@boyingliu01/opencode-plugin 0.17.0 → 0.18.1

package/skills/sprint-flow/SKILL.md

@@ -3,7 +3,7 @@ name: sprint-flow
 version: 2.1.0
 description: >
   Orchestrates a 6-phase end-to-end feature development pipeline (PREP → DESIGN → BUILD → VERIFY → SHIP → CLOSE).
-  Integrates brainstorming, autoplan, delphi-review, TDD, ralph-loop, code-walkthrough, ship, and other skills.
+  Integrates grill-with-docs, batch-grill-me, delphi-review (R1 requirements + R2 design), TDD, ralph-loop, code-walkthrough, and native ship/land steps.
   Pauses at key gates for user decisions. Acknowledges emergent requirements with mandatory manual UAT in CLOSE phase.
 
   WHAT: Automates the full development lifecycle from worktree isolation to production deployment.
@@ -87,12 +87,10 @@ workflow_steps:
   - "Phase 6/6: CLOSE → Output: ## Phase 6/6: CLOSE (收尾)"
 hooks:
   security:
-    - "/careful": "Safety guardrails for destructive commands — activate before any rm, force-push, or git reset"
-    - "/freeze": "Restrict edits to sprint worktree directory — prevent accidental changes outside scope"
-    - "/guard": "Full safety mode combining careful + freeze for maximum protection"
+    - "tools_denied": "Destructive commands blocked via tools_denied (rm -rf, git push --force, DROP TABLE)"
+    - "Security Notes": "See Security Notes section for safety guarantees"
   operational:
-    - "/context-save": "Save sprint context before pause or handoff"
-    - "/context-restore": "Restore sprint context on resume"
+    - "sprint-state.json": "Native sprint state persistence + --resume-from for context restore"
 tools_allowed:
   - "Bash(git, gh, npm, node)"  # git worktree/branch/commit, gh PR/release, npm/node CLI
   - "Read"                       # read project files, configs, docs
@@ -101,7 +99,7 @@ tools_allowed:
   - "Glob"                       # find project files by pattern
   - "Grep"                       # search file contents
   - "Task"                       # delegate to subagents (quick, deep, unspecified-high)
-  - "Skill"                      # invoke integrated skills (brainstorming, autoplan, delphi-review, etc.)
+  - "Skill"                      # invoke integrated skills (grill-with-docs, batch-grill-me, delphi-review, to-issues, etc.)
   - "TodoWrite"                  # track sprint progress
   - "Question"                   # ask user at decision gates
 tools_denied:
@@ -167,15 +165,15 @@ PREP → DESIGN → BUILD → VERIFY → SHIP → CLOSE
 | Phase | Name | Key Actions | Output |
 |-------|------|-------------|--------|
 | 1/6 | PREP | Detect protected branch → Create git worktree → AUTO-ESTIMATE sizing → Classify (lightweight/standard/complex) | Worktree path + impact assessment |
-| 2/6 | DESIGN | CONTEXT.md 预检 (#322) → brainstorming (如需要) → autoplan → delphi-review (HARD-GATE ≥90% consensus) → to-issues → specification.yaml | specification.yaml + slices-manifest.json |
-| 3/6 | BUILD | GITHOOKS-GATE → DELPHI-GATE → ralph-loop (default) or parallel → TDD → freeze → blind review → verification | MVP code |
-| 4/6 | VERIFY | delphi-review --mode code-walkthrough → test-specification-alignment → browse QA → learn + retro | Review report + feedback-log.md |
-| 5/6 | SHIP | VERSION-GATE → finishing-a-development-branch → ship (create PR) → land-and-deploy → merge to main + CI + canary | PR URL + deploy status + merge confirmation |
-| 6/6 | CLOSE | SHIP→CLOSE GATE (merge verified) → Backup sprint-state → USER ACCEPTANCE (⚠️ mandatory manual) → Capture emergent issues → Cleanup worktree + branch | Emergent issues list + cleanup report |
+| 2/6 | DESIGN | CONTEXT.md 预检 (#322) → grill-with-docs → R1 需求评审 → 设计文档+APPROVAL (HARD-GATE) → batch-grill-me → R2 delphi-review (≥90% consensus) → to-issues → specification.yaml | specification.yaml + slices-manifest.json + requirements-reviewed.json |
+| 3/6 | BUILD | BUILD-ENTRY-CONTRACT → GITHOOKS-GATE → DELPHI-GATE → ralph-loop (default) or parallel → TDD → blind-review (read-only subagent) → verification | MVP code |
+| 4/6 | VERIFY | delphi-review --mode code-walkthrough → test-specification-alignment (#367 HARD-GATE) → xp-gate check --all → browser (Layer 4) → learnings + xp-gate retro | Review report + feedback-log.md + test-alignment-report.json |
+| 5/6 | SHIP | VERSION-GATE → 分支完成决策 (4选项) → native ship (create PR) → native land (merge + CI + canary) | PR URL + deploy status + merge confirmation |
+| 6/6 | CLOSE | SHIP→CLOSE GATE (merge verified) → Backup sprint-state → #369 返工指标 → USER ACCEPTANCE (⚠️ mandatory manual) → Capture emergent issues → Cleanup worktree + branch | Emergent issues list + cleanup report + metrics |
 
 **Hard Gates**:
-- **DESIGN → BUILD**: Design must be APPROVED by delphi-review (≥90% consensus) + GITHOOKS-GATE + DELPHI-GATE
-- **VERIFY → SHIP**: feedback-log.md must exist (HARD-GATE)
+- **DESIGN → BUILD**: R1 需求评审 APPROVED + 设计文档用户 APPROVED + R2 delphi-review APPROVED (≥90% consensus) + GITHOOKS-GATE + DELPHI-GATE + BUILD-ENTRY-CONTRACT (manifest schema + slice↔REQ)
+- **VERIFY → SHIP**: feedback-log.md must exist + test-alignment-report.json PASS (#367 程序化 HARD-GATE)
 - **SHIP → CLOSE**: PR must be merged to main + release completed (HARD-GATE)
 
 ---
@@ -282,9 +280,11 @@ next_phase_context: [key info for next phase]
 
 | 门禁 | 位置 | 条件 | 失败处理 |
 |------|------|------|----------|
+| BUILD-ENTRY-CONTRACT | Phase 2→3 | slices-manifest.json schema 合法 + slice↔REQ 一致 | BLOCK，返回 Phase 2 修复 |
 | GITHOOKS-GATE | Phase 2→3 | hooks 已安装且可执行 | 自动修复 (`xp-gate doctor --fix`)，失败则 BLOCK |
-| DELPHI-GATE | Phase 2→3 | delphi-review APPROVED (≥90%) | 重新设计或用户覆盖（记录原因） |
+| DELPHI-GATE | Phase 2→3 | R2 delphi-review APPROVED (≥90%) | 重新设计或用户覆盖（记录原因） |
 | VERSION-GATE | Phase 4→5 | VERSION 文件与 package.json 一致 | 执行 `node scripts/sync-version.cjs` |
+| #367 EVIDENCE-GATE | Phase 4→5 | test-alignment-report.json PASS + head_commit + spec_hash | BLOCK（--skip-evidence 需 --reason，≤2 次/sprint） |
 | SHIP→CLOSE GATE | Phase 5→6 | PR 已合并 + release 完成 | BLOCK，等待合并确认 |
 | feedback-log GATE | Phase 4→5 | feedback-log.md 存在 | BLOCK，必须完成 VERIFY |
 
@@ -296,11 +296,11 @@ next_phase_context: [key info for next phase]
 
 | Phase | 参考文件 | 核心 Skill 链 |
 |-------|----------|---------------|
-| 2/6 DESIGN | `@references/phase-2-design.md` | CONTEXT.md 预检 → brainstorming → autoplan → delphi-review → to-issues |
-| 3/6 BUILD | `@references/phase-3-build.md` | GITHOOKS-GATE → DELPHI-GATE → ralph-loop (TDD) → freeze → blind review |
-| 4/6 VERIFY | `@references/phase-4-verify.md` | delphi code-walkthrough → test-spec-alignment → browse QA → retro |
-| 5/6 SHIP | `@references/phase-5-ship.md` | VERSION-GATE → finishing-branch → ship (PR) → land-and-deploy → merge |
-| 6/6 CLOSE | `@references/phase-6-close.md` | SHIP→CLOSE GATE → backup → USER ACCEPTANCE → emergent → cleanup |
+| 2/6 DESIGN | `@references/phase-2-design.md` | CONTEXT.md 预检 → grill-with-docs → R1 需求评审 → 设计文档+APPROVAL → batch-grill-me → R2 delphi-review → to-issues |
+| 3/6 BUILD | `@references/phase-3-build.md` | BUILD-ENTRY-CONTRACT → GITHOOKS-GATE → DELPHI-GATE → ralph-loop (TDD) → blind-review (read-only subagent) |
+| 4/6 VERIFY | `@references/phase-4-verify.md` | delphi code-walkthrough → test-spec-alignment (#367) → xp-gate check --all → browser (Layer 4) → learnings + retro |
+| 5/6 SHIP | `@references/phase-5-ship.md` | VERSION-GATE → 分支完成决策 (4选项) → native ship (PR) → native land (merge+CI+canary) |
+| 6/6 CLOSE | `@references/phase-6-close.md` | SHIP→CLOSE GATE → backup → #369 返工指标 → USER ACCEPTANCE → emergent → cleanup |
 
 **路径约定**：`@references/` 和 `@templates/` 相对于 skill 目录（`skills/sprint-flow/`）解析。
 
@@ -321,7 +321,7 @@ next_phase_context: [key info for next phase]
 | Route Q&A, explanation, or code-search requests to sprint-flow | Only trigger for explicit feature development/implementation requests |
 | Skip Phase 1/6 PREP isolation, edit directly on main/master/develop | Default: create worktree; only bypass with `--no-isolate` or `--force` + user confirmation |
 | Skip AUTO-ESTIMATE and apply full heavy pipeline blindly | Evaluate lightweight/standard/complex first, follow recommended or user-confirmed flow |
-| Skip Delphi review in DESIGN, go straight to BUILD | All requirement levels (lightweight/standard/complex) must pass autoplan + delphi-review; APPROVED before coding |
+| Skip Delphi review in DESIGN, go straight to BUILD | All requirement levels (lightweight/standard/complex) must pass R1 需求评审 + R2 delphi-review; APPROVED before coding |
 | Skip TDD, implement code directly | Phase 3/6 BUILD must follow RED → GREEN → REFACTOR; tests and implementation delivered together |
 | Skip user acceptance, go straight to Ship | Phase 6/6 CLOSE USER ACCEPTANCE must be manual; never automate, skip, or fake |
 | Enter CLOSE without SHIP completing merge to main | Phase 5/6 SHIP must complete merge to main + release before entering Phase 6/6 CLOSE; otherwise worktree cleanup leaves residue + UAT reviews unmerged code |
@@ -408,4 +408,4 @@ stateDiagram-v2
 
 ## 底层 Skills 保持独立
 
-所有被调用的 Skills 独立可用：`delphi-review` (单独评审), `test-driven-development` (TDD)，sprint-flow 仅自动串联
+所有被调用的 Skills 独立可用：`delphi-review` (单独评审), `test-driven-development` (TDD), `grill-with-docs` (需求访谈), `batch-grill-me` (批量决策), `to-issues` (切片拆分)，sprint-flow 仅自动串联

package/skills/sprint-flow/references/components/memory.md

@@ -73,7 +73,7 @@ ralph-loop 内部分类:
 - `permanent`: 跨 REQ 持久化（通用约束、模式）
 - `contextual`: 当前 REQ 生命周期内有效
 
-gstack/learn 调用分类: permanent / contextual 通过 progress.log 持久化。
+learnings.md 写入分类: permanent / contextual 通过 `.sprint-history/learnings.md` 持久化（原生，替代原 gstack/learn）。
 
 ---
 

package/skills/sprint-flow/references/components/middleware.md

@@ -61,7 +61,7 @@ Phase 6: SHIP → finishing-a-development-branch → canary → Sprint Summary
 | `CIRCUIT_BREAKER_TRIGGERED` | sprint-flow 编排层监控成本，超阈值 BLOCK + 用户决策 |
 | `ROLLBACK_TO_ROUND1` | verification-before-completion 失败 → 修复 max 3 次 → 仍失败 BLOCK |
 | `GATE1_FAILED`/`GATE1_COMPLETE` | verification-before-completion 内置此区分 |
-| `GATE2_RUNNING` | `cso` (gstack) — Phase 1-6 安全审计 |
+| `GATE2_RUNNING` | `xp-gate check --all`（Gate 7/8/9）— Phase 1-6 安全审计 |
 
 ---
 

package/skills/sprint-flow/references/components/skill-invocations.md

@@ -15,15 +15,17 @@
 
 | Skill | 来源 | 触发条件 | 输出 |
 |-------|------|---------|------|
-| `brainstorming` | superpowers | 无条件（首个 Skill） | 结构化设计文档 |
+| `grill-with-docs` | Matt Pocock (内置) | CONTEXT.md 不存在时（首个 Skill） | 访谈记录 + CONTEXT.md + ADR |
+| `delphi-review --mode requirements` | xp-gate | R1 需求评审（轻量 2 专家 1 轮） | requirements-reviewed.json |
+| 原生设计文档生成 | sprint-flow 编排层 | R1 APPROVED 后 | docs/plans/YYYY-MM-DD-<topic>-design.md |
 | **硬闸门** | — | 设计未批准 → 停止 | 禁止进入 Plan |
 
 ### Phase 1: PLAN
 
 | Skill | 来源 | 触发条件 | 条件分支 |
 |-------|------|---------|---------|
-| `autoplan` | gstack | 进入 Phase 1 自动调用 | 输出 AUTO_APPROVED 或 NEEDS_REVIEW |
-| `delphi-review` | xp-gate | Phase 1 强制调用；AUTO_APPROVED + 无 taste_decisions 使用 lightweight delphi-review | 必须产生 `.sprint-state/delphi-reviewed.json` 且 verdict=APPROVED |
+| `batch-grill-me` | Matt Pocock (内置) | 标准路径（change_type != "修改已存在代码"） | 批量前置决策 |
+| `delphi-review` | xp-gate | R2 设计评审；lightweight 路径使用 2 专家 1 轮 | 必须产生 `.sprint-state/delphi-reviewed.json` 且 verdict=APPROVED |
 | `to-issues` | xp-gate | delphi-review APPROVED 后 | 拆解为垂直切片 → slices-manifest.json |
 
 ### Phase 2: BUILD
@@ -31,22 +33,22 @@
 | 步骤 | Skill | 来源 | 参数注入 |
 |------|-------|------|---------|
 | -1 | `hooks-install` | githooks | 无 |
-| 0 | `dispatching-parallel-agents` | superpowers | 仅分发 AFK 切片（dependency_graph 判定） |
-| 1 | `test-driven-development` | superpowers | `--lang` 注入对应 TDD skill |
-| 2 | `executing-plans` | superpowers | 隔离 session，review checkpoint |
-| 3 | `freeze` | gstack | 锁定业务代码 |
-| 4 | `requesting-code-review` | superpowers | 盲评 agent |
-| 5 | `unfreeze` | gstack | 解锁 |
-| 6 | `verification-before-completion` | superpowers | 运行测试 + lint |
-| 7 | 成本监控 | sprint-flow 编排层 | token 阈值 |
+| 0 | BUILD-ENTRY-CONTRACT | xp-gate CLI | slices-manifest.json schema + slice↔REQ 校验 |
+| 1 | `test-driven-development` | xp-gate (内置) | `--lang` 注入对应 TDD skill |
+| 2 | ralph-loop / parallel dispatch | sprint-flow 编排层 | 隔离 session，review checkpoint |
+| 3 | blind-review (read-only subagent) | sprint-flow 编排层 | tools: [Read, Grep, Glob] |
+| 4 | verification-before-completion | sprint-flow 编排层 | 运行测试 + lint |
+| 5 | 成本监控 | sprint-flow 编排层 | token 阈值 |
+| 6 | learnings.md 写入 | sprint-flow 编排层 | 原生文件写入 |
 
 ### Phase 3: REVIEW
 
 | Skill | 模式 | 触发条件 |
 |-------|------|---------|
 | `delphi-review` | `--mode code-walkthrough` | 强制调用 |
-| `test-specification-alignment` | 默认 | 强制调用 |
-| `browse` | gstack | 强制调用 |
+| `test-specification-alignment` | 默认 | 强制调用（#367 程序化 HARD-GATE） |
+| `xp-gate check --all` | 全量门禁 | 强制调用 |
+| 浏览器验证 | Layer 4 可选链 | gstack browse > browser-use MCP > SKIP |
 | `k6`/`locust`/`gatling` | 性能测试 | `--with-performance` 或 `--type backend-*` |
 
 ### Phase 4: USER ACCEPTANCE
@@ -59,18 +61,17 @@
 
 | Skill | 来源 | 说明 |
 |-------|------|------|
-| `learn` | gstack | 模式记录 |
-| `retro` | gstack | 工程回顾 |
-| `systematic-debugging` | superpowers | 根因调试 |
+| learnings.md 写入 | 原生 | 模式记录（替代原 gstack learn） |
+| `xp-gate retro` | 原生 CLI | 工程回顾（含 #369 返工率区块） |
+| systematic-debugging | Layer 4 可选 | 根因调试（如已安装；否则"无根因不修复"文本纪律） |
 
 ### Phase 6: SHIP
 
 | Skill | 说明 |
 |-------|------|
-| `finishing-a-development-branch` | 4 选项 |
-| `ship` | 创建 PR（可选） |
-| `land-and-deploy` | 合并部署 |
-| `canary` | 监控告警 |
+| 分支完成决策（原生 4 选项） | merge / PR / keep / discard |
+| native ship 步骤 | test → VERSION-GATE → commit → push → gh pr create |
+| native land 步骤 | merge 确认 → wait CI → canary → fail git revert |
 
 ---
 

package/skills/sprint-flow/references/components/tool-descriptions.md

@@ -16,14 +16,13 @@
 | 步骤 | Skill | 来源 | 说明 |
 |------|-------|------|------|
 | -1 | `hooks-install` | githooks | `githooks/verify.sh` → 缺失则 `githooks/install.sh` |
-| 0 | `dispatching-parallel-agents` | superpowers | 检测可并行任务 |
-| 1 | `test-driven-development` | superpowers | RED → GREEN → REFACTOR |
-| 2 | `executing-plans` | superpowers | 隔离 session，review checkpoint |
-| 3 | `freeze` | gstack | 盲评隔离 |
-| 4 | `requesting-code-review` | superpowers | 独立 agent 评审 |
-| 5 | `unfreeze` | gstack | 解锁 |
-| 6 | `verification-before-completion` | superpowers | 测试 + lint |
-| 7 | 成本监控 | sprint-flow 编排层 | 超阈值 BLOCK |
+| 0 | BUILD-ENTRY-CONTRACT | xp-gate CLI | slices-manifest.json schema + slice↔REQ 校验 |
+| 1 | `test-driven-development` | xp-gate (内置) | RED → GREEN → REFACTOR |
+| 2 | ralph-loop / parallel dispatch | sprint-flow 编排层 | 隔离 session，review checkpoint |
+| 3 | blind-review (read-only subagent) | sprint-flow 编排层 | tools: [Read, Grep, Glob]，只读盲评 |
+| 4 | verification-before-completion | sprint-flow 编排层 | 测试 + lint |
+| 5 | 成本监控 | sprint-flow 编排层 | 超阈值 BLOCK |
+| 6 | learnings.md 写入 | sprint-flow 编排层 | 原生模式记录 |
 
 ### GITHOOKS-GATE (Phase 1→2 闸门)
 
@@ -46,8 +45,9 @@
 | Skill | 模式 | 说明 |
 |-------|------|------|
 | `delphi-review` | `--mode code-walkthrough` | 多专家匿名代码走查 |
-| `test-specification-alignment` | 默认 | 测试与 Spec 对齐验证 |
-| `browse` | gstack | 浏览器自动化测试 |
+| `test-specification-alignment` | 默认 | 测试与 Spec 对齐验证（#367 程序化 HARD-GATE） |
+| `xp-gate check --all` | 全量门禁 | Gate 0–9 含安全审计 |
+| 浏览器验证 | Layer 4 可选链 | gstack browse > browser-use MCP > SKIP |
 | `k6` / `locust` / `gatling` | 可选 | 后端负载测试 |
 
 ---
@@ -56,9 +56,9 @@
 
 | Skill | 说明 |
 |-------|------|
-| `learn` | gstack，模式记录 |
-| `retro` | gstack，工程回顾 |
-| `systematic-debugging` | superpowers，根因调试 |
+| learnings.md 写入 | 原生模式记录（替代原 gstack learn） |
+| `xp-gate retro` | 原生工程回顾（含 #369 返工率区块） |
+| systematic-debugging | Layer 4 可选，根因调试（如已安装） |
 
 ---
 
@@ -66,10 +66,9 @@
 
 | Skill | 说明 |
 |-------|------|
-| `finishing-a-development-branch` | 4 选项: merge / PR / discard / keep |
-| `ship` | gstack，创建 PR |
-| `land-and-deploy` | 合并部署 |
-| `canary` | 监控告警 |
+| 分支完成决策（原生 4 选项） | merge / PR / keep / discard |
+| native ship 步骤 | test → VERSION-GATE → commit → push → gh pr create |
+| native land 步骤 | merge 确认 → wait CI → canary → fail git revert |
 
 ---
 
@@ -77,12 +76,12 @@
 
 | Phase | Backend (default) | Web Frontend | Mobile |
 |-------|------------------|-------------|--------|
-| Phase 0 (THINK) | `brainstorming` | (同) | (同) |
-| Phase 1 (PLAN) | `autoplan` + `delphi-review` | + `design-shotgun` | (同 web) |
-| Phase 2 (BUILD) | TDD + blind-review | (同 backend) | + `vercel-react-native-skills` / `flutter-review` |
-| Phase 3 (REVIEW) | `delphi-review --mode code-walkthrough` | + `qa` + `design-review` + `benchmark` | `flutter-test` / `detox E2E` |
-| Phase 5 (FEEDBACK) | `learn` + `retro` | (同) | (同) |
-| Phase 6 (SHIP) | `finishing-a-development-branch` + `ship` | (同) | + platform deploy |
+| Phase 0 (THINK) | `grill-with-docs` + R1 `delphi-review --mode requirements` | (同) | (同) |
+| Phase 1 (PLAN) | `batch-grill-me` + R2 `delphi-review` | + OPTIONAL `design-shotgun` | (同 web) |
+| Phase 2 (BUILD) | TDD + blind-review (read-only subagent) | (同 backend) | + `vercel-react-native-skills` / `flutter-review` |
+| Phase 3 (REVIEW) | `delphi-review --mode code-walkthrough` + `xp-gate check --all` | + `xp-gate ui-review` + OPTIONAL qa/design-review/benchmark | `flutter-test` / `detox E2E` |
+| Phase 5 (FEEDBACK) | learnings.md + `xp-gate retro` | (同) | (同) |
+| Phase 6 (SHIP) | 原生 4 选项 + native ship + native land | (同) | + platform deploy |
 
 ---
 

package/skills/sprint-flow/references/orchestration-rules.md

@@ -29,30 +29,32 @@
 | Phase | 名称 | Subagent? | Category | load_skills | 执行者 |
 |-------|------|:---------:|----------|-------------|--------|
 | 1/6 | PREP | ❌ | Bash（直接执行） | 无 | orchestrator |
-| 2/6 | DESIGN | ❌ | orchestrator（直接执行） | `["brainstorming", "autoplan", "delphi-review", "to-issues"]` | orchestrator |
+| 2/6 | DESIGN | ❌ | orchestrator（直接执行） | `["grill-with-docs", "batch-grill-me", "delphi-review", "to-issues"]` | orchestrator |
 | 3/6 | BUILD | ✅ | ralph-loop | `["test-driven-development"]` | subagent |
-| 4/6 | VERIFY | ❌ | orchestrator（直接执行） | `["delphi-review", "test-specification-alignment", "learn", "retro", "systematic-debugging"]` | orchestrator |
-| 5/6 | SHIP | ❌ | orchestrator（直接执行） | `["finishing-a-development-branch", "ship", "land-and-deploy"]` | orchestrator |
+| 4/6 | VERIFY | ❌ | orchestrator（直接执行） | `["delphi-review", "test-specification-alignment"]` | orchestrator |
+| 5/6 | SHIP | ❌ | orchestrator（直接执行） | 无（原生步骤） | orchestrator |
 | 6/6 | CLOSE | ❌ | **强制人工 (UAT)** + Bash (CLEANUP) | 无 | 用户 + orchestrator |
 
 **⚠️ 交互式 skill 必须由 orchestrator 直接执行（不可 dispatch 到 subagent）**：
 
 | Phase | Skill | 为什么不能在 subagent 中执行 |
 |-------|-------|---------------------------|
-| 2/6 | `brainstorming` | 需要与用户对话确认需求、提出澄清问题。Subagent 是 fire-and-forget 模式，无法暂停等待用户输入（Issue #217） |
-| 2/6 | `autoplan` | taste_decisions 节点暂停等待用户确认。必须由 orchestrator 直接执行（Issue #225） |
+| 2/6 | `grill-with-docs` | 需要与用户对话确认需求、提出澄清问题。Subagent 是 fire-and-forget 模式，无法暂停等待用户输入（Issue #217） |
+| 2/6 | `batch-grill-me` | 批量决策节点暂停等待用户确认。必须由 orchestrator 直接执行 |
 | 2/6 | `delphi-review` | design 模式需等待 verdict APPROVED；非 APPROVED 时需用户确认是否接受分歧方案（Issue #249） |
 | 2/6 | `to-issues` | Step 6 "向用户确认" — 展示拆分结果，等待用户批准后才生成 slices-manifest.json |
 | 4/6 | `delphi-review --mode code-walkthrough` | Code walkthrough 非 APPROVED 时需暂停等待用户处理 Critical Issues（Issue #249） |
-| 5/6 | `finishing-a-development-branch` | 4 选项菜单 (merge/PR/keep/discard) 需要用户选择；Option 4 (discard) 要求 typed confirmation |
-| 5/6 | `ship` | PR 创建前需要用户确认；包含 AskUserQuestion STOP 点 |
-| 5/6 | `land-and-deploy` | Merge 确认、rollback 决策 — 均为用户交互点 |
+| 5/6 | 分支完成决策 | 4 选项菜单 (merge/PR/keep/discard) 需要用户选择；Option 4 (discard) 要求 typed confirmation |
+| 5/6 | native ship | PR 创建前需要用户确认 |
+| 5/6 | native land | Merge 确认、rollback 决策 — 均为用户交互点 |
 
 **Phase 2/6 DESIGN 执行模式（全部 orchestrator 直接执行）**：
-1. **Orchestrator 直接执行 brainstorming**：`skill(name="brainstorming")` → 等待 APPROVED
-2. **Orchestrator 直接执行 autoplan**：`skill(name="autoplan")` → 等待用户确认 taste_decisions
-3. **Orchestrator 直接执行 delphi-review**：`skill(name="delphi-review")` → 等待 APPROVED
-4. **Orchestrator 直接执行 to-issues**：`skill(name="to-issues")` → 等待用户确认 Issue 拆分
+1. **Orchestrator 直接执行 grill-with-docs**：`skill(name="grill-with-docs")` → 访谈 + CONTEXT.md/ADR
+2. **Orchestrator 执行 R1 需求评审**：`npx xp-gate delphi-review --mode requirements` → requirements-reviewed.json
+3. **Orchestrator 生成设计文档** → 等待用户 APPROVED
+4. **Orchestrator 直接执行 batch-grill-me**：`skill(name="batch-grill-me")` → 批量决策确认
+5. **Orchestrator 直接执行 R2 delphi-review**：`skill(name="delphi-review")` → 等待 APPROVED
+6. **Orchestrator 直接执行 to-issues**：`skill(name="to-issues")` → 等待用户确认 Issue 拆分
 
 **上下文隔离原则**：
 - 每个 Subagent 在**独立 session** 中启动，不继承 orchestrator 的对话历史