maestro-flow 0.5.40 → 0.5.42

package/.codex/skills/odyssey-ui/SKILL.md

@@ -1,86 +1,73 @@
 ---
 name: odyssey-ui
-description: "Long-running UI optimization cycle — visual survey, multi-dimensional audit, divergent exploration, fix, verify, generalize, and design knowledge persistence"
+description: "Long-running UI optimization cycle — visual survey, multi-dimensional audit, divergent exploration, fix, verify, generalize, discover, and design knowledge persistence"
 argument-hint: '"<target>" [--dimensions <list>] [--skip-fix] [--skip-generalize] [--auto] [-y] [-c] [--heartbeat]'
 allowed-tools: spawn_agents_on_csv, Read, Write, Edit, Bash, Glob, Grep, request_user_input
 ---
 
-<base>@~/.maestro/workflows/odyssey-base.md</base>
+<base>@~/.maestro/workflows/odyssey-base-codex.md</base>
 
 <purpose>
-Deep UI polish cycle: survey → 6-dimension audit → divergent creative exploration →
-fix → verify → generalize → discover → persist. Every pixel is a learning opportunity.
-
-Core philosophy:
-- **Every pixel tells a story** — subtle details create the experience
-- **Diverge before converge** — explore creatively, then implement methodically
-- **Find one, polish all** — a single improvement reveals a class of opportunities
-- **Browser is truth** — verify in real rendering, not just code
-
-**三句哲学约束（穷尽迭代）:**
-1. **零遗留** — 每个 finding/idea 必须是 action item（修复 / issue / 决策），不允许只报告不处理
-2. **穷尽迭代** — 按 impact×severity 递降逐轮修复，直到 0 remaining actionable 才退出 fix loop
-3. **改进即标准** — 每次修复后重审同区域，发现新视觉问题继续修，直到该区域无可改善
+survey -> 6-dimension audit -> divergent creative exploration ->
+fix -> verify -> generalize -> discover -> persist.
+Exhaustive iteration until all findings addressed or deferred.
 </purpose>
 
 <boundary>
-**范围内:** 目标组件/页面的视觉体验优化 — 审查 6 维度 → 发散探索 → 修复 → 泛化到兄弟组件
-**范围外:** 后端逻辑 / 数据模型 / API 设计 / 业务规则 → `$odyssey-planex` | 深度 bug 调查 → `$odyssey-debug` | 代码质量审查 → `$odyssey-review-test-fix`
-**探索自由度:** 边界内最大自由 — S_DIVERGE 阶段鼓励发散思维，不设创意上限。审查 + 发散可发现任何视觉/交互/可访问性细节。在约束下尽可能完善每个像素。
-**Zero-residual principle:** Every finding/idea MUST have a concrete action (fix / issue / decision). "Report and shelve" is not allowed. "Pre-existing design debt" is not a valid skip reason — if discovered within scope, it must be addressed.
-⚠️ **Decision gate** — ONLY these qualify as decisions (not fixes):
-  - Brand/style direction requiring human creative judgment
-  - Layout restructuring that changes user flow significantly
-  - Requires new design tokens or breaking component API
-❌ "Unsure how to fix", "Large scope", "Pre-existing issue" are NOT valid decision reasons — either fix it, or explain specifically why it's unfixable
+**In scope:** Target component/page visual experience optimization -- audit 6 dimensions -> divergent exploration -> fix -> generalize to sibling components.
+**Out of scope:** Backend logic / data model / API design -> `$odyssey-planex` | Deep bug investigation -> `$odyssey-debug` | Code quality review -> `$odyssey-review-test-fix`
+
+**Exploration freedom:** Maximum freedom within boundary -- S_DIVERGE encourages divergent thinking with no creative ceiling. Audit + diverge may discover any visual/interaction/accessibility detail.
+**Zero-residual:** Every finding/idea MUST have a concrete action (fix / issue / decision). "Pre-existing design debt" is not a valid skip reason.
+
+**Decision gate** -- ONLY these qualify as decisions (not fixes):
+- Brand/style direction requiring human creative judgment
+- Layout restructuring that changes user flow significantly
+- Requires new design tokens or breaking component API
 </boundary>
 
 <context>
-$ARGUMENTS — target and optional flags.
+$ARGUMENTS
 
-**Target resolution:** Component path → audit component | Page/route → audit page | `staged`/`HEAD` → diff UI changes | Feature area → resolve to components/pages
+**Target resolution:** Component path -> audit component | Page/route -> audit page | `staged`/`HEAD` -> diff UI changes | Feature area -> resolve to components/pages
 
-**Flags:**
-| Flag | Effect | Default |
-|------|--------|---------|
-| `--dimensions <list>` | Comma-separated subset of 6 dimensions | all 6 |
-| `--fix-threshold <severity>` | 修复到哪个 severity 为止 | all |
-| `--skip-fix` | Audit + diverge only, no code changes | false |
-| `--skip-generalize` | Skip S_GENERALIZE and S_DISCOVER | false |
-| `--auto` | CLI delegates without confirmation | false |
-| `-y` | Auto-confirm all decisions (see appendix) | false |
-| `-c` | Resume most recent session | — |
-| `--heartbeat` | Enable heartbeat progress reporting | false |
+**Flags:** `--dimensions <list>` subset of 6 dims | `--fix-threshold <severity>` | `--skip-fix` audit+diverge only | `--skip-generalize` skip S_GENERALIZE+S_DISCOVER | `--auto` no delegate confirmation | `-y` auto-confirm | `-c` resume | `--heartbeat` /loop heartbeat
 
-**Session**: `SESSION_DIR = .workflow/scratch/{YYYYMMDD}-ui-odyssey-{slug}/`
+**Session**: `.workflow/scratch/{YYYYMMDD}-ui-odyssey-{slug}/`
+**Output**: `session.json` | `evidence.ndjson` | `understanding.md`
 
-**Output — 3 files:** `session.json` (state + audit/diverge results + patterns + phase_goals) | `evidence.ndjson` (phases: survey, audit, diverge, fix, discovery, decision, self-iteration) | `understanding.md` (8-section narrative)
+**session.json -- ui-specific fields:**
+```json
+{ "target": "", "dimensions": [], "audit_result": null, "diverge_result": null,
+  "patterns": [], "confirmation": null, "generalization_stats": null }
+```
 
-**session.json unique fields:** `target`, `dimensions`, `audit_result` {dimensions_audited, finding_count, severity_distribution}, `diverge_result` {improvements_proposed, creative_ideas}, `patterns[]` {id, source_finding, layer, signature, description, risk, fix_template, confidence}, `confirmation` {test_result, cli_review, overall}, `generalization_stats` {patterns_extracted, total_hits, cross_layer_confirmed, regression_risks, by_layer, deepening_triggered}
+**evidence.ndjson phases:** `survey|audit|diverge|fix|discovery|decision|self-iteration`
 
 **phase_goals[]:**
+
 | ID | Goal | Phase | skip_when |
 |----|------|-------|-----------|
-| G1 | Survey completed | S_SURVEY | — |
-| G2 | Audit completed | S_AUDIT | — |
-| G3 | Divergent exploration done | S_DIVERGE | — |
+| G1 | Survey completed | S_SURVEY | -- |
+| G2 | Audit completed | S_AUDIT | -- |
+| G3 | Divergent exploration done | S_DIVERGE | -- |
 | G4 | Zero remaining: all findings/ideas fixed and verified | S_VERIFY | skip_fix |
 | G5 | Pattern generalized | S_GENERALIZE | skip_generalize |
 | G6 | Discoveries triaged | S_DISCOVER | skip_generalize |
-| G7 | Learnings persisted | S_RECORD | — |
+| G7 | Learnings persisted | S_RECORD | -- |
 
-**understanding.md:** §1 Target & Design Context | §2 Survey | §3 Audit | §4 Diverge | §5 Verify | §6 Generalize | §7 Discover | §8 Learnings
+**understanding.md -- 8 sections:**
+1. Target & Design Context <- S_INTAKE | 2. Survey <- S_SURVEY | 3. Audit <- S_AUDIT | 4. Diverge <- S_DIVERGE
+5. Verify <- S_VERIFY | 6. Generalize <- S_GENERALIZE | 7. Discover <- S_DISCOVER | 8. Learnings <- S_RECORD
 
-### Pre-load（可选，缺失不阻塞）
-ARCHITECTURE.md | `maestro search "<target>" --json` (top 5) | `maestro load --type spec --category ui` | `maestro load --type spec --category coding` | `maestro search --category ui` → load knowhow | Glob prior sessions
+**Knowledge Persistence (S_RECORD writes understanding.md section 8):**
 
-### Knowledge Persistence（S_RECORD 写入 understanding.md §8）
-| 分类 | 写入内容 | 后续建议命令 |
-|------|---------|-------------|
-| 设计 pattern | 组件模式 + 适用场景 + token 引用 | `/spec-add ui "..."` |
-| 交互规范 | 状态定义 + 转场规则 + 反馈模式 | `/spec-add ui "..."` |
-| 可访问性规则 | WCAG 要求 + 实现方案 | `/spec-add ui "..."` |
-| 可复用泛化 pattern | pattern 签名 + 应用范围 | `/spec-add coding "..."` |
+| Category | Content | Follow-up |
+|----------|---------|-----------|
+| Design pattern | Component pattern + applicable scenarios + token references | `/spec-add ui "..."` |
+| Interaction spec | State definitions + transition rules + feedback patterns | `/spec-add ui "..."` |
+| Accessibility rules | WCAG requirements + implementation approach | `/spec-add ui "..."` |
+| Reusable generalization pattern | Pattern signature + application scope | `/spec-add coding "..."` |
 </context>
 
 <csv_schema>
@@ -116,68 +103,62 @@ id,title,description,task_type,dimension,deps,wave,status,findings,evidence,erro
 | 4 | Generalization (syntax-grep, semantic-scan, structural-match, historical-grep) | 4 agents |
 </csv_schema>
 
+<invariants>
+1-5: See base (evidence append-only, session is state, phase goal tracking, auto-commit, zero silent drops).
+6. **Browser is truth** -- verify in real rendering, not just code review
+7. **Diverge before converge** -- explore creatively first, then implement methodically
+</invariants>
+
 <self_iteration>
-适用阶段: S_SURVEY, S_AUDIT, S_DIVERGE, S_GENERALIZE
+Applies to: **S_SURVEY, S_AUDIT, S_DIVERGE, S_GENERALIZE**. Logic in base.
 </self_iteration>
 
 <state_machine>
 
 <states>
-S_INTAKE     — Parse target, load design context, resume session           PERSIST: session.json + understanding.md §1
-S_SURVEY     — Visual landscape: design tokens, pattern inventory          PERSIST: evidence.ndjson (survey) + understanding.md §2
-S_AUDIT      — 6-dimension parallel review                                 PERSIST: evidence.ndjson (audit) + understanding.md §3
-S_DIVERGE    — Divergent creative exploration: polish + delight            PERSIST: evidence.ndjson (diverge) + understanding.md §4
-S_FIX        — Implement improvements (skip if --skip-fix)                 PERSIST: code changes + evidence.ndjson (fix)
-S_VERIFY     — Visual verification + test (skip if --skip-fix)             PERSIST: session.json.confirmation + understanding.md §5
-S_GENERALIZE — Pattern extraction + 4-agent scan (skip if --skip-gen)      PERSIST: session.json.patterns + understanding.md §6
-S_DISCOVER   — Classify hits, create issues (skip if --skip-gen)           PERSIST: evidence.ndjson (discovery|decision) + understanding.md §7
-S_RECORD     — Design knowledge persistence + final report                 PERSIST: understanding.md §8 + spec entries
+S_INTAKE -> S_SURVEY -> S_AUDIT -> S_DIVERGE -> S_FIX -> S_VERIFY -> S_GENERALIZE -> S_DISCOVER -> S_RECORD -> END
 </states>
 
 <transitions>
-S_INTAKE:
-  → S_INTAKE      WHEN -c + session found        DO A_RESUME
-  → S_SURVEY      WHEN target resolved            DO A_INTAKE
-  → S_INTAKE      WHEN no target                  DO request_user_input
-
-S_SURVEY       → S_AUDIT        DO A_SURVEY
-S_AUDIT        → S_DIVERGE      DO A_AUDIT
-
-S_DIVERGE:
-  → S_FIX          WHEN !skip_fix AND actionable findings/ideas           DO A_DIVERGE
-  → S_GENERALIZE   WHEN (skip_fix OR no actionable) AND !skip_gen        DO A_DIVERGE
-  → S_RECORD       WHEN (skip_fix OR no actionable) AND skip_gen         DO A_DIVERGE
-
-S_FIX          → S_VERIFY       DO A_FIX
-S_VERIFY:
-  → S_GENERALIZE   WHEN verified AND !skip_gen    DO A_VERIFY
-  → S_RECORD       WHEN verified AND skip_gen     DO A_VERIFY
-  → S_FIX          WHEN needs_rework              DO A_VERIFY
-
-S_GENERALIZE:
-  → S_DISCOVER     WHEN hits found                DO A_GENERALIZE
-  → S_RECORD       WHEN no hits                   DO A_GENERALIZE
-
-S_DISCOVER → S_AUDIT  : new component to audit → cross_phase_loops++
-S_DISCOVER → S_FIX    : fixable sibling, !skip_fix → cross_phase_loops++
-S_DISCOVER → S_RECORD : remaining_actionable == 0 OR loops >= max_loops (MUST log each unfixed item)
-
-S_RECORD   → END      DO A_RECORD
+S_INTAKE -> S_INTAKE       : -c + session found -> A_RESUME
+S_INTAKE -> S_SURVEY       : target resolved -> A_INTAKE
+S_INTAKE -> S_INTAKE       : no target -> request_user_input
+
+S_SURVEY  -> S_AUDIT       : complete
+S_AUDIT   -> S_DIVERGE     : complete
+
+S_DIVERGE -> S_FIX          : !skip_fix AND actionable findings/ideas
+S_DIVERGE -> S_GENERALIZE   : (skip_fix OR no actionable) AND !skip_gen
+S_DIVERGE -> S_RECORD       : (skip_fix OR no actionable) AND skip_gen
+
+S_FIX     -> S_VERIFY       : fix implemented
+S_VERIFY  -> S_GENERALIZE   : verified AND !skip_gen
+S_VERIFY  -> S_RECORD       : verified AND skip_gen
+S_VERIFY  -> S_FIX          : needs_rework
+
+S_GENERALIZE -> S_DISCOVER  : hits found
+S_GENERALIZE -> S_RECORD    : no hits
+
+S_DISCOVER -> S_AUDIT       : new component to audit -> cross_phase_loops++
+S_DISCOVER -> S_FIX         : fixable sibling, !skip_fix -> cross_phase_loops++
+S_DISCOVER -> S_RECORD      : remaining_actionable == 0 OR loops >= max_loops (log per-item reasons)
+
+S_RECORD   -> END           : complete
 </transitions>
 
 <actions>
 
 ### A_INTAKE
 1. Parse arguments: target, flags, `--dimensions` subset
-2. Generate slug, create `SESSION_DIR`
-3. Pre-load: `maestro search` + Glob prior sessions + ARCHITECTURE.md + spec load ui/coding
+2. Generate slug, create SESSION_DIR
+3. `maestro search` + Glob prior sessions + ARCHITECTURE.md + spec load ui/coding
 4. Derive `phase_goals[]` from flags (apply `skip_when`)
-5. Write `session.json` + `understanding.md` §1
-6. Emit Goal Prompt (see Appendix)
-📌 `git commit -m "odyssey-ui({slug}): INTAKE — 目标解析"`
+5. Write `session.json` + `understanding.md` section 1, emit Goal Prompt
+
+Commit: `"odyssey-ui({slug}): INTAKE -- target parsed"`
 
 ### A_RESUME
-Find latest session via Glob → read `session.json` → display summary → jump to `current_state`.
+Glob latest session -> read `session.json` -> jump to `current_state`.
 
 ### A_SURVEY
 **spawn_agents_on_csv (Wave 1):**
@@ -189,11 +170,11 @@ Write `tasks.csv` with Wave 1 rows:
 ```
 `spawn_agents_on_csv({ csv_path:"tasks.csv", max_concurrency:2, max_runtime_seconds:300, output_csv_path:"wave-1-results.csv", output_schema:SHARED_OUTPUT_SCHEMA })`
 
-Merge → evidence.ndjson (phase: "survey"). Update §2. Mark G1 done.
-📌 `git commit -m "odyssey-ui({slug}): SURVEY — 视觉调查"`
+Merge -> evidence (phase: "survey"). Update section 2. Mark G1 done.
+Commit: `"odyssey-ui({slug}): SURVEY -- visual landscape"`
 
 ### A_AUDIT
-**spawn_agents_on_csv (Wave 2)** — 6 agents (one per dimension, or `--dimensions` subset):
+**spawn_agents_on_csv (Wave 2)** -- 6 agents (one per dimension, or `--dimensions` subset):
 
 Append Wave 2 rows to `tasks.csv`:
 ```csv
@@ -207,11 +188,11 @@ Append Wave 2 rows to `tasks.csv`:
 `spawn_agents_on_csv({ csv_path:"tasks.csv", max_concurrency:6, max_runtime_seconds:600, output_csv_path:"wave-2-results.csv", output_schema:SHARED_OUTPUT_SCHEMA })`
 
 Each returns `[{title, severity, file, line, description, suggestion, dimension}]`.
-Merge → evidence (phase: "audit"). Write `audit_result` with dimensions, finding count, severity distribution. Update §3 (severity matrix). Mark G2 done.
-📌 `git commit -m "odyssey-ui({slug}): AUDIT — 多维审查"`
+Merge -> evidence (phase: "audit"). Write `audit_result` with dimensions, finding count, severity distribution. Update section 3 (severity matrix). Mark G2 done.
+Commit: `"odyssey-ui({slug}): AUDIT -- 6-dimension review"`
 
 ### A_DIVERGE
-**spawn_agents_on_csv (Wave 3)** — 2 agents:
+**spawn_agents_on_csv (Wave 3)** -- 2 agents:
 
 Append Wave 3 rows to `tasks.csv`:
 ```csv
@@ -231,36 +212,28 @@ CONSTRAINTS: User-perceptible improvements only
 ```
 Execute with `run_in_background: true`, then wait for callback.
 
-Consolidate: audit findings + divergent ideas → prioritized improvement list (impact/effort matrix). Write `diverge_result`. Append evidence (phase: "diverge"). Update §4. Mark G3 done.
-📌 `git commit -m "odyssey-ui({slug}): DIVERGE — 发散探索"`
+Consolidate: audit findings + divergent ideas -> prioritized improvement list (impact/effort matrix). Write `diverge_result`. Append evidence (phase: "diverge"). Update section 4. Mark G3 done.
+Commit: `"odyssey-ui({slug}): DIVERGE -- creative exploration"`
 
 ### A_FIX
 Skip if `--skip-fix`.
-1. **穷尽修复**: ALL findings/ideas by priority tier (critical→high→medium→low + high-impact ideas). After each tier, re-review — new findings append.
-2. Each fix → evidence (phase: "fix")
-3. **Normal**: request_user_input per-fix. **`-y`**: auto-proceed, record `deferred`.
-📌 `git commit -m "odyssey-ui({slug}): FIX — 优化实现"`
+1. **Exhaustive fix**: ALL findings/ideas by priority tier (critical->high->medium->low + high-impact ideas). After each tier, re-review -- new findings append.
+2. Each fix -> evidence (phase: "fix")
+3. Normal: request_user_input per-fix. `-y`: auto-proceed, record `deferred`.
+
+Commit: `"odyssey-ui({slug}): FIX -- improvements applied"`
 
 ### A_VERIFY
 1. Run tests (lint, unit, visual regression)
-2. **CLI-assisted**: `maestro delegate` with `--role review` — visual correctness, interaction states, accessibility, responsive
-3. `needs_rework` → S_FIX. `verified` → mark G4 done. Update §5, write `confirmation`.
-📌 `git commit -m "odyssey-ui({slug}): VERIFY — 验证"`
+2. CLI-assisted: `maestro delegate --role review` -- visual correctness, interaction states, accessibility, responsive
+3. `needs_rework` -> S_FIX. `verified` -> mark G4 done. Update section 5, write `confirmation`.
 
-### A_GENERALIZE
-Skip if `--skip-generalize`. Pattern 来源: audit findings + diverge ideas (severity >= medium OR impact = high)。
-
-**Step 1 — Multi-layer pattern extraction:**
+Commit: `"odyssey-ui({slug}): VERIFY -- visual verification"`
 
-| Layer | Method | Example |
-|-------|--------|---------|
-| Syntax | Regex patterns (direct Grep) | Missing `focus-visible`, hardcoded colors, `!important` |
-| Semantic | Agent anti-pattern scan | Missing hover state on interactive element, no empty state |
-| Structural | File/module similarity | Same component structure missing accessibility attrs |
-
-Write `session.json.patterns[]`: `[{id, source_finding, layer, signature, description, risk, fix_template}]`
+### A_GENERALIZE
+Skip if `--skip-generalize`. Pattern source: audit findings + diverge ideas (severity >= medium OR impact = high).
 
-**Step 2 — 4-agent scan (spawn_agents_on_csv, Wave 4):**
+**Wave 4 -- 4-agent scan (spawn_agents_on_csv):**
 
 Append Wave 4 rows to `tasks.csv`:
 ```csv
@@ -271,66 +244,48 @@ Append Wave 4 rows to `tasks.csv`:
 ```
 `spawn_agents_on_csv({ csv_path:"tasks.csv", max_concurrency:4, max_runtime_seconds:600, output_csv_path:"wave-4-results.csv", output_schema:SHARED_OUTPUT_SCHEMA })`
 
-**Step 3 — Cross-layer dedup**: Multi-layer hit → boost confidence. Single → `needs_review`. Historical fix → `regression_risk`.
-
-**Step 4 — Iterative deepening**: module ≥3 hits → targeted deep scan. Max 1 round.
-
-**Step 5 — Quality Gate** (self-iteration).
-
-**Step 6:** Write `generalization_stats`. Update §6. Mark G5 done.
-📌 `git commit -m "odyssey-ui({slug}): GENERALIZE — 泛化扫描"`
+Cross-layer dedup + iterative deepening per base. Update section 6. Mark G5 done.
+Commit: `"odyssey-ui({slug}): GENERALIZE -- pattern scan"`
 
-### A_DISCOVER
-按 base A_DISCOVER 执行。Mark G6 done.
-📌 `git commit -m "odyssey-ui({slug}): DISCOVER — 发现分类"`
+### A_DISCOVER, A_RECORD
+Base shared_actions. UI overrides:
+- **A_DISCOVER** routing per base triage logic
+- **A_RECORD** learnings per Knowledge Persistence table
 
-### A_RECORD
-1. Finalize §8: 按 Knowledge Persistence 表分类记录，completion summary 列出建议的 `/spec-add` 命令
-2. Pending decisions: **Normal** → request_user_input. **`-y`** → skip, show deferred count
-3. Goal audit: all confirmed → `phase_goals_all_done = true`. **Normal** → request_user_input | **`-y`** → auto accept
-4. Mark G7 done. Emit completion summary:
+**Completion summary:**
 ```
 --- UI ODYSSEY COMPLETE ---
-Target: {target} | Dimensions: {dimensions_audited}
-Findings: {C}C {H}H {M}M {L}L | Diverge: {improvements} polish + {creative} delight
-Fix: {fixed_count} applied, verified={yes|skipped}
-Patterns: {extracted} ({by_layer}) | Scan hits: {total} ({cross_layer} cross-layer)
-Issues: {N} | Decisions: {N} resolved, {M} pending, {K} deferred
-Learnings: {N} entries | Self-iter: {N} rounds | Goals: {done}/{total} ({skipped} skipped)
+Target:     {target} | Dimensions: {dimensions_audited}
+Findings:   {C}C {H}H {M}M {L}L | Diverge: {improvements} polish + {creative} delight
+Fix:        {fixed_count} applied, verified={yes|skipped}
+Patterns:   {extracted} ({by_layer})
+Scan hits:  {total} ({cross_layer} cross-layer)
+Issues:     {N} created
+Decisions:  {N} resolved, {M} pending, {K} deferred
+Learnings:  {N} entries
+Self-iter:  {N} rounds
+Goals:      {done}/{total} ({skipped} skipped)
 ---
 ```
-📌 `git commit -m "odyssey-ui({slug}): RECORD — 会话总结"`
 
 </actions>
 
 <appendix>
 
-### Goal Prompt Template
-**⚠️ 仅在 A_INTAKE 完成后显示一次。A_RECORD 完成时禁止重新显示。**
+### `-y` ui-specific points
 
-```
-📋 UI Odyssey 会话已创建。可随时复制以下 /goal 设定终止条件：
-
-/goal 完成以下目标：
-{for each G in phase_goals where status != "skipped":}
-- {G.id}: {G.goal} — 完成条件: {G.done_when}
-{end for}
-穷尽迭代：直到 audit + diverge findings 均已处理（fix/issue/decision）
-且 phase_goals_all_done=true 才停。修复按 impact×severity 逐轮迭代。
-每轮修复后重审修改区域，新发现追加继续修。
-遇到 phase=decision 的 pending 必须 request_user_input。不允许"只报告不处理"。
-```
-
-### `-y` Auto-Confirm (5 decision points)
 | Decision Point | Normal | `-y` |
 |----------------|--------|------|
 | A_FIX improvement confirmation | request_user_input | auto-proceed, `deferred` |
-| A_DISCOVER hit routing | request_user_input | auto create issue, `deferred` |
-| A_DISCOVER ambiguous items | request_user_input | all `deferred` |
-| A_RECORD pending decisions | request_user_input | skip, show deferred count |
-| A_RECORD goal audit | request_user_input | auto accept |
 
-`deferred` → "待决策" in completion summary; recoverable via `-c`.
+### Goal Prompt convergence rules
+
+```
+Exhaustive iteration: process all audit + diverge findings (fix/issue/decision)
+until phase_goals_all_done=true. Fix by impact x severity per tier.
+Re-review modified areas after each fix round -- new findings appended.
+phase=decision pending items MUST request_user_input. No report-only items.
+```
 
 </appendix>
 
@@ -350,15 +305,15 @@ Learnings: {N} entries | Self-iter: {N} rounds | Goals: {done}/{total} ({skipped
 - [ ] Improvements implemented and verified (unless --skip-fix)
 - [ ] Multi-layer generalization + discoveries classified (unless --skip-generalize)
 - [ ] Every unfixed finding has individual classification and reason
-- [ ] understanding.md §8 finalized; phase_goals G1-G7 tracked; `-y` no blocking prompts
+- [ ] understanding.md section 8 finalized; phase_goals G1-G7 tracked; `-y` no blocking prompts
 </success_criteria>
 
 <next_step_routing>
-| Condition | Next step |
-|-----------|-----------|
+| Condition | Next |
+|-----------|------|
 | Finding needs deeper debug | `$odyssey-debug "<finding>"` |
 | Issues created from discoveries | `/manage-issue list --source ui-odyssey` |
 | Design pattern worth documenting | `/spec-add ui "..."` |
-| Want full review of changes | `$odyssey-review-test-fix <changed-files>` |
+| Full review of changes | `$odyssey-review-test-fix <changed-files>` |
 | Sibling components to polish | `$odyssey-ui "<sibling>"` |
 </next_step_routing>

package/dashboard/dist-server/src/commands/install-backend.js

@@ -732,6 +732,33 @@ function legacyCleanup(manifest, result) {
 // ---------------------------------------------------------------------------
 // Codex skill deduplication — disable .agents/ skills in codex config
 // ---------------------------------------------------------------------------
+const DEDUPE_START = '# maestro:dedupe-agents-start';
+const DEDUPE_END = '# maestro:dedupe-agents-end';
+/**
+ * Strip ALL maestro-managed dedupe blocks, orphaned markers, and orphaned
+ * .agents/skills entries from codex config content.  Handles corruption left
+ * by older versions where indexOf(END) found an orphan before START.
+ */
+function stripDedupeBlocks(content) {
+    let cleaned = content;
+    // 1. Remove properly-formed START...END blocks (search END only AFTER START)
+    for (;;) {
+        const si = cleaned.indexOf(DEDUPE_START);
+        if (si === -1)
+            break;
+        const ei = cleaned.indexOf(DEDUPE_END, si);
+        if (ei === -1) {
+            cleaned = cleaned.slice(0, si) + cleaned.slice(si + DEDUPE_START.length);
+            break;
+        }
+        cleaned = cleaned.slice(0, si) + cleaned.slice(ei + DEDUPE_END.length);
+    }
+    // 2. Remove orphaned markers (from prior corruption)
+    cleaned = cleaned.split(DEDUPE_START).join('').split(DEDUPE_END).join('');
+    // 3. Remove orphaned [[skills.config]] entries for .agents/skills paths
+    cleaned = cleaned.replace(/\[\[skills\.config\]\]\r?\npath = "[^"]*\.agents[/\\]skills[/\\][^"]*"\r?\nenabled = false\r?\n?/g, '');
+    return cleaned.replace(/\n{3,}/g, '\n\n').trim();
+}
 /**
  * Write `[[skills.config]]` entries to `~/.codex/config.toml` to disable
  * .agents/ skills that duplicate the native codex skills.
@@ -753,15 +780,7 @@ export function writeCodexSkillDedupeConfig(scope, projectPath) {
     if (existsSync(fp)) {
         content = readFileSync(fp, 'utf-8');
     }
-    // Remove existing maestro-managed dedupe block
-    const DEDUPE_START = '# maestro:dedupe-agents-start';
-    const DEDUPE_END = '# maestro:dedupe-agents-end';
-    const startIdx = content.indexOf(DEDUPE_START);
-    const endIdx = content.indexOf(DEDUPE_END);
-    if (startIdx !== -1 && endIdx !== -1) {
-        content = (content.slice(0, startIdx) + content.slice(endIdx + DEDUPE_END.length))
-            .replace(/\n{3,}/g, '\n\n').trim();
-    }
+    content = stripDedupeBlocks(content);
     const entries = skillDirs.map(name => {
         const skillPath = join(agentsSkillsDir, name, 'SKILL.md').replace(/\\/g, '/');
         return `[[skills.config]]\npath = "${skillPath}"\nenabled = false`;
@@ -787,14 +806,10 @@ export function removeCodexSkillDedupeConfig(scope, projectPath) {
     if (!existsSync(fp))
         return false;
     const content = readFileSync(fp, 'utf-8');
-    const DEDUPE_START = '# maestro:dedupe-agents-start';
-    const DEDUPE_END = '# maestro:dedupe-agents-end';
-    const startIdx = content.indexOf(DEDUPE_START);
-    const endIdx = content.indexOf(DEDUPE_END);
-    if (startIdx === -1 || endIdx === -1)
+    if (!content.includes(DEDUPE_START) && !content.includes(DEDUPE_END)
+        && !/\.agents[/\\]skills[/\\]/.test(content))
         return false;
-    const cleaned = (content.slice(0, startIdx) + content.slice(endIdx + DEDUPE_END.length))
-        .replace(/\n{3,}/g, '\n\n').trim();
+    const cleaned = stripDedupeBlocks(content);
     writeFileSync(fp, cleaned + '\n', 'utf-8');
     return true;
 }