maestro-flow 0.4.13 → 0.4.15

package/.agents/skills/maestro/SKILL.md

@@ -1,7 +1,7 @@
 ---
 name: maestro
 description: Auto-route intent to optimal command chain
-argument-hint: "<intent> [-y] [-c] [--dry-run] [--exec auto|cli|internal] [--tool <name>] [--super]"
+argument-hint: "<intent> [-y] [-c] [--dry-run] [--super]"
 allowed-tools:
   - read_file
   - write_file
@@ -42,18 +42,16 @@ $ARGUMENTS — user intent text, or special keywords.
 - `-y` / `--yes` — Auto mode: skip clarification, skip confirmation, auto-skip on errors
 - `-c` / `--continue` — Resume previous session
 - `--dry-run` — Show chain without executing
-- `--exec <mode>` — `auto` (default), `cli`, `internal`
-- `--tool <name>` — CLI tool for delegates (default: claude)
 - `--super` — Read and follow `maestro-super.md`
 </context>
 
 <invariants>
 1. **All chains dispatch via maestro-ralph-execute** — maestro never executes steps directly
 2. **Session before execution** — status.json created before any step runs
-3. **Auto flags only to supporting commands** — unlisted commands execute as-is
+3. **Auto flag pass-through** — 仅当用户传入 `-y` 时透传 `-y` 到 skill args
 4. **Decomposition contract shared with maestro-ralph** — broad/lifecycle intents run S_DECOMPOSE producing the SAME additive block (`boundary_contract`, `execution_criteria`, `task_decomposition`)。Reference maestro-ralph `A_DECOMPOSE_TASKS`
 5. **status.json 唯一真源** — 不生成 `goal-checklist.md` 或外部清单
-6. **Default step type = internal** — chain 内每个 step 解析 `command_scope`/`command_path`（全局优先 `~/.claude/commands/{name}.md`，fallback 项目）
+6. **执行步骤统一 Read .md 内联** — chain 内每个执行 step 解析 `command_scope`/`command_path`（全局优先 `~/.claude/commands/{name}.md`，fallback 项目），由 ralph-execute `read_file({command_path})` 内联执行；CLI 仅在 decision 节点做只读分析
 7. **Topology awareness** — chain catalog 含 brainstorm / blueprint / analyze-macro(text) / analyze(numeric phase) / roadmap / plan(三路径) / execute / verify / ...；scope_verdict 路由由 ralph 在 `post-analyze-scope` 决定
 8. **D-007 milestone 反查** — 数字 phase 步骤的 `milestone_id` 由 `state.json.milestones[].phase_slugs` 反查得出
 9. **每个 step 必须 `completion_confirmed: true`** — 基于 `--- COMPLETION STATUS ---` 的 `STATUS: DONE`
@@ -143,7 +141,7 @@ S_FALLBACK:
    - 数字 phase 上下文 → `analyze {phase}` → `plan {phase}` → `execute {phase}` → `verify {phase}` → quality pipeline
    - 已有 analyze artifact 想直达执行 → `plan --from analyze:{ANL_ID}` → execute → verify
    - 已有 blueprint artifact → `plan --from blueprint:{BLP_ID}` → execute → verify
-4. 每个 step 默认 `type: "internal"`；解析 `command_scope` + `command_path`（全局优先 fallback 项目）；写入 `step.stage` / `step.scope` / `step.source_artifact_ref`（如 `--from` 注入时）
+4. 执行 step 解析 `command_scope` + `command_path`（全局优先 fallback 项目）；写入 `step.stage` / `step.scope` / `step.source_artifact_ref`（如 `--from` 注入时）。decision 节点通过 `step.decision` 字段标识
 
 ### A_CLARIFY
 
@@ -159,9 +157,9 @@ S_FALLBACK:
 3. 派生 `execution_criteria` + `task_decomposition`（每个 sub-goal 含 `done_when` + `evidence` + `lifecycle` + `completion_confirmed: false`）
 4. **status.json 唯一真源**：写入 `boundary_contract` / `execution_criteria` / `task_decomposition`；不生成 markdown 清单
 5. 在最后一个 evidence-producing stage（verify/review/test）之后、`milestone-complete` 之前追加 `decision:post-goal-audit`。ralph-execute 在该节点按需动态生长 `steps[]`
-6. **输出 `/goal` 绑定提示词：**
+6. **输出 `/goal` 绑定提示词（不阻塞，用户可在执行过程中随时输入）：**
    ```
-   📋 任务分解完成。复制下面一行设定目标，会话在子目标全部达成前不停：
+   📋 任务分解完成。可随时复制下面一行设定目标（执行过程中输入即可）：
 
    /goal 目标达成条件: {session_dir}/status.json 中 task_decomposition[*].status == "done" 且 task_decomposition[*].completion_confirmed == true 且 steps[*].completion_confirmed == true。未达成时：阅读 {session_dir}/status.json 取得 execution_criteria / boundary_contract / task_decomposition / steps 作为行动手册，调用 /maestro-ralph continue 推进；严禁手动执行 skill 或越界修改 status.json.boundary_contract.out_of_scope。
    ```
@@ -175,13 +173,14 @@ S_FALLBACK:
      "session_id", "source": "maestro", "intent", "task_type", "chain_name",
      "phase", "phase_is_new": false, "milestone": "",
      "scope_verdict": null, "analyze_macro_id": null, "blueprint_id": null,
-     "auto_mode": false, "exec_mode": "auto", "cli_tool": "claude",
+     "auto_mode": false, "cli_tool": "claude",   // cli_tool: decision 节点 delegate 评估时的 CLI 工具
      "context": { "scratch_dir": null, "plan_dir": null, "analysis_dir": null,
        "brainstorm_dir": null, "blueprint_dir": null, "issue_id": null },
      "steps": [{
-       "index": 0, "type": "internal|external|decision",
+       "index": 0,
        "skill": "", "args": "",
        "stage": "", "scope": null,
+       "decision": null,                 // 非 null → decision 节点；null → 执行节点
        "command_scope": "global|project|missing|null",
        "command_path": "~/.claude/commands/{name}.md | .claude/commands/{name}.md | null",
        "milestone_id": null, "source_artifact_ref": null,
@@ -205,25 +204,6 @@ S_FALLBACK:
 
 <appendix>
 
-### Auto-Yes Flag Map
-
-| Command | Auto Flag | Effect |
-|---------|-----------|--------|
-| maestro-init | `-y` | Skip interactive questioning |
-| maestro-analyze | `-y` | Skip scoping, auto-deepen |
-| maestro-brainstorm | `-y` | Skip questions, use defaults |
-| maestro-blueprint | `-y` | Skip interview, use recommended defaults |
-| maestro-roadmap | `-y` | Skip questions (create/revise/review) |
-| maestro-impeccable | `-y` | Auto-select design variant + skip confirmations |
-| maestro-plan | `-y` | Skip confirmations and clarification |
-| maestro-execute | `-y` | Skip confirmations, blocked auto-continue |
-| quality-auto-test | `-y` | Skip plan confirmation |
-| quality-test | `-y --auto-fix` | Auto-trigger gap-fix loop |
-| quality-retrospective | `-y` | Accept all routing recommendations |
-| maestro-milestone-complete | `-y` | Skip knowledge promotion |
-
-Unlisted commands have no auto flags.
-
 ### Error Codes
 
 | Code | Severity | Description | Recovery |
@@ -248,8 +228,8 @@ Unlisted commands have no auto flags.
 - [ ] status.json 唯一真源；无 markdown 清单；post-goal-audit 节点在 decomposed 时追加；/goal 提示词以 status.json 为判据
 - [ ] Chain selected and confirmed (or auto-confirmed)
 - [ ] Session dir created with status.json before execution; decomposition fields additive-only
-- [ ] 每个 step 含 `command_scope` + `command_path` + `completion_confirmed` 字段
-- [ ] Auto flags propagated to supporting commands only
+- [ ] 执行 step 含 `command_scope` + `command_path` + `completion_confirmed` 字段；decision step 通过 `step.decision` 字段标识
+- [ ] 用户传入 `-y` 时透传到 skill args
 - [ ] All chains dispatched via maestro-ralph-execute
 - [ ] Low-complexity intents routed to maestro-quick
 - [ ] (super) Requirements validated before roadmap

package/.agents/skills/maestro-brainstorm/SKILL.md

@@ -14,7 +14,7 @@ allowed-tools:
 <!-- Open-standard mirror generated by scripts/build-agents-standard.mjs — do not edit; re-run after editing .claude/ source. -->
 
 <purpose>
-Unified brainstorming combining interactive framework generation, multi-role parallel analysis, cross-role review, and resolution writeback. Two modes: Auto (full pipeline: guidance-specification → parallel {role}/ multi-file analysis → cross-role-reviewer compares Decision Digests for conflicts/gaps/synergies → user-confirmed resolutions patched into role files + logged in guidance §12) and Single Role (individual role analysis for an existing session). Outputs structured artifacts in `.workflow/scratch/brainstorm-{slug}-{date}/` ready for downstream planning (roadmap / analyze / blueprint consume `guidance-specification.md`).
+Unified brainstorming combining interactive framework generation, multi-role parallel analysis, cross-role review, and resolution writeback. Two modes: Auto (full pipeline: guidance-specification → parallel {role}/ multi-file analysis → cross-role-reviewer compares Decision Digests for conflicts/gaps/synergies → user-confirmed resolutions patched into role files + logged in guidance §12) and Single Role (individual role analysis for an existing session). Outputs structured artifacts in `.workflow/scratch/{YYYYMMDD}-brainstorm-{slug}/` ready for downstream planning (roadmap / analyze / blueprint consume `guidance-specification.md`).
 </purpose>
 
 <required_reading>
@@ -32,7 +32,7 @@ $ARGUMENTS -- topic text for auto mode, or role name for single role mode.
 
 **Auto mode**: topic text (e.g., "Build real-time collaboration platform") triggers full pipeline.
 **Single role mode**: valid role name (e.g., "system-architect") runs one role analysis.
-**All output** goes to `.workflow/scratch/brainstorm-{slug}-{YYYYMMDD}/` (orchestrator MUST resolve this to an absolute path before passing to sub-agents).
+**All output** goes to `.workflow/scratch/{YYYYMMDD}-brainstorm-{slug}/` (orchestrator MUST resolve this to an absolute path before passing to sub-agents).
 **Artifact registration**: On completion, registers artifact (type=brainstorm) in state.json.
 **Output boundary**: ALL file writes MUST target `{output_dir}/` or `.workflow/state.json` only. NEVER modify source code or files outside these paths.
 **Produced files**: `guidance-specification.md`, `design-research.md` (optional), `{role}/analysis.md` + `{role}/analysis-F-*.md` + `{role}/findings-*.md` (per selected role).

package/.agents/skills/maestro-ralph/SKILL.md

@@ -19,16 +19,17 @@ Closed-loop decision engine for the maestro workflow lifecycle.
 Reads project state → infers position → builds adaptive chain → delegates execution.
 
 Entry points:
-- **`/maestro-ralph "intent"`** — New session: infer → decompose → build → execute
-- **`/maestro-ralph continue`** — Resume via maestro-ralph-execute
+- **`/maestro-ralph "intent"`** — New session: infer → decompose → build → emit /goal prompt（如有 decomposition）→ dispatch ralph-execute
+- **`/maestro-ralph continue`** — Wrapper; dispatches to ralph-execute（首选直接 `/maestro-ralph-execute` 推进 step）
 - **`/maestro-ralph status`** — Display session progress
 
+> 推进规则：**step 推进由 `/maestro-ralph-execute` 负责**；ralph 仅在 build / decision 评估时介入。decision 节点由 ralph-execute 自动 `invoke_skill("maestro-ralph")` handoff，无需用户手动切换。
+
 Initial decomposition (S_DECOMPOSE): boundary-clarified via ≤3 questions for broad intents (重构/全面/迁移/重写). 写入 status.json 的 `boundary_contract` / `execution_criteria` / `task_decomposition`，附 `/goal` prompt。
 
-Node types:
-- **internal** (default): ralph-execute `read_file({command_path})` 命令 .md，按内容内联执行
-- **decision**: 回 ralph 评估
-- **external**: 仅在显式声明时使用（`maestro delegate --to claude`）
+Step kinds:
+- **执行 step**: ralph-execute `read_file({command_path})` 命令 .md，按内容内联执行
+- **decision step**: `step.decision` 字段非空；回 ralph 评估（CLI 只读分析）
 
 Key difference from maestro coordinator:
 - maestro: static chain → one-time selection → runs all steps
@@ -45,8 +46,8 @@ Mutual invocation with `/maestro-ralph-execute` forms a self-perpetuating work l
                               │           writes status.json
                               │           emits /goal prompt
                               ▼
-                       ralph-execute  ◀─┐ internal → read_file(command_path) inline
-                              │         │ decision → invoke_skill("maestro-ralph")
+                       ralph-execute  ◀─┐ 执行 step → read_file(command_path) inline
+                              │         │ decision step → invoke_skill("maestro-ralph")
                               └─────────┘ writes step.completion_confirmed
                        loop until all completion_confirmed | paused
 ```
@@ -70,15 +71,16 @@ Remaining     → intent
 
 <invariants>
 1. **Ralph never executes steps** — only creates sessions and evaluates decisions
-2. **Handoff via invoke_skill("maestro-ralph-execute")** — at session creation and after decision evaluation
+2. **Handoff via invoke_skill("maestro-ralph-execute")** — 创建 session 后始终自动 handoff；decision 评估后始终 handoff
 3. **Decision delegates read-only** — `maestro delegate --role analyze --mode analysis`
-4. **Default type = internal** — `external` 仅显式标注时出现，build 不默认生成
+4. **执行 step 通过 Read 命令 .md 内联执行**
 5. **status.json 是唯一真源** — 不生成 markdown 清单或侧文件
 6. **每个 step 必须 `completion_confirmed: true`** — 基于 `--- COMPLETION STATUS ---` 的 `STATUS: DONE`；缺失则视为未完成
 7. **command_path 在 A_BUILD_STEPS 解析** — 全局优先 `~/.claude/commands/{name}.md`，fallback 项目 `.claude/commands/{name}.md`，写入 status.json
-8. **Decomposition is outcome-oriented** — sub-goals 为可观测交付，禁止 lifecycle 复刻；`/goal` 用户绑定，ralph 只发提示词
-9. **planning_mode governs arg granularity** — `unified` → skill args 无 `{phase}`；`independent` → 含 `{phase}`
-10. **task_decomposition 驱动 steps[] 动态生长** — `post-goal-audit` 按 unmet 子目标插入 scoped mini-loop；字段可选/累加，既有字段不删不改
+8. **执行 step 加载契约** — ralph-execute 读 `command_path` 后，必须解析并加载该命令 `<required_reading>` 引用的所有文件（"入口 + workflow"形式的核心），并把 `<deferred_reading>` 路径记录到 `step.deferred_reads`；加载完成后输出 `✓ skill {name} 加载完成`。ralph 在 build 阶段只解析路径，不读 .md 内容
+9. **Decomposition is outcome-oriented** — sub-goals 为可观测交付，禁止 lifecycle 复刻；`/goal` 用户绑定，ralph 输出提示词后继续 handoff，用户可在执行过程中随时输入 `/goal`
+10. **planning_mode governs arg granularity** — `unified` → skill args 无 `{phase}`；`independent` → 含 `{phase}`
+11. **task_decomposition 驱动 steps[] 动态生长** — `post-goal-audit` 按 unmet 子目标插入 scoped mini-loop；字段可选/累加，既有字段不删不改
 </invariants>
 
 <state_machine>
@@ -148,8 +150,8 @@ S_BUILD_CHAIN:
   → S_CREATE_SESSION DO: A_BUILD_STEPS
 
 S_CREATE_SESSION:
-  → S_CONFIRM       WHEN: not auto_confirm                  DO: A_CREATE_SESSION
-  → S_DISPATCH      WHEN: auto_confirm                      DO: A_CREATE_SESSION
+  → S_CONFIRM       WHEN: not auto_confirm                   DO: A_CREATE_SESSION
+  → S_DISPATCH      WHEN: auto_confirm                       DO: A_CREATE_SESSION
 
 S_CONFIRM:
   → S_DISPATCH      WHEN: user selects "Proceed"
@@ -159,7 +161,7 @@ S_CONFIRM:
 S_DISPATCH:
   → END             DO: invoke_skill({ skill: "maestro-ralph-execute" })
 
-S_DECISION_EVAL:
+S_DECISION_EVAL: (decision 节点 == `step.decision` 非空，下述 gate 名取自该字段)
   → S_APPLY_VERDICT WHEN: quality-gate (post-verify, post-business-test, post-review, post-test)
                      DO: A_DELEGATE_EVALUATE
   → S_APPLY_VERDICT WHEN: goal-gate (post-goal-audit)
@@ -198,7 +200,7 @@ S_FALLBACK:
 
 1. Find latest ralph session (by created_at)
 2. Display: Session, Status, Position, Progress, Current step
-3. List steps: [✓] completion_confirmed, [▸] current, [ ] pending, [◆] decision；附 `command_scope`(global/project) + `command_path`
+3. List steps: [✓] completion_confirmed, [▸] current, [ ] pending, [◆] decision（`step.decision` 非空）；执行 step 附 `command_scope`(global/project) + `command_path`
 4. If `task_decomposition` present (absent → skip):
    ```
    Sub-goals  ({done}/{total})    source: {session_dir}/status.json#/task_decomposition
@@ -378,24 +380,26 @@ narrow → derive defaults from intent + codebase, skip questions.
 
 Generate steps from `session.lifecycle_position` to `milestone-complete`.
 
-| Stage | invoke_skill(independent) | invoke_skill(unified) | Type | Decision after | quality_mode |
-|-------|---------------------|-----------------|------|----------------|--------------|
-| brainstorm | `maestro-brainstorm "{intent}"` | *(same)* | internal | — | all |
-| blueprint | `maestro-blueprint "{intent}"` | *(same)* | internal | — | all |
-| init | `maestro-init` | *(same)* | internal | — | all |
-| analyze-macro | `maestro-analyze "{intent}"` | *(same)* | internal | `post-analyze-scope` | all |
-| roadmap | `maestro-roadmap --from analyze:{analyze_macro_id}` | *(same)* | internal | — | all |
-| analyze | `maestro-analyze {phase}` | `maestro-analyze` | internal | — | all |
-| plan | `maestro-plan {phase}` *(scope=phase)* / `maestro-plan --from analyze:{analyze_macro_id}` *(scope=standalone)* / `maestro-plan --from blueprint:{blueprint_id}` *(scope=standalone)* | `maestro-plan` | internal | — | all |
-| execute | `maestro-execute {phase}` | `maestro-execute` | internal | — | all |
-| verify | `maestro-verify {phase}` | `maestro-verify` | internal | `post-verify` | all |
-| business-test | `quality-auto-test {phase}` | `quality-auto-test` | internal | `post-business-test` | full only |
-| review | `quality-review {phase}` | `quality-review` | internal | `post-review` | all (quick: append `--tier quick`) |
-| test-gen | `quality-auto-test {phase}` | `quality-auto-test` | internal | — | full / standard if coverage<80% |
-| test | `quality-test {phase}` | `quality-test` | internal | `post-test` | full, standard |
-| milestone-audit | `maestro-milestone-audit` | *(same)* | internal | — | all |
-| goal-audit | *(decision-only)* | *(same)* | decision | `post-goal-audit` | all (only if decomposed) |
-| milestone-complete | `maestro-milestone-complete` | *(same)* | internal | `post-milestone` | all |
+| Stage | invoke_skill(independent) | invoke_skill(unified) | Decision after | quality_mode |
+|-------|---------------------|-----------------|----------------|--------------|
+| brainstorm | `maestro-brainstorm "{intent}"` | *(same)* | — | all |
+| blueprint | `maestro-blueprint "{intent}"` | *(same)* | — | all |
+| init | `maestro-init` | *(same)* | — | all |
+| analyze-macro | `maestro-analyze "{intent}"` | *(same)* | `post-analyze-scope` | all |
+| roadmap | `maestro-roadmap --from analyze:{analyze_macro_id}` | *(same)* | — | all |
+| analyze | `maestro-analyze {phase}` | `maestro-analyze` | — | all |
+| plan | `maestro-plan {phase}` *(scope=phase)* / `maestro-plan --from analyze:{analyze_macro_id}` *(scope=standalone)* / `maestro-plan --from blueprint:{blueprint_id}` *(scope=standalone)* | `maestro-plan` | — | all |
+| execute | `maestro-execute {phase}` | `maestro-execute` | — | all |
+| verify | `maestro-verify {phase}` | `maestro-verify` | `post-verify` | all |
+| business-test | `quality-auto-test {phase}` | `quality-auto-test` | `post-business-test` | full only |
+| review | `quality-review {phase}` | `quality-review` | `post-review` | all (quick: append `--tier quick`) |
+| test-gen | `quality-auto-test {phase}` | `quality-auto-test` | — | full / standard if coverage<80% |
+| test | `quality-test {phase}` | `quality-test` | `post-test` | full, standard |
+| milestone-audit | `maestro-milestone-audit` | *(same)* | — | all |
+| goal-audit | *(decision-only)* | *(same)* | `post-goal-audit` | all (only if decomposed) |
+| milestone-complete | `maestro-milestone-complete` | *(same)* | `post-milestone` | all |
+
+> 所有执行 stage 统一通过 Read .md 内联执行；decision 节点单独作为独立 step 插入（见规则 4）。
 
 **Build rules (按顺序应用):**
 
@@ -403,17 +407,18 @@ Generate steps from `session.lifecycle_position` to `milestone-complete`.
 1. **起点**：从 `session.lifecycle_position` 开始
 2. **跳过已完成**：跳过当前 milestone+phase 下已有 completed artifact 的 stage（按 `session.phase` 过滤）；unified 按 milestone 过滤
 3. **quality_mode 过滤**：按 `session.quality_mode` 排除不匹配 stage
-4. **决策节点**：每个 Decision after 非空的 stage 之后插入 `{ type: "decision", decision: "<gate>", retry_count: 0, max_retries: 2 }`
+4. **决策节点**：每个 Decision after 非空的 stage 之后插入 `{ decision: "<gate>", retry_count: 0, max_retries: 2, command_scope: null, command_path: null }`
 5. **goal-audit 插入**：`task_decomposition` 存在时，在最后一个 evidence-producing stage（verify/review/test）之后、`milestone-complete` 之前插入 `decision:post-goal-audit`
 6. **终点硬约束**：chain 以 `milestone-complete` 结尾
 7. **goal_ref 传播**：`task_decomposition` 存在时，每个 step 按 `step.stage ∈ g.lifecycle` 匹配 `step.goal_ref = g.id`（多匹配取字典序最小）；decision 节点不打 goal_ref
 8. **占位符**：independent 保留 `{phase}` `{intent}`；unified 不带 `{phase}`
-9. **command_path 解析**（每个非 decision step）：
+9. **command_path 解析**（每个执行 step，decision 节点跳过）：
    - 取 skill 名（args 前的第一个 token）
    - 全局优先：`~/.claude/commands/{name}.md` 存在 → `command_scope = "global"`
    - Fallback：`.claude/commands/{name}.md` 存在 → `command_scope = "project"`
    - 两者都缺 → `command_scope = "missing"`, `command_path = null`，A_CREATE_SESSION 报错 E006
-10. **每个 step 初始化** `completion_confirmed: false`, `completion_status: null`, `completion_evidence: null`
+   - **不在 build 阶段读取 .md 内容**；`<required_reading>` / `<deferred_reading>` 解析与加载由 ralph-execute A_EXEC_STEP 负责（保持入口/工作流分离）
+10. **每个 step 初始化** `completion_confirmed: false`, `completion_status: null`, `completion_evidence: null`, `deferred_reads: []`
 11. **scope_verdict gating**（仅当 chain 起点 = `analyze-macro`）：
     - `scope_verdict ∈ {medium, small}` → 跳过 `roadmap` + `analyze` 两 stage；`plan` 选 standalone 列（`--from analyze:{analyze_macro_id}`），不带 `{phase}`
     - `scope_verdict == large` → 保留 `roadmap` + `analyze`；`plan` 选 phase 列（`{phase}`）
@@ -431,7 +436,7 @@ Generate steps from `session.lifecycle_position` to `milestone-complete`.
 1. Validate: 所有 step 的 `command_scope != "missing"`；否则 raise E006 + 列出缺失 skill
 2. Write `.workflow/.maestro/ralph-{YYYYMMDD-HHmmss}/status.json` (Appendix: Session Schema)
 3. Display chain overview：每步显示 `{index}. {skill} [{type}] [{command_scope}]`
-4. If `task_decomposition` present: display the **Goal Prompt block** (Appendix: Goal Prompt Template)
+4. If `task_decomposition` present: display **Goal Prompt block** (Appendix)，不阻塞流程，继续 handoff
 
 ### A_DELEGATE_EVALUATE
 
@@ -606,12 +611,14 @@ Runs only when `task_decomposition` present.
     "analysis_dir": null, "brainstorm_dir": null, "blueprint_dir": null },
   "steps": [{
     "index": 0,
-    "type": "internal|external|decision",
-    "skill": "",
+    "skill": "",                  // 执行 step 有值；decision 节点为空字符串/null
     "args": "",
     "stage": "",                  // brainstorm|blueprint|init|analyze-macro|roadmap|analyze|plan|execute|verify|...
     "scope": null,                // "phase"|"standalone"|"milestone"|null（plan 等需要）
-    "command_scope": "global|project|missing|null",
+    "decision": null,             // 非 null → decision 节点（值为 gate 名，如 "post-verify"）；null → 执行 step
+    "retry_count": 0,             // decision 节点专用
+    "max_retries": 2,             // decision 节点专用
+    "command_scope": "global|project|missing|null",  // 执行 step；decision 节点固定 null
     "command_path": "~/.claude/commands/{name}.md | .claude/commands/{name}.md | null",
     "milestone_id": null,         // D-007 反查注入；仅含 {phase} 占位符的 step 有
     "source_artifact_ref": null,  // "analyze:ANL-xxx" | "blueprint:BLP-xxx" | null
@@ -620,7 +627,8 @@ Runs only when `task_decomposition` present.
     "completion_confirmed": false,
     "completion_status": null,
     "completion_evidence": null,
-    "completed_at": null
+    "completed_at": null,
+    "deferred_reads": []          // 由 ralph-execute A_EXEC_STEP 解析 .md 时填充
   }],
   "waves": [], "current_step": 0,
 
@@ -642,7 +650,7 @@ Runs only when `task_decomposition` present.
 
 ### Fix-Loop Templates
 
-所有插入 step 默认 `type: "internal"`，按 A_BUILD_STEPS 规则 9 解析 `command_path` + `command_scope`。
+所有插入的执行 step 按 A_BUILD_STEPS 规则 9 解析 `command_path` + `command_scope`；`decision:*` 条目为 decision 节点（`step.decision` 字段）。
 
 **post-verify:**
 ```
@@ -704,14 +712,12 @@ decision:post-goal-audit {retry+1}
 链路概览后逐字显示（仅当 decomposition 已产出）：
 
 ```
-📋 任务分解完成。复制下面一行设定目标，会话在子目标全部达成前不停：
-
-/goal 目标达成条件: {session_dir}/status.json 中 task_decomposition[*].status == "done" 且 task_decomposition[*].completion_confirmed == true 且 steps[*].completion_confirmed == true。未达成时：阅读 {session_dir}/status.json 取得 execution_criteria / boundary_contract / task_decomposition / steps 作为行动手册，调用 /maestro-ralph continue 推进；严禁手动执行 skill 或越界修改 status.json.boundary_contract.out_of_scope。
+📋 任务分解完成。可随时复制以下 /goal 设定终止条件（执行过程中输入即可）：
 
-随后运行 /maestro-ralph continue 立即开始执行。
+/goal 直到 {session_dir}/status.json 的 task_decomposition[*] 与 steps[*] 全部 completion_confirmed=true 才停。每轮以 status.json 为唯一行动手册，通过 /maestro-ralph-execute 推进 step；decision 节点由其自动 handoff 回 ralph 评估。禁止手动执行 skill 或修改 boundary_contract.out_of_scope。
 ```
 
-`/goal` 由用户输入；ralph 只输出此提示词。判据以 status.json 为权威。
+`/goal` 由用户输入；ralph 输出提示词后继续 handoff，不阻塞。
 
 ### Error Codes
 
@@ -743,8 +749,9 @@ decision:post-goal-audit {retry+1}
 - [ ] quality_mode 由 A_DETERMINE_QUALITY_MODE 决定，过滤 build steps
 - [ ] Decomposition: broad intent ≤3 question clarify；narrow auto-derive
 - [ ] status.json 唯一真源：boundary_contract + execution_criteria + task_decomposition；无外部清单
-- [ ] 每个 step 默认 `type: "internal"`，含 `command_scope` + `command_path`（全局优先 fallback 项目）
-- [ ] 每个 step 含 `completion_confirmed` + `completion_status` + `completion_evidence`（初始 false/null）
+- [ ] 执行 step 含 `command_scope` + `command_path`（全局优先 fallback 项目）；decision step 通过 `step.decision` 字段标识
+- [ ] Ralph build 阶段只解析路径，不读 .md 内容；`<required_reading>` 加载由 ralph-execute A_EXEC_STEP 完成
+- [ ] 每个 step 含 `completion_confirmed` + `completion_status` + `completion_evidence` + `deferred_reads`（初始 false/null/[]）
 - [ ] 每个 sub-goal 含 `completion_confirmed`（初始 false）
 - [ ] post-goal-audit decision 仅在 decomposed 时插入，位于 milestone-complete 之前
 - [ ] Unmet sub-goals 动态 grow steps[]（goal_ref tagged）；max retries → escalate

package/.agents/skills/maestro-ralph-execute/SKILL.md

@@ -31,28 +31,29 @@ Remaining  → session_id (if matches maestro-* or ralph-*)
 ```
 Also read `session.auto_mode` from status.json — if true, treat as `-y`.
 
-**Node types:**
+**Step kinds:**
 
-| Type | Execution | Flow after |
-|------|-----------|------------|
-| decision (ralph-only) | `invoke_skill("maestro-ralph")` | Execution ends here |
-| internal (default) | `read_file({file_path: step.command_path})` + 内联解释执行 | Self-invoke next |
-| external (opt-in) | `maestro delegate --to claude --mode write` (STOP → callback) | Self-invoke next |
+| Kind | Identifier | Execution | Flow after |
+|------|-----------|-----------|------------|
+| decision step | `step.decision` 非空 | `invoke_skill("maestro-ralph")` | Execution ends here |
+| 执行 step | `step.decision == null` | `read_file({file_path: step.command_path})` + 内联解释执行 | Self-invoke next |
 
 HARD RULES:
-- internal step：优先通过 `read_file({command_path})` 把命令 .md 加载进当前会话，再按内容执行；不要对 internal step 使用 `invoke_skill({skill})` 调用
-- decision 节点例外：A_EXEC_DECISION 必须使用 `invoke_skill({ skill: "maestro-ralph" })` 进行 handoff（这是 decision 节点的唯一允许用法）
-- `command_path` 由 ralph 在 A_BUILD_STEPS 写入 status.json；ralph-execute 不再自行解析（缺失 → 报错 E002）
-- external 仅在 `step.type == "external"` 显式声明时使用，并 always append `-y` 到 prompt args
+- 执行 step：通过 `read_file({command_path})` 把命令 .md 加载进当前会话，再按内容执行
+- **必须遵循 `<required_reading>` / `<deferred_reading>` 标签**：命令 .md 通常采用"入口 + workflow"形式，主体逻辑放在 workflow 文件中并通过 `<required_reading>` 引用；缺失 required_reading 视为加载失败
+- decision step：A_EXEC_DECISION 通过 `invoke_skill({ skill: "maestro-ralph" })` handoff 给 ralph 评估
+- `command_path` 由 ralph 在 A_BUILD_STEPS 写入 status.json（缺失 → 报错 E002）
 - 每个 step 必须产出 `--- COMPLETION STATUS ---` 块，否则视为 NEEDS_RETRY
 </context>
 
 <invariants>
-1. **Internal = Read + inline** — 通过 Read 读取 `step.command_path`，按其指令在当前 session 内执行
-2. **External = explicit only** — `step.type == "external"` 才走 delegate；默认绝不发起
-3. **必须显式 completion confirmation** — 每个 step 完成时需有 `STATUS: DONE` 且写入 `step.completion_confirmed = true`
-4. **Self-invocation chain** — 持续直到全部 `completion_confirmed` 或 paused
-5. **status.json 每步骤后写盘** — resume-safe
+1. **执行 = Read + inline** — 通过 Read 读取 `step.command_path`，按其指令在当前 session 内执行
+2. **Required reading must be loaded** — 命令 .md 中的 `<required_reading>` 引用的所有文件必须立即 Read；缺一 → 视为加载失败，pause session（E007）
+3. **Deferred reading recorded only** — `<deferred_reading>` 列出的文件路径需记录，执行过程按需 Read；不在加载阶段读取
+4. **Skill loaded confirmation** — 所有 required_reading 加载完成后必须输出一行确认：`✓ skill {step.skill} 加载完成 (required: N, deferred: M)`
+5. **必须显式 completion confirmation** — 每个 step 完成时需有 `STATUS: DONE` 且写入 `step.completion_confirmed = true`
+6. **Self-invocation chain** — 持续直到全部 `completion_confirmed` 或 paused
+7. **status.json 每步骤后写盘** — resume-safe
 </invariants>
 
 <state_machine>
@@ -78,11 +79,9 @@ S_RESOLVE_ARGS:
   → S_EXECUTE       DO: A_RESOLVE_ARGS
 
 S_EXECUTE:
-  → END             WHEN: step.type == "decision"           DO: A_EXEC_DECISION
-  → S_POST_EXEC     WHEN: step.type == "internal" + success DO: A_EXEC_INTERNAL
-  → S_HANDLE_FAIL   WHEN: step.type == "internal" + failure DO: A_EXEC_INTERNAL
-  → END             WHEN: step.type == "external"           DO: A_EXEC_EXTERNAL
-                     (STOP after background delegate; on callback → S_POST_EXEC or S_HANDLE_FAIL)
+  → END             WHEN: step.decision != null              DO: A_EXEC_DECISION
+  → S_POST_EXEC     WHEN: step.decision == null + success    DO: A_EXEC_STEP
+  → S_HANDLE_FAIL   WHEN: step.decision == null + failure    DO: A_EXEC_STEP
 
 S_POST_EXEC:
   → S_LOCATE        DO: A_MARK_COMPLETE + invoke_skill("maestro-ralph-execute")
@@ -151,40 +150,30 @@ Write enriched args back to status.json.
 ### A_EXEC_DECISION
 
 1. Mark step running, write status.json
-2. Display: `[{index}/{total}] ◆ {decision} Retry: {retry}/{max}`
+2. Display: `[{index}/{total}] ◆ {step.decision} Retry: {retry}/{max}`
 3. `invoke_skill({ skill: "maestro-ralph" })` — ralph 评估 + handoff
 4. 执行在此结束
 
-### A_EXEC_INTERNAL
+### A_EXEC_STEP
 
 1. Validate `step.command_path != null`；否则 raise E002，pause session
 2. Mark step running, write status.json
-3. Display: `[{index}/{total}] {step.skill} [internal · {step.command_scope}]`
-4. `read_file({ file_path: step.command_path })` — 把命令 .md 全文加载进当前会话（prefer Read over Skill for internal steps；decision 节点另行使用 Skill 见 A_EXEC_DECISION）
-5. 解析 frontmatter `argument-hint` 与 `<purpose>/<state_machine>/<actions>` 等指令块
-6. 计算 `effective_args`：`step.args` + auto flag（`auto ? (flag_map[step.skill] || "") : ""`）
-7. 按读到的指令在本会话中**内联执行**：调用允许的工具完成命令所规定的工作，不再发起 delegate
-8. 执行结束：要求最后一段必须包含 `--- COMPLETION STATUS ---` 块（见 A_MARK_COMPLETE）
-9. Return success / failure
-
-**Auto flag map**: 所有 lifecycle skill → `-y`; `quality-test` → `-y --auto-fix`; 未列出 → 无 flag
-
-### A_EXEC_EXTERNAL
-
-仅当 `step.type == "external"` 时使用（默认链路不产生）。
-
-1. Mark step running, write status.json
-2. Display: `[{index}/{total}] ⚡ {step.skill} [external]`
-3. 始终在 prompt 内追加 `-y`（delegate session 非交互）：`flag = flag_map[step.skill] || "-y"`
-4. Execute:
+3. Display: `[{index}/{total}] {step.skill} [{step.command_scope}]`
+4. `read_file({ file_path: step.command_path })` — 把命令 .md 全文加载进当前会话
+5. **解析 reading 标签**（"入口 + workflow"形式核心步骤）：
+   - 抽取 frontmatter `argument-hint` / `allowed-tools`
+   - 抽取 `<required_reading>` 块的所有 `@path` 引用 → 立刻 `read_file({ file_path: <expanded path> })` 加载（`~/` / `@~/` 展开为用户主目录）；任一文件缺失或读取失败 → raise E007，pause session
+   - 抽取 `<deferred_reading>` 块的所有路径 → 仅记录到 `step.deferred_reads = [...]`，执行阶段按需 Read
+   - 抽取 `<purpose>/<context>/<state_machine>/<execution>/<actions>` 等指令块
+6. **加载完成确认**：required_reading 全部成功 Read 后，输出一行：
    ```
-   shell({
-     command: `maestro delegate "/${step.skill} ${effective_args}" --to claude --mode write`,
-     run_in_background: true, timeout: 600000
-   })
-   STOP — wait for callback.
+   ✓ skill {step.skill} 加载完成 (required: {N}, deferred: {M})
    ```
-5. On callback: 把回调输出视为 step 的执行结果 → S_POST_EXEC / S_HANDLE_FAIL
+   其中 N = required_reading 引用数，M = deferred_reading 路径数（缺省块按 0 计）
+7. 计算 `effective_args`：`step.args` + (`auto ? " -y" : ""`)
+8. 按读到的指令在本会话中**内联执行**：调用允许的工具完成命令所规定的工作；执行过程中如触发 deferred_reading 引用的资源 → 按需 Read
+9. 执行结束：要求最后一段必须包含 `--- COMPLETION STATUS ---` 块（见 A_MARK_COMPLETE）
+10. Return success / failure
 
 ### A_MARK_COMPLETE
 
@@ -229,14 +218,14 @@ Write enriched args back to status.json.
      Session:  {session_id} [{source}]
      Steps:    {completed}/{total}   confirmed: {confirmed}/{completed}
 
-     [✓] 0.   maestro-plan 1            [internal · global]
-     [✓] 1.   maestro-execute 1         [internal · project]
-     [✓] 2.   maestro-verify 1          [internal · global]
+     [✓] 0.   maestro-plan 1            [global]
+     [✓] 1.   maestro-execute 1         [project]
+     [✓] 2.   maestro-verify 1          [global]
      [✓] 3. ◆ post-verify               [decision]
      ...
    ============================================================
    ```
-   Icons: `✓` confirmed, `—` skipped, `✗` failed, `◆` decision, `⚡` external
+   Icons: `✓` confirmed, `—` skipped, `✗` failed, `◆` decision
 
 </actions>
 
@@ -249,20 +238,23 @@ Write enriched args back to status.json.
 | Code | Severity | Description | Recovery |
 |------|----------|-------------|----------|
 | E001 | error | No running session found | Suggest /maestro or /maestro-ralph |
-| E002 | error | step.command_path missing for internal step | Pause, ask ralph to rebuild step |
+| E002 | error | step.command_path missing for 执行 step | Pause, ask ralph to rebuild step |
 | E003 | error | status.json corrupt | Show path, manual check |
-| E004 | error | Delegate failed + user abort | Mark paused, suggest resume |
 | E005 | error | COMPLETION STATUS block missing | Trigger NEEDS_RETRY |
+| E007 | error | required_reading file 缺失或读取失败 | List missing paths, pause session |
 | W001 | warning | Step completed with concerns | Log and continue |
+| W002 | warning | command .md 无 `<required_reading>` 标签 | 直接执行 .md 主体，跳过加载阶段 |
 
 ### Success Criteria
 
 - [ ] Session discovery covers maestro-* and ralph-*
-- [ ] `-y` parsed from args 或 session.auto_mode
+- [ ] `-y` parsed from args 或 session.auto_mode；auto=true 时透传 `-y` 到 skill args
 - [ ] Placeholders resolved；per-skill enrichment 正确
-- [ ] Decision 节点 invoke_skill("maestro-ralph") handoff
-- [ ] Internal 节点通过 read_file({step.command_path}) 内联执行，禁止 invoke_skill()
-- [ ] External 仅在显式声明时走 delegate，prompt 必带 `-y`
+- [ ] Decision 节点（`step.decision != null`）invoke_skill("maestro-ralph") handoff
+- [ ] 执行 step 通过 read_file({step.command_path}) 内联执行
+- [ ] 执行 step Read 后必须解析并加载 `<required_reading>` 引用的文件；缺失 → E007 pause
+- [ ] `<deferred_reading>` 仅记录路径到 `step.deferred_reads`，执行阶段按需 Read
+- [ ] required_reading 加载完成后输出 `✓ skill {name} 加载完成 (required: N, deferred: M)`
 - [ ] 每个 step 强制 `--- COMPLETION STATUS ---`；缺失 → NEEDS_RETRY
 - [ ] step.completion_confirmed = true 仅在 STATUS: DONE/DONE_WITH_CONCERNS 时设置
 - [ ] step.completion_evidence 记录 artifact path / 输出节选

package/.agents/skills/maestro-verify/SKILL.md

@@ -21,7 +21,7 @@ Verify execution results through three complementary methods:
 3. **Nyquist test coverage validation** — requirement-to-test mapping with gap classification
 
 Supports dual-level verification:
-- **Single plan**: `verify --dir scratch/plan-xxx` — verifies one plan, writes `verification.json` into plan dir
+- **Single plan**: `verify --dir scratch/{YYYYMMDD}-plan-xxx` — verifies one plan, writes `verification.json` into plan dir
 - **Milestone**: `verify` (no args) — aggregates all execute artifacts for current milestone into `scratch/{YYYYMMDD}-verify-M{N}-{slug}/milestone-verification.json`
 
 Registers VRF artifact in state.json on completion.