maestro-flow 0.5.31 → 0.5.33

package/.claude/commands/odyssey-review-test-fix.md

@@ -20,7 +20,8 @@ fix ALL findings → confirm → generalize → discover → persist. Zero-resid
 <boundary>
 **范围内:** 目标代码的多维度深度审查 → 穷尽修复 ALL 发现（按 severity 递降）→ 泛化 pattern 到全项目
 **范围外:** 深度根因调查（根因不明时）→ `/odyssey-debug` | 需求实现 → `/odyssey-planex` | UI 视觉优化 → `/odyssey-ui`
-**探索自由度:** 边界内自由探索 — 可跨维度关联发现、追溯 git 历史、泛化扫描全项目。修复仅限 critical/high findings。
+**探索自由度:** 边界内自由探索 — 可跨维度关联发现、追溯 git 历史、泛化扫描全项目。修复 ALL findings within fix_threshold（默认 all = 穷尽所有 severity）。
+**Zero-residual principle:** Every finding MUST have a concrete action (fix / issue / decision). "Report and shelve" is not allowed. "Pre-existing issue" is not a valid skip reason — if discovered within scope, it must be addressed.
 </boundary>
 
 <execution_discipline>
@@ -30,10 +31,15 @@ fix ALL findings → confirm → generalize → discover → persist. Zero-resid
    - 代码变更 + understanding.md → `git add` → `git commit -m "odyssey-review({slug}): {phase} — {摘要}"`
    - session.json / evidence.ndjson 为运行时状态，不纳入 commit
 
-2. **有把握才改** — 仅修改自己有把握的内容；不确定的记录决策等人判断
-   - 有把握 → 直接修改代码，commit
-   - 需要决策 → 记录 `evidence.ndjson {"phase":"decision","status":"pending"}` 不改代码
-   - 禁止猜测性修改
+2. **Confident edits only, but must attempt** — only modify what you're confident about; record decisions only when genuinely requiring human judgment
+   - Confident → edit code directly, commit
+   - Needs decision → record `evidence.ndjson {"phase":"decision","status":"pending"}`, don't touch code
+   - No speculative changes
+   - ⚠️ **Decision gate** — ONLY these qualify as decisions (not fixes):
+     - Cross-module architectural tradeoffs requiring human direction
+     - Ambiguous business semantics where the fix could alter intended behavior
+     - Requires new dependency or breaking API change
+   - ❌ "Unsure how to fix", "Large scope", "Pre-existing issue" are NOT valid decision reasons — either fix it, or explain specifically why it's unfixable
 
 3. **多 CLI 辅助** — 利用 `maestro delegate` 调用多个 CLI 工具交叉验证
    - 关键判断用不同 `--role`（analyze / review / explore）获取多视角
@@ -86,7 +92,7 @@ SESSION_DIR/
   "generalization_stats": { "patterns_extracted": 0, "total_hits": 0, "true_positives": 0, "false_positives": 0, "uncertain": 0, "cross_layer_confirmed": 0, "regression_risks": 0, "by_layer": {}, "deepening_triggered": false, "self_iteration_rounds": 0 },
   "phase_goals": [], "phase_goals_all_done": false,
   "self_iteration_log": [],
-  "cross_phase_loops": 0, "max_loops": 3,
+  "cross_phase_loops": 0, "max_loops": 5,
   "created_at": "", "updated_at": ""
 }
 ```
@@ -130,7 +136,7 @@ S_RECORD 阶段将可沉淀知识 **写入 understanding.md §8 Learnings**，
 </context>
 
 <self_iteration>
-**Quality Gate** — auto-evaluate after each analytical phase. Insufficient → re-enter (max 2 rounds).
+**Quality Gate** — auto-evaluate after each analytical phase. Insufficient → re-enter (max 3 rounds).
 
 | Dimension | Sufficient | Insufficient |
 |-----------|-----------|-------------|
@@ -138,7 +144,7 @@ S_RECORD 阶段将可沉淀知识 **写入 understanding.md §8 Learnings**，
 | Depth | ≥80% findings have file:line evidence | Most findings lack specifics |
 | Actionability | Each conclusion has concrete next action | "Consider reviewing" without action |
 
-**Expansion:** Round 1 = widen scope (more dirs, deeper git log, extra delegate angles). Round 2 = shift perspective (different CLI tool, reverse trace, manual reading).
+**Expansion:** Round 1 = widen scope (more dirs, deeper git log, extra delegate angles). Round 2 = shift perspective (different CLI tool, reverse trace, manual reading). Round 3 = combine both + targeted deep-dive on remaining gaps.
 
 **Log:** `evidence.ndjson ← {"phase":"self-iteration","type":"quality-gate","stage":"S_XXX","round":N,"assessment":{},"expansion":""}`
 
@@ -184,9 +190,10 @@ S_GENERALIZE:
   → S_DISCOVER      WHEN hits found                 DO A_GENERALIZE
   → S_RECORD        WHEN no hits                    DO A_GENERALIZE
 
-S_DISCOVER → S_FIX          : discovery finds fixable sibling, !skip_fix, loops < max_loops → cross_phase_loops++
+S_DISCOVER → S_FIX          : discovery finds fixable sibling, !skip_fix → cross_phase_loops++
 S_DISCOVER → S_REVIEW       : discovery opens new review target, loops < max_loops → cross_phase_loops++
-S_DISCOVER → S_RECORD       : triage complete OR loops >= max_loops (剩余项 → issue/decision)
+S_DISCOVER → S_RECORD       : triage complete AND remaining_actionable == 0
+S_DISCOVER → S_RECORD       : loops >= max_loops → MUST log each unfixed item with specific reason (blanket "pre-existing" is forbidden)
 
 S_RECORD   → END            DO A_RECORD
 </transitions>
@@ -252,7 +259,10 @@ for tier in fix_tiers:
 
 **Normal**: AskUserQuestion 确认每个 tier 的 candidates。**`-y`**: auto-fix all, record `deferred`.
 
-**Remaining check**: 所有 tiers 完成后，count unfixed findings within fix_threshold → 写入 `review_result.remaining_actionable`。若 > 0 且未超 max_loops → 回到 tier 1 重试。
+**Remaining check**: 所有 tiers 完成后，count unfixed findings within fix_threshold → 写入 `review_result.remaining_actionable`。
+- If > 0 → retry from tier 1 (NOT limited by max_loops — max_loops only limits cross-phase loops, not FIX-internal retries)
+- If remaining unchanged for 2 consecutive rounds (same findings stuck) → classify each stuck finding individually: record as decision (if meets Decision gate criteria) or issue (with fix suggestion)
+- ❌ Blanket "N remaining items are pre-existing" is forbidden — each item must have individual classification and reason
 
 📌 **Auto-commit per tier**: `git add -A && git commit -m "odyssey-review({slug}): FIX-{tier} — {N}项修复"`
 
@@ -267,7 +277,7 @@ EXPECTED: JSON {verdict, findings_addressed, remaining_unfixed, regression_risk,
 CONSTRAINTS: Focus on correctness AND completeness — flag ANY remaining actionable improvement
 " --role review --mode analysis
 ```
-Run_in_background, STOP, wait.
+以 `run_in_background: true` 执行 delegate，等待回调后继续（不中断 Odyssey 流程）。
 
 **Zero-residual gate:**
 - `remaining_unfixed == 0 AND new_findings == 0` → `confirmed`, mark G3 done
@@ -309,7 +319,12 @@ Write `session.json.generalization_stats`. Mark G4 done.
 
 ### A_DISCOVER
 Classify each hit: `bug` / `risk` / `safe`.
-**Normal**: AskUserQuestion for bug routing. **`-y`**: auto create issue, `deferred`.
+- `bug` + directly fixable → **fix immediately** (not just log an issue) → back to S_FIX
+- `bug` + requires cross-module/architectural decision → create issue (with fix suggestion + impact analysis)
+- `risk` → evaluate if guard/validation can mitigate directly; if yes, fix it
+- `safe` → mark skip
+
+**Normal**: AskUserQuestion for routing ambiguity. **`-y`**: auto-fix what's fixable, create issue for rest.
 Append evidence (phase: discovery + decision). Update `understanding.md` §7. Mark G5 done.
 
 📌 **Auto-commit**: `git add understanding.md && git commit -m "odyssey-review({slug}): DISCOVER — 发现分类完成"`
@@ -394,6 +409,7 @@ Goals:      {done}/{total} ({skipped} skipped)
 - [ ] **ALL findings within fix_threshold fixed** — remaining_actionable == 0 (unless --skip-fix)
 - [ ] Per-tier fix with re-review gate: modified area re-reviewed, new findings appended
 - [ ] Zero-residual confirmed by CLI external model
+- [ ] **Every unfixed finding has individual classification and reason** — blanket "pre-existing" labels are forbidden
 - [ ] Pattern generalized with multi-layer scan + deepening (unless --skip-generalize)
 - [ ] Quality Gate self-iteration triggered when insufficient
 - [ ] Discoveries classified and routed

package/.claude/commands/odyssey-ui.md

@@ -21,6 +21,7 @@ fix → verify → generalize → discover → persist. Every pixel is a learnin
 **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.
 </boundary>
 
 <execution_discipline>
@@ -30,10 +31,15 @@ fix → verify → generalize → discover → persist. Every pixel is a learnin
    - 代码变更 + understanding.md → `git add` → `git commit -m "odyssey-ui({slug}): {phase} — {摘要}"`
    - session.json / evidence.ndjson 为运行时状态，不纳入 commit
 
-2. **有把握才改** — 仅修改自己有把握的内容；不确定的记录决策等人判断
-   - 视觉确定性高（缺少 hover state、对比度不足等）→ 直接修复
-   - 设计方向不确定（色彩选择、布局重构等）→ 记录 decision 等用户判断
-   - 禁止猜测性修改，尤其是品牌/风格层面的改动
+2. **Confident edits only, but must attempt** — only modify what you're confident about; record decisions only when genuinely requiring human judgment
+   - High visual certainty (missing hover state, insufficient contrast, etc.) → fix directly
+   - Design direction uncertain (color choices, layout restructure, etc.) → record decision for user judgment
+   - No speculative changes, especially brand/style-level modifications
+   - ⚠️ **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
 
 3. **多 CLI 辅助** — 利用 `maestro delegate` 调用多个 CLI 工具交叉验证
    - survey 阶段: `--role explore` 发现设计系统用法
@@ -87,7 +93,7 @@ SESSION_DIR/
   "generalization_stats": { "patterns_extracted": 0, "total_hits": 0, "cross_layer_confirmed": 0, "regression_risks": 0, "by_layer": {}, "deepening_triggered": false },
   "phase_goals": [], "phase_goals_all_done": false,
   "self_iteration_log": [],
-  "cross_phase_loops": 0, "max_loops": 3,
+  "cross_phase_loops": 0, "max_loops": 5,
   "created_at": "", "updated_at": ""
 }
 ```
@@ -133,7 +139,7 @@ S_RECORD 阶段将可沉淀知识 **写入 understanding.md §8 Learnings**，
 </context>
 
 <self_iteration>
-**Quality Gate** — auto-evaluate after each analytical phase. Insufficient → re-enter (max 2 rounds).
+**Quality Gate** — auto-evaluate after each analytical phase. Insufficient → re-enter (max **3 rounds**).
 
 | Dimension | Sufficient | Insufficient |
 |-----------|-----------|-------------|
@@ -141,7 +147,7 @@ S_RECORD 阶段将可沉淀知识 **写入 understanding.md §8 Learnings**，
 | Depth | ≥80% findings have file:line evidence | Most findings lack specifics |
 | Actionability | Each conclusion has concrete improvement action | "Consider reviewing" without action |
 
-**Expansion:** Round 1 = widen scope (more components, deeper import chain, extra delegate angles). Round 2 = shift perspective (different CLI tool, reverse dependency trace, manual code reading).
+**Expansion:** Round 1 = widen scope (more components, deeper import chain, extra delegate angles). Round 2 = shift perspective (different CLI tool, reverse dependency trace, manual code reading). Round 3 = combine both + targeted deep-dive on remaining gaps.
 
 **Log:** `evidence.ndjson ← {"phase":"self-iteration","type":"quality-gate","stage":"S_XXX","round":N,"assessment":{},"expansion":""}`
 
@@ -188,9 +194,10 @@ S_GENERALIZE:
   → S_DISCOVER     WHEN hits found                DO A_GENERALIZE
   → S_RECORD       WHEN no hits                   DO A_GENERALIZE
 
-S_DISCOVER → S_AUDIT        : discovery reveals new component to audit, loops < max_loops → cross_phase_loops++
-S_DISCOVER → S_FIX          : discovery finds fixable sibling, !skip_fix, loops < max_loops → cross_phase_loops++
-S_DISCOVER → S_RECORD       : triage complete OR loops >= max_loops (剩余项 → issue/decision)
+S_DISCOVER → S_AUDIT        : discovery reveals new component to audit → cross_phase_loops++
+S_DISCOVER → S_FIX          : discovery finds fixable sibling, !skip_fix → cross_phase_loops++
+S_DISCOVER → S_RECORD       : triage complete AND remaining_actionable == 0
+S_DISCOVER → S_RECORD       : loops >= max_loops → MUST log each unfixed item with specific reason (blanket "pre-existing" is forbidden)
 
 S_RECORD   → END            DO A_RECORD
 </transitions>
@@ -224,7 +231,7 @@ CONTEXT: @{target_files}
 EXPECTED: JSON {tokens_used, spacing_patterns, typography_scale, component_hierarchy, consistency_issues}
 " --role analyze --mode analysis
 ```
-Run_in_background, STOP, wait for callback.
+Execute with `run_in_background: true`, then wait for callback (do NOT halt the Odyssey flow).
 
 4. Append evidence.ndjson (phase: "survey"). Update `understanding.md` §2. Mark G1 done.
 
@@ -269,7 +276,7 @@ CONTEXT: @{target_files} | Audit summary: {audit_findings_summary}
 EXPECTED: JSON [{category, idea, rationale, reference}]
 " --role analyze --mode analysis
 ```
-Run_in_background, STOP, wait for callback.
+Execute with `run_in_background: true`, then wait for callback (do NOT halt the Odyssey flow).
 
 **Step 3 — Consolidate**: Merge audit findings + divergent ideas → prioritized improvement list (severity x impact x effort matrix).
 Append evidence.ndjson (phase: "diverge"). Update `understanding.md` §4. Mark G3 done.
@@ -298,7 +305,7 @@ CONTEXT: @{modified_files} | Improvements: {fix_summary}
 EXPECTED: JSON {verdict, verified_improvements, remaining_issues, regression_risk}
 " --role review --mode analysis
 ```
-Run_in_background, STOP, wait for callback.
+Execute with `run_in_background: true`, then wait for callback (do NOT halt the Odyssey flow).
 
 3. `needs_rework` → S_FIX. `verified` → mark G4 done, advance.
 4. Update `understanding.md` §5. Write `session.json.confirmation`.
@@ -337,7 +344,12 @@ Update `understanding.md` §6 (per-pattern summary, cross-layer matrix). Write `
 
 ### A_DISCOVER
 Classify each hit: `needs_treatment` / `low_risk` / `already_handled`.
-**Normal**: AskUserQuestion for routing. **`-y`**: auto create issue, `deferred`.
+- `needs_treatment` + directly fixable → **fix immediately** → back to S_FIX
+- `needs_treatment` + requires design direction decision → create issue (with fix suggestion)
+- `low_risk` → evaluate if a quick guard/improvement is feasible; if yes, fix it
+- `already_handled` → mark skip
+
+**Normal**: AskUserQuestion for routing ambiguity. **`-y`**: auto-fix what's fixable, create issue for rest.
 Append evidence (phase: "discovery" + "decision"). Update `understanding.md` §7. Mark G6 done.
 
 📌 **Auto-commit**: `git add understanding.md && git commit -m "odyssey-ui({slug}): DISCOVER — 发现分类"`
@@ -427,6 +439,7 @@ Goals:      {done}/{total} ({skipped} skipped)
 - [ ] Multi-layer generalization scan + cross-layer dedup (unless --skip-generalize)
 - [ ] Quality Gate self-iteration triggered when insufficient
 - [ ] Discoveries classified and routed
+- [ ] **Every unfixed finding has individual classification and reason** — blanket "pre-existing" labels are forbidden
 - [ ] understanding.md §8 finalized with design learnings
 - [ ] phase_goals G1-G7 tracked and audited
 - [ ] Goal Prompt displayed once

package/.claude/skills/delegation-check/SKILL.md

@@ -0,0 +1,297 @@
+---
+name: delegation-check
+description: Check workflow delegation prompts against agent role definitions for content separation violations. Detects conflicts, duplication, boundary leaks, and missing contracts. Triggers on "check delegation", "delegation conflict", "prompt vs role check".
+allowed-tools: Read, Glob, Grep, Bash, AskUserQuestion
+---
+
+<purpose>
+Validate that command delegation prompts (Agent() calls) and agent role definitions respect GSD content separation boundaries. Detects 7 conflict dimensions: role re-definition, domain expertise leaking into prompts, quality gate duplication, output format conflicts, process override, scope authority conflicts, and missing contracts.
+
+Invoked when user requests "check delegation", "delegation conflict", "prompt vs role check", or when reviewing workflow skill quality.
+</purpose>
+
+<required_reading>
+- @.claude/skills/delegation-check/specs/separation-rules.md
+</required_reading>
+
+<process>
+
+## Pre-load (before execution)
+
+1. **Codebase docs**: If `.workflow/codebase/ARCHITECTURE.md` exists, read for project context
+2. **Specs**: `maestro spec load --category coding` — load coding conventions
+3. **Wiki knowledge**: `maestro search "skill design optimization" --json` — top 5 entries as prior context
+4. All optional — proceed without if unavailable
+
+## 1. Determine Scan Scope
+
+Parse `$ARGUMENTS` to identify what to check.
+
+| Signal | Scope |
+|--------|-------|
+| File path to command `.md` | Single command + its agents |
+| File path to agent `.md` | Single agent + commands that spawn it |
+| Directory path (e.g., `.claude/skills/team-*/`) | All commands + agents in that skill |
+| "all" or no args | Scan all `.claude/commands/`, `.claude/skills/*/`, `.claude/agents/` |
+
+If ambiguous, ask:
+
+```
+AskUserQuestion(
+  header: "Scan Scope",
+  question: "What should I check for delegation conflicts?",
+  options: [
+    { label: "Specific skill", description: "Check one skill directory" },
+    { label: "Specific command+agent pair", description: "Check one command and its spawned agents" },
+    { label: "Full scan", description: "Scan all commands, skills, and agents" }
+  ]
+)
+```
+
+## 2. Discover Command-Agent Pairs
+
+For each command file in scope:
+
+**2a. Extract Agent() calls from commands:**
+
+```bash
+# Search both Agent() (current) and Task() (legacy GSD) patterns
+grep -n "Agent(\|Task(" "$COMMAND_FILE"
+grep -n "subagent_type" "$COMMAND_FILE"
+```
+
+For each `Agent()` call, extract:
+- `subagent_type` → agent name
+- Full prompt content between the prompt markers (the string passed as `prompt=`)
+- Line range of the delegation prompt
+
+**2b. Locate agent definitions:**
+
+For each `subagent_type` found:
+```bash
+# Check standard locations
+ls .claude/agents/${AGENT_NAME}.md 2>/dev/null
+ls .claude/skills/*/agents/${AGENT_NAME}.md 2>/dev/null
+```
+
+**2c. Build pair map:**
+
+```
+$PAIRS = [
+  {
+    command: { path, agent_calls: [{ line, subagent_type, prompt_content }] },
+    agent: { path, role, sections, quality_gate, output_contract }
+  }
+]
+```
+
+If an agent file cannot be found, record as `MISSING_AGENT` — this is itself a finding.
+
+## 3. Parse Delegation Prompts
+
+For each Agent() call, extract structured blocks from the prompt content:
+
+| Block | What It Contains |
+|-------|-----------------|
+| `<objective>` | What to accomplish |
+| `<files_to_read>` | Input file paths |
+| `<additional_context>` / `<planning_context>` / `<verification_context>` | Runtime parameters |
+| `<output>` / `<expected_output>` | Output format/location expectations |
+| `<quality_gate>` | Per-invocation quality checklist |
+| `<deep_work_rules>` / `<instructions>` | Cross-cutting policy or revision instructions |
+| `<downstream_consumer>` | Who consumes the output |
+| `<success_criteria>` | Success conditions |
+| Free-form text | Unstructured instructions |
+
+Also detect ANTI-PATTERNS in prompt content:
+- Role identity statements ("You are a...", "Your role is...")
+- Domain expertise (decision tables, heuristics, comparison examples)
+- Process definitions (numbered steps, step-by-step instructions beyond scope)
+- Philosophy statements ("always prefer...", "never do...")
+- Anti-pattern lists that belong in agent definition
+
+## 4. Parse Agent Definitions
+
+For each agent file, extract:
+
+| Section | Key Content |
+|---------|------------|
+| `<role>` | Identity, spawner, responsibilities, mandatory read |
+| `<philosophy>` | Guiding principles |
+| `<upstream_input>` | How agent interprets input |
+| `<output_contract>` | Return markers (COMPLETE/BLOCKED/CHECKPOINT) |
+| `<quality_gate>` | Self-check criteria |
+| Domain sections | All `<section_name>` tags with their content |
+| YAML frontmatter | name, description, tools |
+
+## 5. Run Conflict Checks (7 Dimensions)
+
+### Dimension 1: Role Re-definition
+
+**Question:** Does the delegation prompt redefine the agent's identity?
+
+**Check:** Scan prompt content for:
+- "You are a..." / "You are the..." / "Your role is..."
+- "Your job is to..." / "Your responsibility is..."
+- "Core responsibilities:" lists
+- Any content that contradicts agent's `<role>` section
+
+**Allowed:** References to mode ("standard mode", "revision mode") that the agent's `<role>` already lists in "Spawned by:".
+
+**Severity:** `error` if prompt redefines role; `warning` if prompt adds responsibilities not in agent's `<role>`.
+
+### Dimension 2: Domain Expertise Leak
+
+**Question:** Does the delegation prompt embed domain knowledge that belongs in the agent?
+
+**Check:** Scan prompt content for:
+- Decision/routing tables (`| Condition | Action |`)
+- Good-vs-bad comparison examples (`| TOO VAGUE | JUST RIGHT |`)
+- Heuristic rules ("If X then Y", "Always prefer Z")
+- Anti-pattern lists ("DO NOT...", "NEVER...")
+- Detailed process steps beyond task scope
+
+**Exception:** `<deep_work_rules>` is an acceptable cross-cutting policy pattern from GSD — flag as `info` only.
+
+**Severity:** `error` if prompt contains domain tables/examples that duplicate agent content; `warning` if prompt contains heuristics not in agent.
+
+### Dimension 3: Quality Gate Duplication
+
+**Question:** Do the prompt's quality checks overlap or conflict with the agent's own `<quality_gate>`?
+
+**Check:** Compare prompt `<quality_gate>` / `<success_criteria>` items against agent's `<quality_gate>` items:
+- **Duplicate:** Same check appears in both → `warning` (redundant, may diverge)
+- **Conflict:** Contradictory criteria (e.g., prompt says "max 3 tasks", agent says "max 5 tasks") → `error`
+- **Missing:** Prompt expects quality checks agent doesn't have → `info`
+
+**Severity:** `error` for contradictions; `warning` for duplicates; `info` for gaps.
+
+### Dimension 4: Output Format Conflict
+
+**Question:** Does the prompt's expected output format conflict with the agent's `<output_contract>`?
+
+**Check:**
+- Prompt `<expected_output>` markers vs agent's `<output_contract>` return markers
+- Prompt expects specific format agent doesn't define
+- Prompt expects file output but agent's contract only defines markers (or vice versa)
+- Return marker names differ (prompt expects `## DONE`, agent returns `## TASK COMPLETE`)
+
+**Severity:** `error` if return markers conflict; `warning` if format expectations unspecified on either side.
+
+### Dimension 5: Process Override
+
+**Question:** Does the delegation prompt dictate HOW the agent should work?
+
+**Check:** Scan prompt for:
+- Numbered step-by-step instructions ("Step 1:", "First..., Then..., Finally...")
+- Process flow definitions beyond `<objective>` scope
+- Tool usage instructions ("Use grep to...", "Run bash command...")
+- Execution ordering that conflicts with agent's own execution flow
+
+**Allowed:** `<instructions>` block for revision mode (telling agent what changed, not how to work).
+
+**Severity:** `error` if prompt overrides agent's process; `warning` if prompt suggests process hints.
+
+### Dimension 6: Scope Authority Conflict
+
+**Question:** Does the prompt make decisions that belong to the agent's domain?
+
+**Check:**
+- Prompt specifies implementation choices (library selection, architecture patterns) when agent's `<philosophy>` or domain sections own these decisions
+- Prompt overrides agent's discretion areas
+- Prompt locks decisions that agent's `<context_fidelity>` says are "Claude's Discretion"
+
+**Allowed:** Passing through user-locked decisions from CONTEXT.md — this is proper delegation, not authority conflict.
+
+**Severity:** `error` if prompt makes domain decisions agent should own; `info` if prompt passes through user decisions (correct behavior).
+
+### Dimension 7: Missing Contracts
+
+**Question:** Are the delegation handoff points properly defined?
+
+**Check:**
+- Agent has `<output_contract>` with return markers → command handles all markers?
+- Command's return handling covers COMPLETE, BLOCKED, CHECKPOINT
+- Agent lists "Spawned by:" — does command actually spawn it?
+- Agent expects `<files_to_read>` — does prompt provide it?
+- Agent has `<upstream_input>` — does prompt provide matching input structure?
+
+**Severity:** `error` if return marker handling is missing; `warning` if agent expects input the prompt doesn't provide.
+
+## 6. Aggregate and Report
+
+### 6a. Per-pair summary
+
+For each command-agent pair, aggregate findings:
+
+```
+{command_path} → {agent_name}
+  Agent() at line {N}:
+    D1 (Role Re-def):      {PASS|WARN|ERROR} — {detail}
+    D2 (Domain Leak):       {PASS|WARN|ERROR} — {detail}
+    D3 (Quality Gate):      {PASS|WARN|ERROR} — {detail}
+    D4 (Output Format):     {PASS|WARN|ERROR} — {detail}
+    D5 (Process Override):  {PASS|WARN|ERROR} — {detail}
+    D6 (Scope Authority):   {PASS|WARN|ERROR} — {detail}
+    D7 (Missing Contract):  {PASS|WARN|ERROR} — {detail}
+```
+
+### 6b. Overall verdict
+
+| Verdict | Condition |
+|---------|-----------|
+| **CLEAN** | 0 errors, 0-2 warnings |
+| **REVIEW** | 0 errors, 3+ warnings |
+| **CONFLICT** | 1+ errors |
+
+### 6c. Fix recommendations
+
+For each finding, provide:
+- **Location:** file:line
+- **What's wrong:** concrete description
+- **Fix:** move content to correct owner (command or agent)
+- **Example:** before/after snippet if applicable
+
+## 7. Present Results
+
+```
+━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
+ DELEGATION-CHECK ► SCAN COMPLETE
+━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
+
+Scope: {description}
+Pairs checked: {N} command-agent pairs
+Findings: {E} errors, {W} warnings, {I} info
+
+Verdict: {CLEAN | REVIEW | CONFLICT}
+
+| Pair | D1 | D2 | D3 | D4 | D5 | D6 | D7 |
+|------|----|----|----|----|----|----|-----|
+| {cmd} → {agent} | ✅ | ⚠️ | ✅ | ✅ | ❌ | ✅ | ✅ |
+| ... | | | | | | | |
+
+{If CONFLICT: detailed findings with fix recommendations}
+
+───────────────────────────────────────────────────────
+
+## Fix Priority
+
+1. {Highest severity fix}
+2. {Next fix}
+...
+
+───────────────────────────────────────────────────────
+```
+
+</process>
+
+<success_criteria>
+- [ ] Scan scope determined and all files discovered
+- [ ] All Agent() calls extracted from commands with full prompt content
+- [ ] All corresponding agent definitions located and parsed
+- [ ] 7 conflict dimensions checked for each command-agent pair
+- [ ] No false positives on legitimate patterns (mode references, user decision passthrough, `<deep_work_rules>`)
+- [ ] Fix recommendations provided for every error/warning
+- [ ] Summary table with per-pair dimension results displayed
+- [ ] Overall verdict determined (CLEAN/REVIEW/CONFLICT)
+</success_criteria>