maestro-flow 0.5.35 → 0.5.36

package/.agy/agents/workflow-analyzer.md

@@ -39,6 +39,7 @@ You perform structured multi-dimensional analysis of technical topics, proposals
 - Comparison alternatives (if applicable)
 - **Codebase docs** (if `.workflow/codebase/` exists) — `ARCHITECTURE.md` and `CONCERNS.md` as evidence sources for feasibility/risk/dependency dimensions
 - **Wiki prior knowledge** (if `maestro wiki` available) — `maestro wiki search "<subject keywords>"` for prior decisions and analyses on related topics
+- **Codebase search** — prefer `maestro explore "FIND: <analysis target> SCOPE: src/ EXPECTED: file:line evidence"` over raw Grep for gathering multi-file evidence across dimensions
 
 ## Output
 `analysis.md`:

package/.agy/agents/workflow-debugger.md

@@ -49,6 +49,7 @@ Each line in evidence.ndjson:
 - **Project specs** — `maestro spec load --category debug`: known issues, root causes, workarounds. Check before forming hypotheses to avoid re-investigating known problems.
 - **Codebase docs** (if `.workflow/codebase/` exists) — Read `ARCHITECTURE.md` for module boundaries to scope impact analysis and form better hypotheses
 - **Wiki prior knowledge** (if `maestro wiki` available) — `maestro wiki search "<symptom keywords>"` for prior investigations on similar issues; skip already-documented root causes
+- **Codebase search** — prefer `maestro explore "FIND: <symptom> SCOPE: src/ ATTENTION: <error context>"` over raw Grep for multi-file evidence gathering
 
 ## Output
 - Debug session directory with:

package/.agy/agents/workflow-executor.md

@@ -66,6 +66,7 @@ You implement a single task from the execution plan. Each task is executed atomi
 - Codebase access for implementation
 - **Codebase docs** (if `.workflow/codebase/` exists) — Read `ARCHITECTURE.md` for module boundaries and component relationships before implementing cross-module changes
 - **Wiki prior knowledge** (if `maestro wiki` available) — `maestro wiki search "<task keywords>"` for related decisions/constraints that may affect implementation approach
+- **Codebase search** — prefer `maestro explore "FIND: <pattern> SCOPE: src/ EXCLUDE: tests"` over raw Grep when searching for implementation patterns or integration points
 
 ## Output
 - Code changes (the actual implementation)

package/.agy/skills/domain-add/SKILL.md

@@ -0,0 +1,68 @@
+---
+name: domain-add
+description: Register a domain term into project glossary
+argument-hint: <canonical> \"<definition>\"
+allowed-tools:
+  - grep_search
+  - run_command
+  - view_file
+  - write_to_file
+---
+<purpose>
+Register a domain term into `.workflow/domain/glossary.yaml`. Domain terms are automatically injected into agent context via hooks (domain-compact for all prompts, domain-expanded on keyword match).
+</purpose>
+
+<required_reading>
+@~/.maestro/workflows/domain-add.md
+</required_reading>
+
+<context>
+$ARGUMENTS -- expects `<canonical> "<definition>"`
+
+**Examples:**
+```bash
+/domain-add auth-token "Short-lived credential for API authentication"
+/domain-add event-bus "Central pub-sub message broker for cross-module communication"
+/domain-add 会话上下文 "Runtime state container for active workflow session"
+```
+
+Domain term lifecycle: discover/manual → register → active → (optional) deprecated → removed.
+
+**Related commands:**
+- `maestro domain list` — list all registered terms
+- `maestro domain discover` — scan codebase for term candidates
+- `maestro domain show <canonical>` — show term details
+- `maestro domain deprecate <canonical> --successor <new>` — deprecate a term
+</context>
+
+<execution>
+Follow '~/.maestro/workflows/domain-add.md' completely.
+</execution>
+
+<error_codes>
+| Code | Severity | Description | Stage |
+|------|----------|-------------|-------|
+| E001 | fatal | Canonical name and definition are both required | parse_input |
+| E002 | fatal | `.workflow/domain/` not initialized — run `maestro domain init` first | validate |
+| E003 | fatal | Term already registered with same canonical name | duplicate_check |
+| E004 | warning | Near-match found — confirm merge or create new | duplicate_check |
+</error_codes>
+
+<success_criteria>
+- [ ] Canonical name and definition parsed and validated
+- [ ] No duplicate term in glossary (or user confirmed near-match)
+- [ ] Aliases and keywords auto-extracted from definition
+- [ ] Term written to glossary.yaml with tier and relationships
+- [ ] Confirmation displayed with term details and verify command
+</success_criteria>
+
+<completion>
+### Next-step routing
+
+| Condition | Suggestion |
+|-----------|-----------|
+| Verify term added | `maestro domain show <canonical>` |
+| Add more terms | `/domain-add <canonical> "<definition>"` |
+| Discover candidates | `maestro domain discover` |
+| List all terms | `maestro domain list` |
+</completion>

package/.agy/skills/maestro/SKILL.md

@@ -40,17 +40,18 @@ $ARGUMENTS — user intent text, or special keywords.
 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 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`
+4. **Decomposition contract — maestro owns** — `source=="maestro"` 的 session 由 maestro 拥有分解契约（`decomposition_owner="maestro"`）：S_DECOMPOSE 产出 additive block (`boundary_contract`, `execution_criteria`, `task_decomposition`)，下游 ralph 只消费不覆盖（ralph A_DECOMPOSE_TASKS step 0 ownership guard 跳过二次提问）。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. **执行步骤统一通过 `maestro ralph next` 加载** — `command_scope`/`command_path` 由 `maestro ralph skills --platform agy --json --quiet` 预校验（project 覆盖 global，限定 `.claude/`）；decision 节点不走 CLI，走 `Skill("maestro-ralph")` handoff
 7. **Topology awareness** — chain catalog 含 grill / brainstorm / blueprint / analyze-macro / analyze / roadmap / plan(三路径) / execute / ...；scope_verdict 由 ralph 在 `post-analyze-scope` 决定
-8. **Grill is interactive-only** — `-y` auto mode MUST skip grill stage and route directly to brainstorm; grill requires Socratic Q&A with the user
+8. **Grill `-y` 透传** — `-y` auto mode 透传 `-y` 到 grill args（grill 自身 Auto mode 用代码代答），不删除 grill stage；grill 仍产出 grill-report/terminology/context-package 供下游 brainstorm
 9. **D-007 milestone 反查** — 数字 phase 的 `milestone_id` 由 `state.json.milestones[].phase_slugs` 反查
 10. **每个 step 必须 `completion_confirmed: true`** — 由 `maestro ralph complete N --status DONE|DONE_WITH_CONCERNS` 写入
 11. **schema** — `ralph_protocol_version: "1"` 标记 CLI-driven session；新增字段全部可选
 12. **Invariant violation = BLOCK** — 违反上述任一 invariant 即阻断当前操作，不可绕过。特别是 invariant 1（dispatch via ralph-execute）和 invariant 2（session before execution）和 invariant 10（completion_confirmed 由 CLI 写入）为硬约束。
 14. **禁止以上下文消耗为由中断执行** — harness 自动处理 context compression，以"上下文不足"或"避免 context overflow"为由中断属于 invariant violation
 13. **Classification evidence** — S_CLASSIFY 的 chain 选择决策 MUST 记录到 status.json 的 `classification_rationale` 字段：匹配了哪个 pattern、排除了哪些备选、confidence level。无记录的分类不可进入 S_CREATE。
+15. **控制权优先级（范式治理）** — FSM（maestro/maestro-ralph）独占 session 生命周期 + step 排序 + cross-step decision 节点；Pipeline（plan/execute/analyze）只拥有自身 artifact GATE，由 ralph dispatch 时 GATE 失败 → `complete BLOCKED|NEEDS_RETRY`、自身 GATE 全过 → DONE；Router（maestro-next）只单次推荐，不得出现在 FSM step 内。
 </invariants>
 
 <state_machine>
@@ -129,7 +130,7 @@ S_FALLBACK:
 1. Read `~/.maestro/workflows/maestro.md` from deferred_reading
 2. Match intent to task_type via chain catalog (semantic)
 3. Select chain from chainMap，遵循拓扑约束：
-   - 压力测试/拷问/验证假设/grill/stress-test → `grill`（**-y 模式跳过 grill，直接走 brainstorm**）
+   - 压力测试/拷问/验证假设/grill/stress-test → `grill`（**-y 模式透传 `-y` 到 grill，grill 以 Auto mode 执行，不跳过**）
    - 头脑风暴/探索 → `brainstorm`
    - 学习/阅读代码/跟读/follow → `Skill("learn-follow")`；调查/为什么/investigate → `Skill("learn-investigate")`；分解/模式/decompose → `Skill("learn-decompose")`；评审/挑战/second-opinion → `Skill("learn-second-opinion")`；回顾/retro → `Skill("quality-retrospective")`
    - 正式规格/spec-generate/7-phase → `blueprint`
@@ -147,7 +148,7 @@ S_FALLBACK:
 
 ### A_DECOMPOSE_TASKS
 
-与 maestro-ralph `A_DECOMPOSE_TASKS` 共享分解契约。Condensed:
+设 `session.decomposition_owner = "maestro"`。下游 ralph 只消费不二次提问（invariant 4）。Condensed:
 
 1. 分类意图广度。narrow / 单步 / `{status,init,quick}` 链跳过
 2. broad/medium → `ask_question` ≤3 轮：Scope / Constraints / Definition of Done
@@ -176,7 +177,7 @@ S_FALLBACK:
      "ralph_protocol_version": "1", "active_step_index": null,
      "phase", "phase_is_new": false, "milestone": "",
      "scope_verdict": null, "analyze_macro_id": null, "blueprint_id": null,
-     "auto_mode": false, "cli_tool": "claude",
+     "auto_mode": false, "decomposition_owner": "maestro", "cli_tool": "claude",
      "context": { "scratch_dir": null, "plan_dir": null, "analysis_dir": null,
        "brainstorm_dir": null, "blueprint_dir": null, "issue_id": null },
      "steps": [{
@@ -221,7 +222,7 @@ S_FALLBACK:
 
 - [ ] Intent classified with task_type, complexity, clarity_score
 - [ ] Chain catalog 覆盖 grill / brainstorm / blueprint / analyze-macro / analyze / roadmap / plan(三路径) / execute / quality pipeline
-- [ ] `-y` 模式不触发 grill（交互式压力测试不支持自动模式，跳过直接走 brainstorm）
+- [ ] `-y` 模式透传 `-y` 到 grill（grill 以 Auto mode 代码代答执行，stage 不跳过）
 - [ ] D-007: 数字 phase 步骤的 `milestone_id` 通过 `state.json.milestones[].phase_slugs` 反查
 - [ ] macro analyze 后跟 `decision:post-analyze-scope`（由 ralph 评估 scope_verdict 决定下游链路）
 - [ ] plan 支持 `{phase}` / `--from analyze:{ANL_ID}` / `--from blueprint:{BLP_ID}` 三路径；`source_artifact_ref` 写入 step

package/.agy/skills/maestro-amend/SKILL.md

@@ -11,8 +11,6 @@ allowed-tools:
 ---
 <purpose>
 Signal-driven overlay generator — collect workflow deficiency signals from multiple sources, diagnose which commands need amendment, batch-generate targeted overlays. All amendments use overlay system (`~/.maestro/overlays/*.json`) — non-invasive, idempotent, survives reinstall.
-
-Differs from `/maestro-overlay` (single explicit intent). This command **discovers** what needs amending by analyzing workflow artifacts.
 </purpose>
 
 <required_reading>

package/.agy/skills/maestro-analyze/SKILL.md

@@ -25,6 +25,7 @@ Multi-dimensional analysis of a proposal, decision, or architecture choice via C
 <deferred_reading>
 - [state.json](~/.maestro/templates/state.json) — read when registering artifact
 - [issue-gaps-analyze.md](~/.maestro/workflows/issue-gaps-analyze.md) — read when --gaps is triggered
+- [boundary-grill.md](~/.maestro/workflows/boundary-grill.md) — read when boundary conflicts detected (between Phase 4 and Phase 5)
 </deferred_reading>
 
 <context>
@@ -96,6 +97,12 @@ Every decision MUST trace to independently gathered evidence. Manual Read/Grep i
 
 Decisions without CLI/agent-sourced evidence MUST be flagged as LOW CONFIDENCE.
 
+### Boundary Grill (Step 5 → Step 6)
+
+After discussion rounds, BEFORE synthesis: run boundary grill per `~/.maestro/workflows/boundary-grill.md`.
+Input: discussion.md decisions + exploration-codebase.json. Scope guard: "only analyze decisions; do not prejudge plan/execute concerns".
+IF conflicts → results to `analysis.md` § Boundary Grill Results + update `context.md` Locked/Free/Deferred.
+
 ### Standard Mode Gates
 
 Gates 1-4 are defined in `analyze.md`. NEVER skip gates. NEVER substitute manual Read/Grep for agent/CLI exploration.
@@ -195,6 +202,8 @@ Full mode:
 - [ ] Confidence tracking initialized (Step 4.6) and re-scored each round (Step 5.8)
 - [ ] Readiness gate checked before synthesis (Step 5.10)
 - [ ] Pressure pass completed ≥ 1 time before Step 6
+- [ ] Boundary grill executed between Phase 4 and Phase 5 (skip if no conflicts detected)
+- [ ] Boundary grill results written to analysis.md § Boundary Grill Results (if conflicts found)
 - [ ] Confidence summary with factor decomposition written to analysis.md
 
 Gaps mode:

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

@@ -27,6 +27,7 @@ Pipeline: grill (optional) → **brainstorm** → roadmap / analyze / blueprint.
 - [scratch-index.json](~/.maestro/templates/scratch-index.json) — read when operating in scratch mode
 - [index.json](~/.maestro/templates/index.json) — read when operating in phase mode
 - [brainstorm-visualize.md](~/.maestro/workflows/brainstorm-visualize.md) — read when html-prototypes/ produced and user wants to browse them
+- [boundary-grill.md](~/.maestro/workflows/boundary-grill.md) — read when boundary conflicts detected (in cross-role review)
 </deferred_reading>
 
 <context>
@@ -90,8 +91,14 @@ These gates apply to Auto mode (full pipeline). Do NOT advance past a gate until
 - REQUIRED: Per-feature files `{role}/analysis-F-*.md` written for each feature in §10.
 - BLOCKED if missing: complete all role analyses before spawning cross-role-reviewer.
 
-**GATE 3: Cross-Role Review → Completion** (Step 4.5 → Report)
+**GATE 2.5: Cross-Role Review → Boundary Grill** (Step 4.5 → Step 4.6)
+Run boundary grill per `~/.maestro/workflows/boundary-grill.md` after cross-role-reviewer output.
+Input: reviewer findings + role Decision Digests. Scope guard: "only brainstorm decisions; do not pre-resolve roadmap/plan choices".
+IF conflicts → results to `guidance-specification.md` §12.5 + feed into GATE 3. NON-BLOCKING.
+
+**GATE 3: Cross-Role Review → Completion** (Step 4.5/4.6 → Report)
 - REQUIRED: Cross-role-reviewer output received with `patch_targets[]`.
+- REQUIRED: Boundary grill completed (if conflicts detected, results logged).
 - REQUIRED: If findings > 0, resolutions applied via Edit AND logged in `guidance-specification.md` §12.
 - REQUIRED: If findings == 0, final report explicitly states "No cross-role issues detected".
 - BLOCKED if missing: complete review synthesis before reporting.
@@ -193,6 +200,8 @@ Status verdicts:
 - [ ] `ui-designer/analysis.md` references DESIGN.md visual constraints when ui-designer is selected
 - [ ] Each `{role}/analysis.md` §2 Decisions table has ≥ 1 row per feature
 - [ ] Cross-role review (Step 4.5) executed; reviewer compares §2 Decision Digests; output includes `patch_targets[]` for every finding
+- [ ] Boundary grill executed after cross-role review (skip if no conflicts detected)
+- [ ] Boundary grill results written to guidance-specification.md §12.5 (if conflicts found)
 - [ ] If findings exist: each accepted resolution applied via replace_file_content(annotate / strikeout / append) AND logged in `guidance-specification.md` §12 "Cross-Role Resolutions"
 - [ ] If zero findings: final report explicitly states "No cross-role issues detected"; guidance §12 unchanged
 - [ ] Heading-drift patch failures surfaced in final report (if any)

package/.agy/skills/maestro-collab/SKILL.md

@@ -75,7 +75,12 @@ S_COLLECT:
   GUARD: 1+ succeeded → continue with partial results (W001)
 
 S_CROSS_VERIFY:
-  → S_SYNTHESIZE    DO: A_CLASSIFY_FINDINGS
+  → S_BOUNDARY_GRILL  DO: A_CLASSIFY_FINDINGS
+
+S_BOUNDARY_GRILL:
+  → S_SYNTHESIZE    WHEN: no boundary conflicts detected     DO: —
+  → S_SYNTHESIZE    WHEN: conflicts detected + resolved      DO: A_BOUNDARY_GRILL
+  GUARD: max 3 conflicts × 3 questions; non-blocking
 
 S_SYNTHESIZE:
   → S_REGISTER      DO: A_GENERATE_OUTPUTS
@@ -136,6 +141,12 @@ Read all per-tool outputs. For each finding:
 consensus_level = consensus_count / total_findings * 100.
 If consensus_level < 40%: W003.
 
+### A_BOUNDARY_GRILL
+
+Run boundary grill per `~/.maestro/workflows/boundary-grill.md`.
+Input: classified CONFLICT findings + per-tool outputs. Check upstream scope if `--from` used.
+IF conflicts → tag with resolution, feed into A_GENERATE_OUTPUTS. No conflicts → pass through.
+
 ### A_GENERATE_OUTPUTS
 
 Resolve conflicts via evidence-weighted voting:
@@ -162,6 +173,8 @@ Write 3 files:
 <success_criteria>
 - [ ] All delegates launched in parallel via run_command(run_in_background: true), STOP after launch
 - [ ] Cross-verification: consensus/conflict/unique classification with consensus_level
+- [ ] Boundary grill executed on CONFLICT items (skip if no boundary conflicts detected)
+- [ ] Boundary grill results written to collab-report.md § Boundary Grill Results (if conflicts found)
 - [ ] 3 output files produced (collab-report.md, context.md, conclusions.json)
 - [ ] CLB artifact registered in state.json
 - [ ] Partial degradation: continued if 1+ tools succeeded

package/.agy/skills/maestro-next/SKILL.md

@@ -90,9 +90,9 @@ S_FALLBACK:
 读 project state 推断 `lifecycle_position`（核心信号）：
 
 ```bash
-cat .workflow/state.json 2>$null              # phase / milestone / artifacts
-ls -la .workflow/scratch/ 2>$null | head -10  # 最近 artifact (mtime DESC)
-ls -la .workflow/.maestro/ 2>$null | head -5  # 进行中的 session
+cat .workflow/state.json 2>/dev/null              # phase / milestone / artifacts
+ls -la .workflow/scratch/ 2>/dev/null | head -10  # 最近 artifact (mtime DESC)
+ls -la .workflow/.maestro/ 2>/dev/null | head -5  # 进行中的 session
 ```
 
 **项目状态 → lifecycle_position → 自然下一步：**
@@ -108,7 +108,8 @@ ls -la .workflow/.maestro/ 2>$null | head -5  # 进行中的 session
 | 最新 artifact = plan | execute | `maestro-execute {phase}` |
 | 最新 artifact = execute | review | `quality-review {phase}` |
 | review verdict=PASS | test-gen | `quality-auto-test {phase}` |
-| 测试全绿 | milestone-audit | `maestro-milestone-audit` |
+| 测试全绿 + current_milestone 存在 | milestone-audit | `maestro-milestone-audit` |
+| 测试全绿 + current_milestone=null (standalone) | review-done | 回退到 `quality-review` 或 `manage-status`（无 milestone 上下文时不推荐 milestone 命令） |
 | 当前 milestone 全 phase 完成 | milestone-complete | `maestro-milestone-complete` |
 | 任一 stage 产物含 gaps/failed | debug | `quality-debug {gap}` |
 
@@ -131,6 +132,16 @@ brainstorm → blueprint → init → analyze-macro → roadmap
 | `name` 关键词命中 intent | 中 | intent 含 "test" → quality-test/quality-auto-test 加分 |
 | Workflow 簇匹配 | 中 | intent 涉及学习/知识/issue 等场景触发对应簇 |
 | Recent activity 反向避免 | 低 | 刚完成的 stage 短期内降权 |
+| **前置条件不满足** | **禁止** | 候选命令的前置条件未满足时，直接从候选池移除（如 `maestro-milestone-*` 在 `current_milestone=null` 时移除） |
+
+**前置条件检查（评分前执行，不满足则移除候选）：**
+
+| 命令 | 前置条件 |
+|------|---------|
+| `maestro-milestone-audit` | `current_milestone` 存在且非 null |
+| `maestro-milestone-complete` | `current_milestone` 存在且非 null |
+| `maestro-milestone-release` | `current_milestone` 存在且非 null |
+| `maestro-merge` | 存在活跃的 fork 分支 |
 
 **特殊意图处理：**
 

package/.agy/skills/maestro-overlay/SKILL.md

@@ -20,7 +20,10 @@ Turn natural-language instructions into command overlays — JSON patch files th
 </required_reading>
 
 <context>
-**Overlay model** — an overlay is a JSON file with a `name`, one or more `targets` (command names without `.md`), and a list of `patches`. Each patch targets an XML section (`execution`, `required_reading`, `context`, `success_criteria`, etc.), a mode (`append`, `prepend`, `replace`, `new-section`), and `content`. On apply, the patcher wraps the content in hashed HTML-comment markers so re-apply is idempotent and removal is surgical.
+**Overlay model**:
+- JSON file: `name`, `targets[]` (command names), `patches[]`
+- Patch: `section` (XML tag), `mode` (append/prepend/replace/new-section), `content`
+- Apply: hashed HTML-comment markers (idempotent, surgical removal)
 
 **Where overlays live**
 - User overlays: `~/.maestro/overlays/*.json` — created by this skill
@@ -138,8 +141,6 @@ Run:
 maestro overlay add ~/.maestro/overlays/<slug>.json
 ```
 
-This validates the overlay, copies it into place (idempotent), and applies it across all known install scopes. On validation failure, fix the JSON and re-run.
-
 ### 5. Report
 
 Show the user:

package/.agy/skills/maestro-plan/SKILL.md

@@ -27,6 +27,7 @@ Produces plan.json + TASK files; registers PLN artifact in state.json.
 - [plan.json](~/.maestro/templates/plan.json) — read when generating plan output
 - [task.json](~/.maestro/templates/task.json) — read when generating task files
 - [state.json](~/.maestro/templates/state.json) — read when registering artifact
+- [boundary-grill.md](~/.maestro/workflows/boundary-grill.md) — read when boundary conflicts detected (in P4)
 </deferred_reading>
 
 <context>
@@ -52,7 +53,7 @@ Scope routing, base flags (`--collab`, `--spec`, `-y`, `--gaps`, `--dir`), outpu
 
 **Ad-hoc milestone (D-008):** When scope resolves to "standalone" via the standard standalone resolution (no `--from` source), and `current_milestone == null`, plan auto-creates an adhoc milestone (`type: "adhoc"`) in state.json before proceeding. This ensures downstream milestone-audit/complete have a valid milestone context. See workflow plan.md § "Ad-hoc Milestone Auto-Creation".
 
-**Exception (`--from analyze:ANL-xxx` / `blueprint:BLP-xxx`):** When scope is set to "standalone" by `--from`, skip adhoc milestone auto-creation — the upstream analyze/blueprint artifact already provides the milestone context (or is intentionally milestone-free). Adhoc creation in this path would conflict with the `--from` semantic of "this is a one-shot plan rooted in an existing artifact".
+**`--from analyze:*` / `blueprint:*`**: scope=standalone → skip adhoc milestone auto-creation.
 
 ### Role Knowledge
 `maestro search --category arch` → select relevant → `maestro wiki load`
@@ -86,8 +87,15 @@ Follow '~/.maestro/workflows/plan.md' completely.
 - REQUIRED: Main flow inline planning is FORBIDDEN (see P3 Agent Constraint below).
 - BLOCKED if missing: plan.json or TASK files not produced by planner agent — do not proceed to checking.
 
+**GATE P3.5 → P4: Boundary Grill → Plan Check**
+Run boundary grill per `~/.maestro/workflows/boundary-grill.md`.
+Input: plan.json tasks + convergence criteria + upstream context. Scope guard: "only plan scope; do not re-analyze or re-scope".
+IF conflicts → results to plan.json `boundary_grill` section + affected TASK files. DEC conflicts add `boundary_warning` to confidence.
+NON-BLOCKING: warnings, not hard stops.
+
 **GATE P4 → P5: Plan Check → User Confirmation**
 - REQUIRED: Plan-checker passed (or minor issues acknowledged).
+- REQUIRED: Boundary grill completed (conflicts resolved or accepted as risks).
 - REQUIRED: Confidence scored with 5-dimension factor model.
 - REQUIRED: Pressure pass completed on highest-complexity task.
 - REQUIRED: If plan touches UI (检出 `dashboard/` 或 UI 关键词 `landing|page|dashboard|frontend|UI|component|界面`), each delivery wave has ≥1 `[UI-observable]` convergence criterion (vertical-slice delivery, not backend-only).
@@ -153,8 +161,6 @@ For each created TASK-{NNN}.json that has issue_id:
   Append history entry: { action: "planned", at: <ISO>, by: "maestro-plan", summary: "Linked to TASK-{NNN}" }
 ```
 
-This ensures issue → TASK traceability. The `task_refs[]` and `task_plan_dir` fields on the issue allow the dashboard to resolve and display associated TASK details.
-
 ### Mode: Revise / Check
 
 Follow workflow plan.md § "Revise Mode" and § "Check Mode" respectively. These modes bypass the standard P1-P5 create pipeline.
@@ -218,6 +224,9 @@ Status verdicts:
 - [ ] Every task has `convergence.criteria[]` with grep-verifiable conditions (no subjective language)
 - [ ] UI plans: each delivery wave has ≥1 `[UI-observable]` convergence criterion (vertical slice; verified at runtime by ralph frontend-verify gate)
 - [ ] Every task `action` and `implementation` contain concrete values (no "align X with Y")
+- [ ] Boundary grill executed in P3.5 (skip if no conflicts detected)
+- [ ] Boundary grill results written to plan.json `boundary_grill` section (if conflicts found)
+- [ ] DEC conflicts reflected in confidence `boundary_warning` factor
 - [ ] Plan confidence scored in P4 with 5-dimension factor model
 - [ ] Plan readiness gate checked before P4.5 collision detection
 - [ ] Pressure pass completed on highest-complexity task

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

@@ -20,7 +20,7 @@ $ARGUMENTS — intent text, flags, or keywords.
 
 **Parse:**
 ```
--y flag       → auto_confirm = true
+-y flag       → auto_confirm = true   # 唯一来源：用户显式传入；ralph 不内部推断（invariant 14）
 --roadmap     → wants_roadmap = true (强制多发布 roadmap 路径；roadmap 默认 opt-in)
 .md/.txt path → input_doc (supplementary context only, NEVER substitutes lifecycle stages)
 Remaining     → intent
@@ -46,6 +46,9 @@ Remaining     → intent
 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
 12. **Invariant violation = BLOCK** — 违反上述任一 invariant 即阻断当前操作。不得以 "效率" 或 "意图明确" 为由绕过。特别是 invariant 1（ralph 不执行 step）和 invariant 6（completion_confirmed 由 CLI 写入）不可隐性违反。
 13. **Delegate fallback 必须标记** — A_DELEGATE_EVALUATE 解析 verdict 失败时 fallback 为 "fix"，但 MUST 在 decisions.ndjson 记录 `"parse_failed": true, "confidence_score": 0`，后续 step 继承 LOW CONFIDENCE 标记。
+14. **auto_confirm 单一来源** — `auto_confirm` 仅由用户 `-y` 标志设定；ralph 不得内部推断。`session.auto_mode` 仅反映用户输入。
+15. **分解契约单一所有者** — `boundary_contract` / `task_decomposition` 由 session 创建者拥有（`source=="ralph"` → `decomposition_owner="ralph"`；`source=="maestro"` → `"maestro"`）。contract 已存在时，后续 S_DECOMPOSE MUST 跳过 ask_question，仅做 shape 校验 + 缺省补齐；goal-audit 只更新 `task_decomposition[*].status/completion_confirmed/completed_at`，禁止改 `goal/done_when/boundary`。
+16. **控制权优先级（范式治理）** — FSM 独占 session 生命周期 + step 排序 + retry/fix/escalate + cross-step decision 节点；Pipeline 命令只拥有自身 artifact GATE（GATE 失败 → `maestro ralph complete <idx> --status BLOCKED|NEEDS_RETRY`，自身 GATE 全过 → DONE）；Router 命令不得出现在 FSM step 内。
 </invariants>
 
 <state_machine>
@@ -135,11 +138,14 @@ S_DECISION_EVAL: (decision 节点 == `step.decision` 非空，下述 gate 名取
                      DO: A_SCOPE_EVALUATE
   → S_APPLY_VERDICT WHEN: structural (post-milestone, post-debug-escalate)
                      DO: A_STRUCTURAL_EVALUATE
+  → S_APPLY_VERDICT WHEN: reground-gate (post-reground)
+                     DO: A_REGROUND_EVALUATE
 
 S_APPLY_VERDICT:
   → S_DISPATCH      WHEN: verdict == "proceed"              DO: A_APPLY_PROCEED
-  → S_DISPATCH      WHEN: post-goal-audit + unmet sub-goals  DO: A_APPLY_GOAL_FIX
-  → S_DISPATCH      WHEN: post-goal-audit + all sub-goals met DO: A_APPLY_GOAL_DONE
+  → S_DISPATCH      WHEN: post-goal-audit + has_unmet         DO: A_APPLY_GOAL_FIX
+  → S_DISPATCH      WHEN: post-goal-audit + all_met + INTENT_ALIGNED=true  DO: A_APPLY_GOAL_DONE
+  → END             WHEN: post-goal-audit + all_met + INTENT_ALIGNED=false DO: A_REGROUND_HALT（尾部漂移熔断）
   → S_DISPATCH      WHEN: post-analyze-scope                 DO: A_APPLY_SCOPE_VERDICT
   → S_DISPATCH      WHEN: verdict == "fix"                  DO: A_APPLY_FIX
   → S_DISPATCH      WHEN: verdict == "escalate"             DO: A_APPLY_ESCALATE
@@ -147,11 +153,15 @@ S_APPLY_VERDICT:
   → END             WHEN: post-milestone + standard + no next milestone DO: mark completed
   → END             WHEN: post-milestone + adhoc                       DO: mark completed (adhoc self-contained)
   → END             WHEN: post-debug-escalate (always STOP)  DO: A_PAUSE_ESCALATE
+  → END             WHEN: post-reground + drifted + confidence_score >= 60  DO: A_REGROUND_HALT
+  → S_DISPATCH      WHEN: post-reground + aligned                           DO: A_APPLY_PROCEED
+  → S_DISPATCH      WHEN: post-reground + drifted + confidence_score < 60   DO: A_APPLY_PROCEED (标 LOW CONFIDENCE)
   GUARD: retry_count >= max_retries → force escalate
   GUARD: confidence_score < 60 AND proceed → override to fix
   GUARD: confidence_score > 95 AND fix AND retry > 0 → suggest proceed
   GUARD: auto_confirm → skip user prompt, apply adjusted verdict
   GUARD: not auto_confirm → ask_question with override options
+  GUARD: post-reground + drifted + confidence_score >= 60 → A_REGROUND_HALT（漂移熔断为安全门，auto_confirm 不跳过）
 
 S_FALLBACK:
   → S_PARSE_ROUTE   WHEN: user provides input               DO: ask_question
@@ -209,7 +219,7 @@ resolve_milestone(phase_number):
 
 | Pattern | Position |
 |---------|----------|
-| 压力测试 / 拷问 / 验证假设 / grill / stress-test | `grill`（**auto_confirm=true 时跳过，直接 `brainstorm`**） |
+| 压力测试 / 拷问 / 验证假设 / grill / stress-test | `grill`（**auto_confirm=true 时透传 `-y`，grill 以 Auto mode 代码代答，不跳过**） |
 | brainstorm / 头脑风暴 / 探索 / ideate / 设计思路 | `brainstorm` |
 | blueprint / 规格 / 正式文档 / spec-generate / 7-phase | `blueprint` |
 | broad/medium intent 无数字 phase (重构/全面/重写/迁移/新功能 X) | `analyze-macro` |
@@ -271,7 +281,8 @@ wants_roadmap = (--roadmap flag)
 | passed==true, no review.json | `business-test` |
 | review.json: verdict=="BLOCK" | `review-failed` |
 | review.json: verdict!="BLOCK" | `test` |
-| uat.md: all passed | `milestone-audit` |
+| uat.md: all passed + `session.milestone` 存在 | `milestone-audit` |
+| uat.md: all passed + `session.milestone=null` (standalone) | 标记 session completed（无 milestone 可审计） |
 | uat.md: has failures | `test-failed` |
 
 ### A_DETERMINE_QUALITY_MODE
@@ -316,7 +327,9 @@ options:
 
 ### A_DECOMPOSE_TASKS
 
-Runs once before chain build; additive to status.json.
+Runs once before chain build; additive to status.json. 设 `session.decomposition_owner = "ralph"`。
+
+**0. Ownership guard** (invariant 15): 若 `session.boundary_contract` 或 `session.task_decomposition` 已非空（上游 maestro 已写入，`decomposition_owner == "maestro"`）→ MUST 跳过下述提问，仅做 shape 校验 + 缺省字段补齐，直接进入步骤 6。
 
 **1. Classify intent breadth:**
 
@@ -353,11 +366,11 @@ narrow → derive defaults from intent + codebase, skip questions.
 
 ### A_BUILD_STEPS
 
-Generate steps from `session.lifecycle_position` to `milestone-complete`.
+Generate steps from `session.lifecycle_position` to `milestone-complete`（`session.milestone` 存在时）或最后一个质量门（standalone 时）。
 
 | Stage | Skill (independent) | Skill (unified) | Decision after | quality_mode |
 |-------|---------------------|-----------------|----------------|--------------|
-| grill | `maestro-grill "{intent}"` | *(same)* | — | all (**skip when auto_confirm**) |
+| grill | `maestro-grill "{intent}"` | *(same)* | — | all (**auto_confirm → 透传 `-y` 到 grill args，不删除 stage**) |
 | brainstorm | `maestro-brainstorm "{intent}" --from grill:{grill_id}` *(if grill ran)* / `maestro-brainstorm "{intent}"` *(otherwise)* | *(same)* | — | all |
 | blueprint | `maestro-blueprint "{intent}"` | *(same)* | — | all |
 | init | `maestro-init` | *(same)* | — | all |
@@ -385,11 +398,12 @@ 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
-3.5. **grill auto_confirm 跳过**：`auto_confirm == true` 时删除 `grill` stage（grill 为交互式苏格拉底拷问，不支持自动模式）；brainstorm args 不含 `--from grill:*`
+3.5. **grill auto_confirm 透传**：`auto_confirm == true` 时为 `grill` step args 追加 `-y`（grill 自身 Auto mode 用代码代答，见 maestro-grill `<context>` Mode selection）；保留 `grill` stage 与 brainstorm 的 `--from grill:*`（grill 仍产出 grill-report/terminology/context-package）
 3.6. **frontend-verify UI 门控**：仅当当前 phase 交付前端（检出 `dashboard/` 目录，或 phase 目标/计划含 UI 关键词 `landing|page|dashboard|frontend|UI|component|界面`）时保留 `frontend-verify` stage + `post-frontend-verify` decision；纯后端 phase 删除该 stage
 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（execute/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
+5.5. **re-grounding 插入**：当 `task_decomposition` 存在 **且** 链路含 ≥3 个执行 step（不含 decision 节点）时，从第 3 个执行 step 起每隔 3 个执行 step 后插入 `{ decision: "post-reground", retry_count: 0, max_retries: 0, command_scope: null, command_path: null }`。不在最后一个执行 step 之后插入（由 goal-audit 覆盖）；不与已有 quality-gate decision 节点相邻（顺延到下一个 3-step 边界）；fix-loop 动态插入的 step（index > 原始 chain 长度）不纳入计数
+6. **终点硬约束**：`session.milestone` 存在时 chain 以 `milestone-complete` 结尾；`session.milestone=null`（standalone）时跳过 `milestone-audit` + `milestone-complete` stage，chain 以最后一个质量门 stage 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**（每个执行 step，decision 节点跳过）：
@@ -492,14 +506,18 @@ Runs only when `task_decomposition` present.
      1. 读取 status.json.task_decomposition 中 status!=done 的子目标
      2. 打开 evidence 产物，对照 done_when 严格判定
      3. 输出 met / unmet，unmet 给出 gap + target_phase
+     4. 对照 intent + definition_of_done 判定累积产出是否仍服务原始意图（意图保真检查）
    CONTEXT:
-     status.json   = {session_dir}/status.json
-     evidence      = {evidence artifacts}
+     status.json        = {session_dir}/status.json
+     intent             = {session.intent}
+     definition_of_done = {boundary_contract.definition_of_done}
+     evidence           = {evidence artifacts}
      execution_criteria = {execution_criteria}
      boundary_contract  = {boundary_contract}
    EXPECTED:
      ---VERDICT---
      STATUS=all_met|has_unmet
+     INTENT_ALIGNED=true|false
      UNMET=[{id:G2,gap:'...',target_phase:execute}, ...]
      CONFIDENCE_SCORE=0-100
      ---END---
@@ -512,9 +530,64 @@ Runs only when `task_decomposition` present.
    ```
 4. On callback: 对每个 met 子目标，set `task_decomposition[i].status="done"` + `completion_confirmed=true` + `completed_at=now`
 5. Append `{session_dir}/decisions.ndjson` with `"type": "goal-gate"`, `unmet_count`, `unmet_ids`
-6. Verdict: `all_met` → A_APPLY_GOAL_DONE; `has_unmet` → A_APPLY_GOAL_FIX
+6. Verdict routing:
+   - `all_met` + `INTENT_ALIGNED=true` → A_APPLY_GOAL_DONE
+   - `all_met` + `INTENT_ALIGNED=false` → A_REGROUND_HALT（尾部漂移熔断，auto_confirm 不跳过）
+   - `has_unmet` → A_APPLY_GOAL_FIX
    GUARD: retry_count >= max_retries AND still unmet → A_APPLY_ESCALATE
 
+### A_REGROUND_EVALUATE
+
+仅当 `task_decomposition` 存在。周期触发（build rule 5.5）。
+
+1. 从 status.json 读取：`session.intent`、`session.boundary_contract`、`steps[]` 中 `status=="completed"` 的 step + `completion_evidence`、`task_decomposition` 中已 done 子目标的 `goal` + `done_when`
+2. Delegate read-only audit (run_in_background, STOP, wait):
+   ```
+   maestro delegate "PURPOSE: 意图保真检查 — 对照 intent 验证累积执行是否漂移
+   TASK:
+     1. 读取 intent + boundary_contract.definition_of_done
+     2. 读取已完成 steps 的 completion_evidence + 已 done 子目标 done_when
+     3. 判定累积产出是否仍服务 intent；是否有 step 产出超出 in_scope 或触碰 out_of_scope
+     4. 输出 aligned / drifted，drifted 给出 drift_description + corrective_action
+   CONTEXT:
+     intent             = {session.intent}
+     definition_of_done = {boundary_contract.definition_of_done}
+     in_scope           = {boundary_contract.in_scope}
+     out_of_scope       = {boundary_contract.out_of_scope}
+     completed_steps    = [{index, skill, stage, completion_evidence}, ...]
+     done_goals         = [{id, goal, done_when}, ...]
+   EXPECTED:
+     ---VERDICT---
+     STATUS=aligned|drifted
+     DRIFT_DESCRIPTION=<空或具体描述>
+     CORRECTIVE_ACTION=<空或建议>
+     CONFIDENCE_SCORE=0-100
+     ---END---
+   CONSTRAINTS:
+     - 只评估，不修改文件
+     - aligned 阈值：≥80% 已完成产出直接服务 intent
+     - 单个 step 触碰 out_of_scope → 直接判 drifted"
+   --role analyze --mode analysis
+   ```
+3. On callback: parse verdict
+4. Append `{session_dir}/decisions.ndjson`：`{ "id": "DEC-{ts}", "type": "reground-gate", "source": "ralph", "node_id": "post-reground", "verdict": "{aligned|drifted}", "confidence_score": {N}, "drift_description": "...", "corrective_action": "..." }`
+5. Verdict routing：`aligned` → A_APPLY_PROCEED；`drifted` + `confidence_score >= 60` → A_REGROUND_HALT；`drifted` + `confidence_score < 60` → A_APPLY_PROCEED（标 LOW CONFIDENCE）
+
+### A_REGROUND_HALT
+
+漂移熔断（安全门，auto_confirm 不跳过）。
+
+1. Set `session.status = "paused"`，write status.json
+2. Display:
+   ```
+   ⚠️ Re-grounding 检测失败 — 执行已偏离 intent。
+   Intent: {session.intent}
+   Drift:  {drift_description}
+   建议回归: {corrective_action}
+   选项：1) /maestro-ralph continue 忽略漂移继续  2) 手动修正后 continue  3) /maestro-ralph status 查看后决定
+   ```
+3. GUARD: auto_confirm 对本动作无效——漂移熔断不可自动跳过
+
 ### A_APPLY_PROCEED
 
 1. Mark decision completed, write status.json
@@ -589,6 +662,8 @@ Runs only when `task_decomposition` present.
   "phase": null, "phase_is_new": false,
   "milestone": "",                // D-007 反查结果，禁止读 current_milestone
   "auto_mode": false,
+  "decomposition_owner": "ralph", // 分解契约所有者（invariant 15）；缺省按 source 推断
+
   "quality_mode": "standard",     // "full" | "standard" | "quick"
   "planning_mode": "independent", // "unified" | "independent"
   "scope_verdict": null,          // "large" | "medium" | "small" | "unknown" | null
@@ -739,7 +814,7 @@ decision:post-goal-audit {retry+1}
 - [ ] D-007 反查：phase 数字 → `session.milestone`，禁止读 current_milestone；写入 step.milestone_id
 - [ ] phase_is_new=true → lifecycle_position 强制 `analyze`
 - [ ] Intent overrides 识别 grill / brainstorm / blueprint / analyze-macro
-- [ ] auto_confirm=true 时 grill stage 跳过（交互式拷问不支持自动模式）
+- [ ] auto_confirm=true 时 grill step args 追加 `-y`（grill 以 Auto mode 执行，stage 不跳过，产出 grill-report/terminology/context-package）
 - [ ] A_RESOLVE_SCOPE_VERDICT 读 macro analyze conclusions.scope_verdict，写入 session.scope_verdict + analyze_macro_id
 - [ ] 链路起点 = analyze-macro 时：large+wants_roadmap→roadmap+analyze+plan(phase)；其余(含 large 默认/medium/small)→直跳 plan --from analyze:{ANL_ID}（跳过 roadmap+analyze）
 - [ ] post-analyze-scope decision 节点在 macro analyze 之后插入；A_SCOPE_EVALUATE/A_APPLY_SCOPE_VERDICT 重塑链路

package/.agy/skills/maestro-tools-register/SKILL.md

@@ -70,12 +70,8 @@ Parse $ARGUMENTS to determine mode:
 - Update frontmatter via: `maestro wiki update <id> --frontmatter '{"tool": true, "category": "<cat>", "summary": "<summary>"}'`
 - Do NOT recreate the document — modify in place
 
-**For all modes** — identify the usage timing: when should an agent or user invoke this tool? This becomes the first line of the entry description (see Step 5).
-
 ### Step 3: Determine Category
 
-**Core principle**: `category` = **who consumes this tool** (which agent type discovers and uses it), not what the content is about.
-
 | Category | Consumer Agent | Decision Question | Signal Words |
 |---|---|---|---|
 | `coding` | code-developer, workflow-executor | 开发者实现时需要这个流程吗？ | build, deploy, integrate, configure, setup, migrate, api-contract |
@@ -89,8 +85,6 @@ Parse $ARGUMENTS to determine mode:
 - API verification steps (how to test) → `category: test` (RCP-*, tool: true)
 - Ask user when ambiguous: "This tool content serves both developers and testers. Split into separate documents?"
 
-**Ambiguous cases**: Choose the **primary consumer** — the agent that would fail without this knowledge.
-
 ### Step 4: Decide Inline vs Ref
 
 - Steps <10 and no code blocks → **inline mode**

package/.agy/skills/maestro-ui-codify/SKILL.md

@@ -44,8 +44,6 @@ Load project UI conventions before extracting design system:
 maestro spec load --category ui
 ```
 
-If specs not initialized, continue without — the workflow still produces valid output.
-
 ## 2. Execute Workflow
 
 Route to `~/.maestro/workflows/ui-codify.md` and follow completely.