@menghuan1918/dsh-apollo 0.3.0 → 0.4.0

package/skills/brainstorming/spec-document-reviewer-prompt.md

@@ -1,8 +1,8 @@
 # Spec Document Reviewer Prompt Template
 
-Use this template when dispatching a spec document reviewer via the `subagent` tool (fresh read-only child, quality tier = the strongest model this session offers; omit provider/model to inherit the parent route).
+Use this template when dispatching a spec document reviewer via the `subagent` tool (fresh read-only child, quality tier).
 
-**Purpose:** Verify a main decomposition spec or child spec is complete, consistent, and ready for implementation.
+**Purpose:** Verify a master Spec or sub-Spec is complete, consistent, and ready for implementation.
 
 **Dispatch after:** Spec document is written to the workspace's spec directory (`.workspace-docs/specs/` where that convention exists, otherwise the target repo's own specs directory).
 
@@ -11,8 +11,8 @@ subagent(
   prompt="You are a spec document reviewer. Verify this spec is complete and ready for implementation.
 
     **Spec to review:** [SPEC_FILE_PATH]
-    **Spec type:** [main decomposition | child]
-    **Main spec, if this is a child spec:** [MAIN_SPEC_FILE_PATH or N/A]
+    **Spec type:** [master | sub]
+    **Master Spec, if this is a sub-Spec:** [MASTER_SPEC_FILE_PATH or N/A]
 
     ## What to Check
 
@@ -22,7 +22,7 @@ subagent(
     | Completeness | TODOs, placeholders, "TBD", incomplete sections |
     | Consistency | Internal contradictions, conflicting requirements |
     | Clarity | Requirements ambiguous enough to cause someone to build the wrong thing |
-    | Scope | Main specs decompose large work into child specs; child specs are independently implementable and do not try to implement the whole main spec |
+    | Scope | Master Specs decompose large work into sub-Specs; sub-Specs are independently implementable and do not try to implement the whole master Spec |
     | YAGNI | Unrequested features, over-engineering |
 
     ## Calibration
@@ -32,7 +32,7 @@ subagent(
     interpreted two different ways — those are issues. Minor wording improvements,
     stylistic preferences, and "sections less detailed than others" are not.
 
-    Approve unless there are serious gaps that would lead to a flawed implementation. Do not reject a main decomposition spec merely because it covers multiple subsystems; reject it only if it lacks clear child specs, ordering, boundaries, or shared contracts. Do not reject a child spec merely because it does not implement the whole main spec.
+    Approve unless there are serious gaps that would lead to a flawed implementation. Do not reject a master Spec merely because it covers multiple subsystems; reject it only if it lacks clear sub-Specs, ordering, boundaries, or shared contracts. Do not reject a sub-Spec merely because it does not implement the whole master Spec.
 
     ## Output Format
 

package/skills/code-review/SKILL.md

@@ -57,7 +57,7 @@ Each smell reads *what it is* → *how to fix*; match it against the diff:
 
 ### 4. Spawn both sub-agents in parallel
 
-Send both `subagent` calls in a single message — each a fresh child (quality tier = the strongest model this session offers; omit provider/model to inherit the parent route) with a fully self-contained prompt; children see none of this conversation.
+Send both `subagent` calls in a single message — each a fresh quality-tier child with a fully self-contained prompt; children see none of this conversation.
 
 **Standards sub-agent prompt** — include:
 

package/skills/dev/SKILL.md

@@ -1,43 +1,41 @@
 ---
 name: dev
-description: "DSH 执行后端的节点契约：实现节点与审查节点的 prompt 要求、报告 schema 与失败语义。"
+description: "Node contract for the DSH execution backend: prompt requirements, report formats, and failure semantics for implementation and review nodes."
 ---
 
-# 内置开发后端（节点契约）
+# Built-in development backend (node contracts)
 
-本技能定义执行后端的两类节点。波次编排（worktree、合并、清理、CR 循环调度）归 `/exec`；本技能不得创建、合并或删除 worktree。子代理没有独立工作目录，也看不到编排会话：节点的一切输入靠 prompt 自带（worktree 绝对路径、Spec 路径、共享契约、验证命令），bash 一律 `workdir`、文件工具一律绝对路径。
+This skill defines the execution backend's two node types. Wave orchestration (worktrees, merging, cleanup, review-loop scheduling) belongs to `/exec`; this skill must not create, merge, or delete worktrees. Subagents have no independent working directory and cannot see the orchestration session: every node input must come with the prompt (absolute worktree path, Spec path, shared contracts, verification commands), with bash always using `workdir` and file tools always using absolute paths.
 
-「质量档」指本会话可用的最强模型；不指定路由时子代理继承父会话的 provider/model，具体档位由调用方的会话配置决定，本技能不写死供应商。
+## Implementation node (develop)
 
-## 实现节点（develop）
+One brand-new subagent (quality tier) handles exactly one sub-Spec, following `main-agent-driven-development` in prebuilt-worktree mode (in an `/exec` wave, skip its internal review step — the review loop is run by `/exec`, and nodes do not dispatch reviewers themselves).
 
-一个全新子代理（质量档）处理恰好一个子 Spec，以预建 worktree 模式遵循 `main-agent-driven-development`（在 `/exec` 的 workflow 波次中跳过其内部 CR 步骤——CR 循环由编排脚本承担，节点不自行派 reviewer）。
-
-报告 schema（结构化输出）：
+Report format (JSON code block at the end of the closing message):
 
 ```js
 {
   status: 'complete' | 'blocked',
-  commit: '<最终 commit SHA>',
-  verification: '<本轮已跑的验证命令与结果>',
-  summary: '<实现摘要，供 reviewer 与编排器使用>',
-  blocker: '<status=blocked 时必填>'
+  commit: '<final commit SHA>',
+  verification: '<verification commands run this round and their results>',
+  summary: '<implementation summary for the reviewer and orchestrator>',
+  blocker: '<required when status=blocked>'
 }
 ```
 
-## 审查节点（review-only）
+## Review node (review-only)
 
-全新只读子代理（质量档）。prompt 自带：worktree 绝对路径、diff 范围、Spec 路径、实现摘要、已跑验证。四态判定 schema：
+A brand-new read-only subagent (quality tier). The prompt supplies: absolute worktree path, diff range, Spec path, implementation summary, and verification already run. Four-state verdict format (JSON code block at the end of the closing message):
 
 ```js
 {
   status: 'APPROVED' | 'APPROVED_WITH_NOTES' | 'CHANGES_REQUIRED' | 'BLOCKED',
-  findings: ['<问题，附文件与行号>']
+  findings: ['<issue, with file and line number>']
 }
 ```
 
-严重正确性错误、Spec 缺口、集成风险、安全问题或缺失验证必须 `CHANGES_REQUIRED`。不得编辑、提交、合并。
+Serious correctness errors, Spec gaps, integration risks, security issues, or missing verification must yield `CHANGES_REQUIRED`. Do not edit, commit, or merge.
 
-## 失败语义
+## Failure semantics
 
-子代理失败（error / 空返回）= `node-failed`；`blocked`、超时、部分回复或未提交的结果均不得视为完成。调用方决定重派，或仅在对同一子 Spec 解除阻塞时用 `send_message` 续谈。不得复用节点处理其他子 Spec。
+A subagent failure (error / empty return) = `node-failed`; `blocked`, timeouts, partial replies, or uncommitted results never count as complete. The caller decides whether to redispatch, or to continue via `send_message` only when unblocking the same sub-Spec. Never reuse a node for another sub-Spec.

package/skills/exec/SKILL.md

@@ -1,91 +1,78 @@
 ---
 name: exec
-description: "当用户调用 /exec 并提供已批准的主 Spec 时使用。负责编排逐 Spec worktree、波次 workflow 执行、合并、验证和最终代码审查。"
+description: "Use when the user invokes /exec with an approved master Spec. Orchestrates per-Spec worktrees, wave-parallel subagent execution, merging, verification, and final review."
 ---
 
-# 执行多 Spec 任务
-
-在目标仓库的 `.worktrees/` 隔离 worktree 中执行已批准的子 Spec。主工作区始终是合入目标；编排状态只保存在当前会话上下文中。
-
-## 前置条件
-
-- 主 Spec 索引至少两个子 Spec。
-- 确认唯一目标仓库；主工作区位于命名分支且工作树干净。
-- `.worktrees/` 已被目标仓库 `.gitignore` 覆盖；没有就先提示用户加入。
-
-## 执行
-
-1. 读取主 Spec 和全部子 Spec，确认共享契约、依赖 DAG、验证命令。
-2. 按依赖波次创建任务列表。
-3. 每波：从主工作区 HEAD 建分支，在 `<repo>/.worktrees/exec-<任务>/<子任务>` 建 worktree，再派遣整波节点。前置波全部合入后才创建下一波 worktree。
-
-## 波次执行：workflow 驱动
-
-每波恰好一次 `workflow` 工具调用：脚本只做波内扇出与 CR 循环——worktree 创建、合并、清理全在主线程（workflow 引擎无文件系统，脚本碰不了 git）。节点契约（prompt 要素、schema、失败语义）见 `dev` skill。本波 specs 经 workflow 的 `args` 传入，每个元素带具体值：`{ id, specPath, worktree, contracts, verify }`（`worktree` 为绝对路径）。
-
-```js
-const specs = args.specs
-// 质量档 = 本会话可用的最强模型。留空即不覆盖路由：子代理继承父会话的
-// provider/model，任何环境都能跑。有固定质量档时只改这一处，例如：
-// const quality = { provider: '<provider>', model: '<model>' }
-const quality = {}
-const implSchema = { type: 'object', required: ['status', 'commit', 'verification', 'summary'], properties: { status: { type: 'string', enum: ['complete', 'blocked'] }, commit: { type: 'string' }, verification: { type: 'string' }, summary: { type: 'string' }, blocker: { type: 'string' } }, additionalProperties: false }
-const verdictSchema = { type: 'object', required: ['status', 'findings'], properties: { status: { type: 'string', enum: ['APPROVED', 'APPROVED_WITH_NOTES', 'CHANGES_REQUIRED', 'BLOCKED'] }, findings: { type: 'array', items: { type: 'string' } } }, additionalProperties: false }
-const implPrompt = (s) => `你在隔离 worktree ${s.worktree} 中工作：bash 一律 workdir=${s.worktree}，文件工具用绝对路径。以预建 worktree 模式遵循 main-agent-driven-development skill（跳过其内部 CR 步骤，CR 由本编排循环承担，节点不自行派 reviewer）。只实现 ${s.specPath} 的子 Spec，遵守共享契约：${s.contracts}。运行验证：${s.verify}。提交后按 schema 报告。不得合入或删除 worktree；阻塞时 status=blocked 并填 blocker。`
-const reviewPrompt = (s, impl) => `只读审查 worktree ${s.worktree} 相对基线的完整 diff（bash 一律 workdir=${s.worktree}）。Spec：${s.specPath}。实现摘要：${impl.summary}。已跑验证：${impl.verification}。按严重度列出问题，每条附文件与行号；按 schema 四态判定。不得编辑、提交、合并。`
-const fixPrompt = (s, impl, verdict) => `你在隔离 worktree ${s.worktree} 中继续前人的实现（bash 一律 workdir=${s.worktree}，文件工具用绝对路径）。此前摘要：${impl.summary}（commit ${impl.commit}）。reviewer 发现：${verdict.findings.join('；')}。逐条修复真实问题，对误报在 summary 中给出理由；重跑验证：${s.verify}；提交后按 schema 报告。不得合入。`
-log(`wave: dispatching ${specs.length} spec(s)`)
-return await parallel(specs.map((s) => async () => {
-  let impl = await agent(implPrompt(s), { label: `${s.id}-impl`, schema: implSchema, ...quality })
-  if (!impl || impl.status !== 'complete') return { spec: s.id, status: 'node-failed', impl }
-  let verdict = await agent(reviewPrompt(s, impl), { label: `${s.id}-cr-1`, schema: verdictSchema, ...quality })
-  let round = 1
-  while (verdict && verdict.status === 'CHANGES_REQUIRED' && round < 5) {
-    impl = await agent(fixPrompt(s, impl, verdict), { label: `${s.id}-fix-${round}`, schema: implSchema, ...quality })
-    if (!impl || impl.status !== 'complete') return { spec: s.id, status: 'fix-failed', round }
-    round += 1
-    verdict = await agent(reviewPrompt(s, impl), { label: `${s.id}-cr-${round}`, schema: verdictSchema, ...quality })
-  }
-  return { spec: s.id, status: verdict ? verdict.status : 'review-failed', rounds: round, impl, verdict }
-}))
-```
+# Execute multi-Spec tasks
+
+Run approved sub-Specs in isolated worktrees under `.worktrees/` in the target repo. The main workspace is always the merge target; orchestration state lives only in the current session context.
+
+## Prerequisites
+
+- The master Spec indexes at least two sub-Specs.
+- Confirm a single target repo; the main workspace is on a named branch and its working tree is clean.
+- `.worktrees/` is covered by the target repo's `.gitignore`; if not, ask the user to add it first.
+
+## Execution
+
+1. Read the master Spec and all sub-Specs; confirm shared contracts, dependency DAG, and verification commands.
+2. Build the task list by dependency wave.
+3. Per wave: create a branch from the main workspace HEAD, create a worktree at `<repo>/.worktrees/exec-<task>/<subtask>`, then dispatch the whole wave of nodes. Create the next wave's worktrees only after every prior wave has merged.
+
+## Wave execution: subagent + wait_subagent
+
+The main agent orchestrates each wave; node contracts (prompt elements, report format, failure semantics) are in the `dev` skill.
+
+1. **Dispatch**: in a single message, call `subagent` once per sub-Spec in this wave (quality tier), and record "Spec → subagent id". Implementation-node prompt template:
+
+   ```
+   You work in the isolated worktree <worktree absolute path>: always run bash with workdir=<worktree>, and use absolute paths for file tools.
+   Follow the main-agent-driven-development skill in prebuilt-worktree mode (skip its internal review step; the review loop is run by /exec).
+   Implement only <sub-Spec path> and obey the shared contracts: <contracts>. Run verification: <verification command>.
+   After committing, report in the dev skill's implementation-node format. Do not merge or delete the worktree; if blocked, set status=blocked and fill in blocker.
+   ```
+
+2. **Collect**: pass every id in this wave to `wait_subagent` in one call; reports arrive with the settlement notice. A Spec with a missing report, `blocked`, or no commit is recorded as `node-failed` and does not affect the other Specs in the wave.
+3. **Review loop** (each completed Spec advances independently; batches may be dispatched in parallel):
+   - Dispatch a brand-new read-only reviewer (quality tier): `Read-only review of the full diff of worktree <worktree> against the baseline (always run bash with workdir=<worktree>). Spec: <path>. Implementation summary: <summary>. Verification already run: <verification>. List issues by severity, each with file and line number; judge with the dev skill's four-state format. Do not edit, commit, or merge.`
+   - `CHANGES_REQUIRED` → send the findings to the original implementation subagent with `send_message` (preserving its context), and require it to fix each real issue, explain false positives, rerun verification, commit, and report again; then `wait_subagent` and dispatch a brand-new reviewer.
+   - At most 5 rounds; if still failing, record `review-exhausted`.
+4. Only Specs judged `APPROVED` / `APPROVED_WITH_NOTES` proceed to merge.
 
-要点：
+Key points:
 
-- CR 循环是代码不是纪律：每轮全新 reviewer（`agent()` 一次一代理）、schema 校验判定、5 轮熔断。
-- 子代理失败 resolve `null` → 该 Spec 记 `node-failed`，`parallel` 等整波，单个失败不拖垮其他 Spec。
-- 质量档（本会话最强模型）在脚本顶部一处定义，impl / review / fix 节点全部使用；留空则由子代理继承父会话路由。
-- 调用前台阻塞至整波结束，波内无人工交互；节点的疑问一律按 blocked 上报，由主线程处置。
-- 返回值是结构化波次报告：只有 `status` 为 `APPROVED` / `APPROVED_WITH_NOTES` 的 Spec 进入合并。
+- Every review round uses a brand-new subagent; fixes reuse the original implementation subagent — never start another implementation node for the same Spec.
+- Report any node question as blocked for the main agent to handle; do not ask the user within a wave.
+- In PTC mode, a whole wave's dispatch and collection can be done in one `run_code`.
 
-## 合并
+## Merge
 
-对每个完成节点：确认已提交且验证通过 → 检查变更文件排除越界 → 合入主工作区 → 合并后验证 → 删除 worktree 和子分支。
+For each completed node: confirm it is committed and verification passed → check the changed files for out-of-scope edits → merge into the main workspace → verify after merging → delete the worktree and sub-branch.
 
-小而明确的冲突由主代理直接解决。复杂冲突用 `.worktrees/` 下新的修复 worktree 和开发节点。不得合并失败或阻塞的节点。
+Small, well-defined conflicts are resolved directly by the main agent. For complex conflicts, use a new fix worktree under `.worktrees/` and a development node. Never merge failed or blocked nodes.
 
-## 最终审查
+## Final review
 
-所有子 Spec 合入后，运行完整集成验证，然后派遣一个全新只读 reviewer 子代理（质量档 = 本会话最强模型）审查全量集成结果：
+Once all sub-Specs are merged, run the full integration verification, then dispatch a brand-new read-only reviewer subagent (quality tier) to review the whole integrated result:
 
 ```
 subagent(
-  prompt="只读审查 <workspace> 的 <base>..HEAD diff（bash 一律 workdir=<workspace>）。
-         主 Spec: <path> | 全部子 Spec | 共享契约 | 变更文件 | 实现摘要 | 验证结果。
-         按严重度列出问题，每条附文件与行号。
-         返回 APPROVED / APPROVED_WITH_NOTES / CHANGES_REQUIRED / BLOCKED。不得编辑、提交、合并。"
+  prompt="Read-only review of the <base>..HEAD diff in <workspace> (always run bash with workdir=<workspace>).
+         Master Spec: <path> | all sub-Specs | shared contracts | changed files | implementation summary | verification results.
+         List issues by severity, each with file and line number.
+         Return APPROVED / APPROVED_WITH_NOTES / CHANGES_REQUIRED / BLOCKED. Do not edit, commit, or merge."
 )
 ```
 
-用 `wait_subagent` 等待。`CHANGES_REQUIRED` 时不需要询问用户——主代理直接分类并修复所有真实 bug，对误报和既有行为在上下文中简述理由；修复后重新验证，再派全新 reviewer 复审。软熔断 3 轮后仍存在严重或阻塞问题则停止修复循环，如实向用户报告剩余问题。
+Wait with `wait_subagent`. On `CHANGES_REQUIRED` there is no need to ask the user — the main agent classifies and fixes all real bugs directly, and briefly explains false positives and existing behavior in context; after fixing, verify again and dispatch a brand-new reviewer for re-review. If serious or blocking issues remain after a soft cap of 3 rounds, stop the fix loop and truthfully report the remaining issues to the user.
 
-## 收尾
+## Wrap-up
 
-运行完整验证，核对 Spec，报告分支、提交、验证结果和遗留问题，询问用户下一步。未经用户选择不得创建 PR 或删除分支。
+Run the full verification, check the Specs, report branches, commits, verification results, and open issues, and ask the user what to do next. Do not create a PR or delete branches without the user's choice.
 
 ## KISS
 
-- 一个子 Spec、一个 worktree、一个开发节点。
-- 主线程只持仓库拓扑（分支/worktree/合并/清理）；波内扇出交给一次 workflow 调用。
-- 状态只保存在会话上下文；不增加集成分支、调度脚本或状态文件。
-- 等待靠完成通知自动送达，需要结果才继续时再等待。不得用 `sleep` 轮询。
+- One sub-Spec, one worktree, one development node.
+- The main agent holds repo topology (branches/worktrees/merges/cleanup) and in-wave scheduling; implementation and review go to subagents.
+- State lives only in session context; add no integration branch, scheduler scripts, or state files.
+- Completion notices arrive automatically; wait only when you need results to proceed. Never poll with `sleep`.

package/skills/handoff/SKILL.md

@@ -1,23 +1,23 @@
 ---
 name: handoff
-description: 把当前对话压缩成一份交接文档，供下一个全新 agent 接续。
-argument-hint: "下一个会话将用来做什么？"
+description: Compress the current conversation into a handoff document for a fresh agent to continue from.
+argument-hint: "What will the next session be used for?"
 disable-model-invocation: true
 ---
 
-把当前对话压缩成一份交接文档，让全新 agent 无需重读父会话即可接续工作。
+Compress the current conversation into a handoff document, so a brand-new agent can pick up the work without re-reading the parent session.
 
-## 存放与复用
+## Storage and reuse
 
-- **已有则复写**：若会话上下文中已存在交接文档（本会话早前写过，或会话开启时注入了一份），整篇重写该文件，不新建。
-- **否则新建**：工作区有 `.workspace-docs/` 时写 `.workspace-docs/notes/<仓库或主题>/`，交接本质上就是一篇 note；否则写目标仓库现有的文档目录。文件名带日期前缀，沿用目录内现有命名风格。
-- 写入 `.workspace-docs/` 时新建文件带 OKF 头（`type: Note` 及 `title`/`description`/`tags`/`status`/`repos`），不登记 `index.md`；提交/推送遵循该仓库既有纪律。目标仓库无此约定时用其现有文档格式。
-- 两个位置都不存在时，回退写 OS 临时目录。
+- **Rewrite if one exists**: if a handoff document is already in the session context (written earlier in this session, or injected when the session started), rewrite that file in full; do not create a new one.
+- **Otherwise create one**: when the workspace has `.workspace-docs/`, write to `.workspace-docs/notes/<repo-or-topic>/` — a handoff is essentially a note; otherwise write to the target repo's existing docs directory. Prefix the file name with the date and follow the naming style already used in that directory.
+- When writing under `.workspace-docs/`, new files carry an OKF header (`type: Note` plus `title`/`description`/`tags`/`status`/`repos`), and are not registered in `index.md`; commit/push follows that repo's existing discipline. Where the target repo has no such convention, use its existing doc format.
+- If neither location exists, fall back to the OS temp directory.
 
-## 内容要求
+## Content requirements
 
-- 含「建议技能」一节，提示接手 agent 应调用的技能。
-- 不复述已落盘物（spec、plan、ADR、issue、commit、diff）的内容，只给路径或 URL。
-- 只写客观事实与验证证据，不写自我免责叙事。
-- 脱敏 API key、密码、个人身份信息等敏感内容。
-- 用户带参数调用时，参数即下一会话焦点，据此裁剪文档。
+- Include a "Suggested skills" section pointing the receiving agent at the skills it should invoke.
+- Do not restate content already on disk (spec, plan, ADR, issue, commit, diff); give paths or URLs only.
+- Record only objective facts and verification evidence; no self-justifying narrative.
+- Redact sensitive content such as API keys, passwords, and personal identity information.
+- When the user invokes it with an argument, that argument is the next session's focus; trim the document accordingly.

package/skills/main-agent-driven-development/SKILL.md

@@ -1,39 +1,39 @@
 ---
 name: main-agent-driven-development
-description: "仅当用户或编排技能显式调用 /main-agent-driven-development 来完成一个边界明确的实现任务时使用。"
+description: "Use only when the user or an orchestration skill explicitly invokes /main-agent-driven-development to complete a well-bounded implementation task."
 ---
 
-# 主代理驱动开发
+# Main-agent-driven development
 
-由当前 Agent 会话直接实现一个边界明确的 Spec。外层 `/exec` 编排器负责 worktree 和合入生命周期。
+The current agent session implements a well-bounded Spec directly. The outer `/exec` orchestrator owns the worktree and merge lifecycle.
 
-## Worktree 模式
+## Worktree modes
 
-只选一种：
+Choose exactly one:
 
-- **预建模式** — 调用方已提供隔离 worktree 并声明负责生命周期时，直接使用；不得创建、合并或删除 worktree。
-- **独立模式** — 否则识别目标仓库，要求基线位于命名分支，记录起始 SHA，在仓库 `.worktrees/` 下创建 worktree。
+- **Prebuilt mode** — when the caller already provided an isolated worktree and owns its lifecycle, use it directly; do not create, merge, or delete worktrees.
+- **Standalone mode** — otherwise, identify the target repo, require the baseline to be on a named branch, record the starting SHA, and create a worktree under the repo's `.worktrees/`.
 
-所有操作必须在选定 worktree 内完成。隔离后不得编辑原始 checkout。
+All operations must happen inside the chosen worktree. After isolation, do not edit the original checkout.
 
-## 流程
+## Flow
 
-1. 读取分配的 Spec 及相关仓库指令。
-2. 确认任务边界、依赖、验收标准和必要验证。只有缺失决策真正阻塞实现时才提问。
-3. 根据 Spec 初始化任务列表。
-4. 项目初始化 + 基线验证。基线失败时先报告；仅当失败明确无关且已记录时才继续。
-5. 直接实现，限定在 Spec 范围。遵循 `tdd` skill（本包已捆绑）：先写失败测试，再写最小实现。
-6. 每个逻辑步骤后运行聚焦验证、自审 diff，内容完整时提交。验证标准：本轮运行命令并确认输出，不得以"应该通过"代替实际运行。
-7. 实现完成后运行全部必要验证。
-8. 验证失败或 CR 发现 bug 时，遵循 `diagnosing-bugs` skill（本包已捆绑）：先建反馈循环找根因，再修复。
-9. 执行内部 CR 循环（见下文）。例外：作为 `/exec` dev 后端 workflow 波次中的实现节点时，**跳过本步**——CR 循环由编排脚本承担，节点只实现、验证、提交、报告。
-10. 提交全部已批准修复，向调用方报告。
+1. Read the assigned Spec and the relevant repo instructions.
+2. Confirm task boundaries, dependencies, acceptance criteria, and required verification. Ask questions only when a missing decision truly blocks implementation.
+3. Initialize the task list from the Spec.
+4. Project setup + baseline verification. Report first if the baseline fails; continue only when the failure is clearly unrelated and documented.
+5. Implement directly, limited to the Spec's scope. Follow the `tdd` skill (bundled in this package): write a failing test first, then the minimal implementation.
+6. After each logical step, run focused verification, self-review the diff, and commit when it is complete. Verification standard: run the command this round and confirm the output; never replace it with "it should pass".
+7. After implementation, run all required verification.
+8. When verification fails or review finds a bug, follow the `diagnosing-bugs` skill (bundled in this package): build a feedback loop to find the root cause first, then fix.
+9. Run the internal review loop (see below). Exception: when acting as an implementation node in an `/exec` wave, **skip this step** — the review loop is run by `/exec`, and the node only implements, verifies, commits, and reports.
+10. Commit all approved fixes and report to the caller.
 
-保持 KISS。优先复用既有模式，小而完整的修改，只做 Spec 必需的针对性重构。
+Keep it KISS. Prefer reusing existing patterns, small and complete changes, and only the targeted refactoring the Spec requires.
 
-## 内部 CR 循环
+## Internal review loop
 
-完整验证后，派遣恰好一个全新只读 reviewer 子代理（质量档 = 本会话最强模型）：
+After full verification, dispatch exactly one brand-new read-only reviewer subagent (quality tier):
 
 ```
 subagent(
@@ -45,20 +45,20 @@ subagent(
 )
 ```
 
-要求附文件和行号，返回一种状态：`APPROVED` / `APPROVED_WITH_NOTES` / `CHANGES_REQUIRED` / `BLOCKED`。
+Require file and line numbers, and one status: `APPROVED` / `APPROVED_WITH_NOTES` / `CHANGES_REQUIRED` / `BLOCKED`.
 
-用 `wait_subagent` 等待审查完成。收到结果后直接修复所有必要的正确性错误、Spec 缺口、安全问题、集成风险和验证缺口——不需要询问用户。验证并提交修复后，再用 `subagent` 派遣全新 reviewer。重复直到 `APPROVED` 或仅含非阻塞建议。
+Wait for the review with `wait_subagent`. Once results arrive, fix all necessary correctness errors, Spec gaps, security issues, integration risks, and verification gaps directly — no need to ask the user. After verifying and committing the fixes, dispatch a brand-new reviewer with `subagent` again. Repeat until `APPROVED` or only non-blocking suggestions remain.
 
-不得自我批准，不得复用旧 reviewer。
+Never self-approve, and never reuse an old reviewer.
 
-## 完成契约
+## Completion contract
 
-报告完成前必须满足：
+Before reporting completion, all of the following must hold:
 
-- 所有分配的验收标准已实现
-- 必要验证已在本轮运行并通过（有命令输出为证）
-- 没有未提交的实现修改
-- 内部 CR 已通过且无必要修复项
-- 可提供最终 commit SHA
+- All assigned acceptance criteria are implemented
+- Required verification ran and passed this round (backed by command output)
+- No uncommitted implementation changes
+- Internal review passed with no required fixes
+- The final commit SHA is available
 
-如实报告阻塞。不得自行合入；调用方负责集成和清理。
+Report blockers truthfully. Do not merge on your own; the caller owns integration and cleanup.

package/src/cli-adapter.js

@@ -16,7 +16,7 @@ export function enabledIn(config, agent) {
     const projections = agent?.ctx?.get?.('sessionProjections')
     if (projections) preset = projections.stateOf(agent.session, 'agentPreset') ?? preset
   } catch { /* Compositions without the optional preset registry use the header. */ }
-  return scope.global || (scope.eng && ['eng', 'eng-noask'].includes(preset))
+  return scope.global || (scope.eng && ['eng', 'eng-ptc'].includes(preset))
 }
 
 /** Exact checks are repeated before every CLI turn, including cold resume. */