaf-executor-core.md`**「Shared anti-recursion NEVER」；lease / worktree / Phase 相关反模式见 **`mstar-branch-worktree`** 与 **`mstar-iteration`**。本节仅列派发机制专属：
 
 - QC 三审拆在多条消息（tri 模式）或单席却未附 review-package 路径。
 - 仅 1 次 invoke 却声称「tri-review 已并行启动」（tri 模式 N=3）。

package/harness-skills/mstar-dispatch-gates/references/leaf-executor-checklist.md

@@ -20,4 +20,4 @@ Before any Task/subagent call (if I somehow forget the preamble):
 
 If blocked, report: `## Blocked — recursive dispatch refused (<which NEVER or reason>)`
 
-Full NEVER/DO NOT list → **`mstar-dispatch-gates` SKILL.md**「承接方反递归红线」.
+Full NEVER/DO NOT list → **`mstar-roles/references/_shared/leaf-executor-core.md`**「Shared anti-recursion NEVER」; dispatch-specific DO NOTs → **`mstar-dispatch-gates` SKILL.md**「承接方反递归红线」.

package/harness-skills/mstar-harness-core/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: mstar-harness-core
-description: Morning Star (启明星) harness **强制全局入口** —— 信息源优先级、最小交付循环、状态机与 Done 权限、Task category 路由（含 quick 禁豁免）、@explore 边界、长任务纪律、核心研发守则、护栏不变量、反模式索引、Morning Star Skill 索引与宿主入口。**任何**非平凡任务开始前必须先 Read 本 skill；再按角色与任务 **按需** Read 其它 `mstar-*` 专题（勿默认通读全部）。`@project-manager` 开轮必读 + `mstar-dispatch-gates` / `mstar-phase-gates` / `mstar-conventions` 等；实现/审查/QA 必读本 skill + `mstar-coding-behavior` 及角色清单（见 `mstar-roles`）。Prepare/派发/Git/residual/QC 细则在专题 skill，不在此重复。
+description: Morning Star (启明星) harness **生命周期 / 授权语义权威与全局入口** —— 信息源优先级、最小交付循环、状态机与 Done 权限、Task category 路由（含 quick 禁豁免）、@explore 边界、长任务纪律、核心研发守则、护栏不变量、Morning Star Skill 索引与宿主入口。加载**选择**权威在 **`mstar-roles`**（hub § Load Order 按 Assignment `Skill presets:` 决策；本 skill 不另设全局必读表）：PM 与标准路线仍以本 skill 为全局入口；独立直接调用专题时本 skill 是首个依赖；explicit `none` 角色路线以身份 + 角色自有方法自洽（唯一 hub bootstrap 例外）。`@project-manager` 开轮必读 + `mstar-dispatch-gates` / `mstar-phase-gates` / `mstar-conventions` 等；实现/审查/QA 按其角色 preset 清单加载。Prepare/派发/Git/residual/QC 细则在专题 skill，不在此重复。
 ---
 
 # Morning Star Harness Core（启明星核心）
@@ -9,16 +9,16 @@ description: Morning Star (启明星) harness **强制全局入口** —— 信
 
 ## 与其它 `mstar-*` skill 的加载契约
 
-- 凡 **`mstar-*`**（`name` ≠ `mstar-harness-core`）假定读者**已 Read 本 skill**。
-- **仅读专题、未读核心** → 未完成 harness 加载。
-- 各专题 SKILL.md 含 **Load order**；按 **`mstar-harness-core`** 专题 skill 索引 + 角色 load contract 按需加载，**禁止**为「保险」通读全部专题。
+- 本 skill 是 harness 的**生命周期 / 授权语义权威**（状态机、Done 权限、门禁、路由以本 skill 为准）；加载**选择**权威是 **`mstar-roles`**（hub bootstrap → 角色身份 → Assignment `Skill presets:` 决策，见其 § Load Order）。本 skill 不维护第二份全局必读角色表。
+- **独立直接调用专题**（不经角色 hub bootstrap）时，`mstar-harness-core` 仍是首个依赖：各专题 SKILL.md 的 Load Order / First action 节须声明 core-first。**唯一例外**是 `mstar-roles` hub bootstrap —— explicit `none` 下角色以身份 + 角色自有方法自洽，不强制读任何专题（含本 skill）；此时授权、反递归、证据诚实等 load-bearing 语义由角色引用与其 leaf 边界承接。
+- 各专题 SKILL.md 含 **Load order**；按 **`mstar-roles`** 的加载选择 + 本 skill 专题索引按需加载，**禁止**为「保险」通读全部专题。
 - **加载条件（`mstar-engine-legacy`）**：`mstar-engine-legacy` 是**条件契约档案**（engine-absent fallback）。**engine 约束激活（或宿主含 engine 能力）时不加载**——engine-present 宿主以运行时 skills 的 engine-check 指针 + engine 校验为权威；仅 engine-absent 宿主（无 `mstar` CLI / engine import）为找回被 engine 校验接管的 contract 全文而读取（触发契约见其 description）。
 
 ## Standalone harness（`mstar-*` 自洽）
 
 - **`mstar-*` skill 体系**在本仓库内自洽运行：正文与 load order **不得**依赖仓库外的 skills、CLI、或 MCP 服务。
 - **Commands**（如 `/iteration-start`）可引用本仓库 bundled、**非 `mstar-*`** 的辅助资产（例如 `skills/grill-me/`）；该引用**仅**存在于 command 层，**不**进入 `mstar-*` 专题索引或 load matrix。
-- 框架/SDK/API 问题：先 Read/Grep 项目内文档与源码；不将第三方文档工具写入 `mstar-*` 必读路径。
+- 框架/SDK/API 问题：先 Read/Grep 项目内文档、规格与源码；仍不确定时再向用户澄清。不将第三方文档工具写入 `mstar-*` 必读路径。
 
 ## 信息源优先级
 
@@ -38,9 +38,11 @@ description: Morning Star (启明星) harness **强制全局入口** —— 信
 
 ## 加载约定（强制）
 
+加载选择 SSOT：**`mstar-roles`** hub § Load Order（Assignment `Skill presets:` 决策；PM required reading 不受 preset 门控）。下表是各角色的**典型追加指引**，不是第二套选择机制；冲突时以 hub 为准。
+
 | 角色 | 始终 | 按任务追加（典型） |
 |------|------|-------------------|
-| **全部** | 本 skill | — |
+| **全部** | 加载选择 → **`mstar-roles`**（hub § Load Order；本 skill = 生命周期/授权权威，`mstar-roles` hub bootstrap 是 core-first 的唯一例外） | — |
 | **`@project-manager`** | 本 skill | `mstar-dispatch-gates`、`mstar-phase-gates`、`mstar-conventions`、`mstar-roles`；implement 波次 `mstar-sdd`；派 QC 前 `mstar-review-qc`；并行/审查 `mstar-branch-worktree`；plan/status/review bundle `mstar-artifacts`；UI 类 plan Prepare 阶段 `mstar-design-md`（DESIGN.md 门禁）；新建/大改 skill 时 `mstar-skill-authoring`；迭代管理 `mstar-iteration`（Phase 1–5）；战略性工作 `mstar-strategy`；`audit` 类请求 `mstar-audit`（执行归 `@code-reviewer`）。**不**读 `mstar-coding-behavior` |
 | **实现/审查/运维** | 本 skill + `mstar-coding-behavior` + 角色 ref | 有 git 写：`mstar-branch-worktree`；有 plan 路径：`mstar-conventions`；**PM** 派 QC 前：`mstar-review-qc`；**`qc-specialist*`**：`mstar-roles` → `references/qc-specialist/`；`qa-engineer`：`references/qa-engineer/`；改 status/residual：`mstar-artifacts`；UI：`mstar-design-md`；知识库：`mstar-compound`（PM） |
 | **leaf 承接方** | 上栏 + **`mstar-dispatch-gates`**（反递归节） | — |
@@ -100,7 +102,7 @@ PM 在 Assignment 写 **`Task category`**（主类 + 可选 `secondary`）：
 | `mstar-project-governance` | 项目治理层：`projects/<id>/roadmap.md` 编写约定 + `residuals.json` register 生命周期（open → verified close in place）、`_default` 回退、provenance；schema 与 engine `project.ts` 逐字一致 |
 | `mstar-design-md` | DESIGN.md 设计系统规范 —— 创建/审计/维护 design tokens，三级检查清单，light/dark 双主题 |
 | `mstar-review-qc` | PM：QC tri 编排、residual 留档、四层边界；leaf 执行 → `mstar-roles/references/qc-specialist/` |
-| `mstar-coding-behavior` | Think / Simplicity / Surgical / Debugging / Review Feedback / Goal-Driven / Communication |
+| `mstar-coding-behavior` | Think / Simplicity / Surgical / Debugging / Review Feedback / Goal-Driven |
 | `mstar-compound` | 知识结晶 —— 已解决问题→结构化知识文档，双轨（Bug/Knowledge），「是否值得结晶」自检清单，重叠检测，可发现性检查，CONCEPTS.md 协同 |
 | `mstar-compound-refresh` | 知识维护 —— 审查/更新/合并/删除 `{KNOWLEDGE_DIR}` 文档；**项目知识 bootstrap**（无/残旧 STRATEGY.md、CONCEPTS.md、`{KNOWLEDGE_DIR}`）→ `references/project-knowledge-bootstrap.md` |
 | `mstar-strategy` | `STRATEGY.md` 全局战略方向 —— 产品愿景、技术方向、决策原则 |
@@ -143,54 +145,8 @@ Read **`mstar-host`** after this skill; detect host per its table, then Read the
 - plan-writing artifacts land in `{PLAN_DIR}`, not external default plan directories.
 - PM Assignment 键名英文；任务正文可中文；产出/报告默认英文。
 
-## 库文档 / API 问题
-
-先 Read/Grep 项目内文档、规格与源码；仍不确定时再向用户澄清。**不**将第三方 MCP/CLI 文档工具写入 `mstar-*` load order。
-
 ## 升级触发
 
 验收仍模糊、评审冲突、重复失败、根因不可收敛 → 升级报告（状态、方案、推荐路径）。
 
-## 反模式（索引）
-
-| 反模式 | 详见 |
-|--------|------|
-| SDD paste-only / 跳过 task review / 并行 implementer | `mstar-sdd` · `mstar-dispatch-gates` |
-| SDD plan 以单席 `qc.md` 收尾 / 跳过 plan tri | `mstar-dispatch-gates` · `mstar-review-qc` · `mstar-sdd` |
-| fix 后无脑重派三审 / 用 `-rev2` 代替原位复验 | `mstar-artifacts` · `mstar-review-qc` |
-| 递归误派 / 误读 Handoff | `mstar-dispatch-gates` |
-| `quick` 跳过 Prepare | 上表 + `mstar-phase-gates` |
-| 多 worktree 未归并就 QC | `mstar-branch-worktree` |
-| 因默认 gitignore 致 feature 缺 plans 而 `Worktree mode: waived`（应保留 feature worktree + control 绝对 Plan Path / SDD dir；无 flock 仅 → `Plan parallelism: serial`） | `mstar-branch-worktree` · `mstar-iteration` §2.0 #5 · `phase-2-worktree-lease` |
-| 并行 writable implement 无隔离（L2 同 plan 多轨：N invoke ≠ worktree；L1 跨 plan：无 verified `execution_lease` + feature worktree） | `mstar-branch-worktree` L1/L2 · `mstar-iteration` §2.6 · `references/parallel-writable-pre-dispatch.md` |
-| 跨 plan 可写派发无 verified `execution_lease` / steal 活跃 lease / 并行 merge 入 `spec_integration_branch` | `mstar-iteration` · `mstar-artifacts`（leases）· `mstar-branch-worktree` L1 |
-| `InProgress` 无 `execution_lease`（snapshot 行）未恢复即可写派发 | `mstar-artifacts` — orphan recovery |
-| 混淆跨 plan lease 门控并行与单 plan 内 SDD 并行 implementer | `mstar-dispatch-gates` · `mstar-sdd` |
-| residual 只写 plan 不写 SSOT | `mstar-artifacts` |
-| `zero-residual` 下把可修 findings 登记为 open R# / 草草 `Approve with residuals` | `mstar-artifacts` Findings cleanup modes · `mstar-review-qc` |
-| 角色文件塞流程长文 | 用专题 skill |
-| 无证据宣称完成 | `mstar-coding-behavior` / verification |
-| CreatePlan 不落盘 / 无 `{HARNESS_DIR}` mirror | `mstar-host` · `cursor-plan-mode-bridge` |
-| 临时方案 / 后续计划只写在对话里 | `mstar-phase-gates` · Durable Roadmap Gate |
-| Phase 1 review chain 未完成即 commit | `mstar-iteration` §1.6；PM 代做专业角色编辑；或三角色并行派发 |
-| OpenCode prompt 含多个 prefix-style role mention | `mstar-host/references/opencode.md` § Role-mention hygiene |
-| Phase 2 paste-only / PM 自实现 | `mstar-dispatch-gates` |
-| Phase 3 折叠进 final plan closure / 跳过 §3.1 gate | `mstar-iteration` §3.0–§3.5 |
-| Phase 4 开 PR 后跳过 merge-ready loop | `mstar-iteration` §5 |
-| Phase 5 在 CI / AI review 仍在跑时 push | `mstar-iteration` §5.1a |
-| iteration-close 无 frontmatter completed / 漏 compound Phase 6 | `mstar-iteration` §3.0.5、§3.4、§3.2 #5 |
-| iteration 默认 `main` 作 base 或 PR 目标 | `mstar-iteration` §1.2、§2.3；`mstar-conventions` Spec 分支模型 |
-
-## 常见 harness 说法对照（帮助理解角色分工）
-
-| 常见说法 | 本仓库实体 |
-|----------|------------|
-| 总编排 | `@project-manager` |
-| 规划/访谈 | `@product-manager` / `@architect` + Prepare 阶段 |
-| category 路由 | **`Task category`** + 路由表 + 子代理选择 |
-| 持续推进 / 不半途而废 | Phase Gate + Todo/`tasks` + 验证门禁 |
-| 行级哈希锚定编辑 | 以 **读后再改 + 小步 Patch** 纪律落实（`mstar-phase-gates`） |
-
-项目根 **`AGENTS.md` 写什么、分层 bootstrap** → **`mstar-conventions`** `references/harness-bootstrap-and-agents-layering.md`（勿在 core 重复长文）。
-
 **专题 skill**（规则在各自 `SKILL.md`）：`mstar-phase-gates`、`mstar-branch-worktree`、`mstar-artifacts` 等 — 见上表索引。

package/harness-skills/mstar-host/references/zcode.md

@@ -13,6 +13,7 @@ Parallel PM dispatch: read **`parallel-dispatch.md`** when dispatching **N ≥ 2
 - Plugin commands: repo `commands/` → `/morning-star-harness:<name>` (e.g. `/morning-star-harness:iteration-start`).
 - Plugin agents: repo `agents/*.md` (role frontmatter `name` + **single-line quoted English `description`** — ZCode's flat frontmatter parser cannot read `|-` block scalars and silently drops nested `tools`/`permission` maps). ZCode registers them as callable `subagent_type`s in both bare (`fullstack-dev`) and plugin-qualified (`morning-star-harness:fullstack-dev`) forms (see C5).
 - **No `sessionStart.skill`** (ZCode has no Kimi-style session auto-load) — enter PM manually via **`/morning-star-harness:pm`** or the **`pm`** skill, then **Read next** → `mstar-harness-core` → `project-manager.md`.
+- **Plugin hooks** (`hooks/hooks.json`, ZCode-only surface): **SessionStart** injects harness-workspace context ({HARNESS_DIR} + `status.json` summary) when a harness workspace is detected — a partial substitute for the missing session auto-load; **PreToolUse (Bash)** enforces the `mstar-branch-worktree` gates deterministically (no direct commit on the default protected branch → `MSTAR_ALLOW_DEFAULT_BRANCH_COMMIT=1` escape; no bare `git push --force` → use `--force-with-lease`; disable all with `MSTAR_BRANCH_GUARD=off`). Silent no-op outside git repos / harness workspaces. Skill text stays authoritative; these hooks only backstop it.
 - Install (user-scoped, recommended): `npx @mstar-harness/cli init --target zcode --scope global`, then in ZCode **Settings → Plugin Management → Discover** install **morning-star-harness** from the **mstar-local** marketplace. Direct-add also works without the CLI: the repo ships `.claude-plugin/marketplace.json` (root `marketplace.json` fallback), which ZCode discovers when refreshing a `github`-source marketplace.
 - Plugins are **user-scoped** (all projects); managed copy lives under `~/.zcode/cli/plugins/` after install.
 - Project `.agents/skills/` symlinks are **not** required when using the plugin — commands and skills come from the plugin mount.