@arvorco/relentless 0.3.0 → 0.4.2

package/.claude/commands/relentless.constitution.md

@@ -22,7 +22,7 @@ The constitution skill (`.claude/skills/constitution/SKILL.md`) will guide you t
    - Version control (branches, commits, CI/CD)
 
 2. **Generate Constitution**: Create personalized governance document
-   - Load template from `.claude/skills/constitution/templates/constitution-template.md`
+   - Load template from `.claude/skills/constitution/templates/constitution.md`
    - Replace all placeholders with concrete values from user answers
    - Ensure MUST/SHOULD rules are clear and testable
    - Set version 1.0.0 for new, increment semantically for updates

package/.claude/commands/relentless.convert.md

@@ -0,0 +1,25 @@
+---
+description: Convert tasks.md to prd.json with smart routing classification.
+handoffs:
+  - label: Analyze Consistency
+    agent: relentless.analyze
+    prompt: Analyze cross-artifact consistency
+    send: true
+  - label: Start Implementation
+    agent: relentless.implement
+    prompt: Begin implementation
+    send: true
+---
+
+Load the convert skill and convert tasks.md to prd.json with routing.
+
+**Context:** $ARGUMENTS
+
+The convert skill will:
+1. Locate tasks.md in the current feature directory
+2. Validate story structure, dependencies, and TDD compliance
+3. Run `relentless convert` with routing classification
+4. Display routing summary (complexity, harness, model, cost)
+5. Report next steps
+
+**Important:** Routing is ALWAYS included by default. This enables intelligent cost optimization.

package/.claude/commands/relentless.specify.md

@@ -27,7 +27,7 @@ The specify skill (`.claude/skills/specify/SKILL.md`) will guide you through:
 2. **Load Context**
    - Read `relentless/constitution.md` for governance rules
    - Note MUST/SHOULD requirements for specifications
-   - Load spec template from `.claude/skills/specify/templates/spec-template.md`
+   - Load spec template from `.claude/skills/specify/templates/spec.md`
 
 3. **Generate Specification**
    - Extract key concepts: actors, actions, data, constraints

package/.claude/skills/analyze/SKILL.md

@@ -9,12 +9,36 @@ Validate consistency across feature artifacts before implementation.
 
 ---
 
+## SpecKit Workflow
+
+This skill is **Step 5 of 6** in the Relentless workflow:
+
+specify → plan → tasks → convert → **analyze** → implement
+
+Prerequisites (ALL must exist):
+- `spec.md` - Feature specification
+- `plan.md` - Technical implementation plan
+- `tasks.md` - User stories and tasks
+- `prd.json` - Converted PRD with routing metadata (run convert first)
+- `checklist.md` - Quality validation checklist (recommended)
+
+Purpose:
+- Validate consistency across ALL artifacts
+- Catch gaps before implementation begins
+- **Ensure TDD and routing compliance**
+- **Verify quality gates are defined**
+
+---
+
 ## The Job
 
 1. Read all feature artifacts
 2. Check for consistency issues
-3. Validate against constitution
-4. Report findings
+3. **Validate TDD compliance**
+4. **Validate routing metadata**
+5. **Validate quality gates**
+6. Validate against constitution
+7. Generate analysis report
 
 ---
 
@@ -25,10 +49,10 @@ Required:
 - `relentless/features/NNN-feature/spec.md`
 - `relentless/features/NNN-feature/plan.md`
 - `relentless/features/NNN-feature/tasks.md`
+- `relentless/features/NNN-feature/prd.json`
 - `relentless/features/NNN-feature/checklist.md`
 
 Optional:
-- `relentless/features/NNN-feature/prd.json`
 - `relentless/features/NNN-feature/progress.txt`
 
 ---
@@ -41,33 +65,69 @@ Optional:
 - [ ] Plan addresses all spec requirements
 - [ ] Checklist covers all tasks
 
-### 2. Constitution Compliance
+### 2. TDD Compliance Validation (MANDATORY)
+
+Verify that:
+- [ ] Every story in tasks.md has test acceptance criteria
+- [ ] Test specifications exist in plan.md
+- [ ] Checklist includes test validation items
+- [ ] No stories marked "tests optional"
+- [ ] Given/When/Then format used in acceptance criteria
+
+**Flag as CRITICAL if TDD requirements are missing.**
+
+### 3. Routing Metadata Validation (MANDATORY)
+
+Verify that prd.json contains for EVERY story:
+- [ ] `routing.complexity` - simple/medium/complex/expert
+- [ ] `routing.harness` - claude/gemini/codex/opencode/amp/droid
+- [ ] `routing.model` - specific model name
+- [ ] `routing.mode` - free/cheap/good/genius
+- [ ] `routing.estimatedCost` - cost in USD
+
+Also verify:
+- [ ] Routing preference in spec.md matches prd.json routing mode
+- [ ] Complexity classifications are reasonable for story scope
+
+**Flag as CRITICAL if routing metadata is missing.**
+
+### 4. Quality Gates Validation (MANDATORY)
+
+Verify that ALL THREE quality gates are present in acceptance criteria:
+- [ ] Typecheck requirement (`bun run typecheck` passes with 0 errors)
+- [ ] Lint requirement (`bun run lint` passes with 0 errors AND 0 warnings)
+- [ ] Test requirement (`bun test` passes)
+
+**Flag as CRITICAL if any quality gate is missing.**
+
+### 5. Constitution Compliance
 - [ ] Plan follows MUST rules
 - [ ] Tasks include required quality checks
 - [ ] Testing requirements met
 - [ ] Security requirements addressed
+- [ ] No `any` types planned
 
-### 3. Dependency Consistency
+### 6. Dependency Consistency
 - [ ] Task dependencies are valid (no circular refs)
 - [ ] Referenced dependencies exist
 - [ ] Dependency order makes sense
 
-### 4. Scope Consistency
+### 7. Scope Consistency
 - [ ] Plan doesn't include out-of-scope items
 - [ ] Tasks match plan scope
 - [ ] No scope creep in checklist
 
-### 5. Data Model Consistency
+### 8. Data Model Consistency
 - [ ] Entities mentioned in spec are in plan
 - [ ] Plan data models match spec requirements
 - [ ] Tasks create required entities
 
-### 6. API Consistency
+### 9. API Consistency
 - [ ] Endpoints in plan match spec scenarios
 - [ ] Tasks implement all planned endpoints
 - [ ] Checklist validates all endpoints
 
-### 7. Testing Coverage
+### 10. Testing Coverage
 - [ ] Each task has test acceptance criteria
 - [ ] Checklist includes test validation
 - [ ] Test types match constitution requirements
@@ -76,15 +136,19 @@ Optional:
 
 ## Issue Severity
 
-**CRITICAL:** Blocks implementation
+**CRITICAL:** Blocks implementation - MUST fix before proceeding
 - Constitution MUST rule violations
+- **Missing TDD requirements**
+- **Missing routing metadata in prd.json**
+- **Missing quality gate requirements**
 - Circular dependencies
 - Missing required artifacts
 
 **WARNING:** Should fix before implementation
 - Incomplete coverage of requirements
 - Ambiguous acceptance criteria
-- Missing test criteria
+- Missing test criteria for some stories
+- Routing preference mismatch (spec vs prd.json)
 
 **INFO:** Nice to have
 - Style inconsistencies
@@ -95,48 +159,54 @@ Optional:
 
 ## Report Format
 
+Use the template at `templates/analysis-report.md`:
+
 ```markdown
-# Consistency Analysis: Feature Name
+# Consistency Analysis Report
 
-**Date:** 2026-01-11
-**Status:** PASS / ISSUES FOUND
+**Feature:** [feature-name]
+**Date:** [date]
+**Status:** [PASS | FAIL | WARNINGS]
 
 ## Summary
-- Stories: N/M completed
-- Issues: X total (Y critical, Z warnings, W info)
 
-## Critical Issues
+| Category | Status | Issues |
+|----------|--------|--------|
+| Completeness | ✅/❌ | [count] |
+| TDD Compliance | ✅/❌ | [count] |
+| Routing Validation | ✅/❌ | [count] |
+| Quality Gates | ✅/❌ | [count] |
+| Constitution | ✅/❌ | [count] |
+| Dependencies | ✅/❌ | [count] |
 
-### CRIT-001: Circular Dependency
-**Location:** tasks.md
-**Details:** US-002 depends on US-003, US-003 depends on US-002
-**Fix:** Remove circular dependency, reorder tasks
+## Critical Issues
 
-## Warnings
+### CRIT-001: [Issue Title]
+**Location:** [file]
+**Details:** [description]
+**Fix:** [required action]
 
-### WARN-001: Missing Test Coverage
-**Location:** tasks.md, US-004
-**Details:** No integration test in acceptance criteria
-**Fix:** Add integration test requirement
+## Recommendations
 
-## Info
+1. [Action item 1]
+2. [Action item 2]
 
-### INFO-001: Checklist Gap
-**Location:** checklist.md
-**Details:** No performance validation for US-005
-**Suggestion:** Add performance checklist item
+**Next Step:** /relentless.implement (if PASS) or fix issues (if FAIL)
+```
 
-## Recommendations
+---
 
-1. Fix all CRITICAL issues before proceeding
-2. Address WARNINGS for better quality
-3. Consider INFO items for completeness
+## Output
 
-**Next Steps:**
-- If CRITICAL issues: Fix and re-run analysis
-- If only WARNINGS: Proceed with caution
-- If PASS: Ready for `/relentless.implement`
-```
+1. Save analysis report to `relentless/features/NNN-feature/analysis-report.md`
+2. Update progress.txt with analysis results
+3. Report:
+   - Overall status: PASS/FAIL/WARNINGS
+   - Critical issues count
+   - TDD compliance: PASS/FAIL
+   - Routing validation: PASS/FAIL
+   - Quality gates: PASS/FAIL
+   - Next step: `/relentless.implement` or fix issues
 
 ---
 
@@ -144,6 +214,9 @@ Optional:
 
 - Run before starting implementation
 - Constitution compliance is non-negotiable
+- **TDD compliance is non-negotiable**
+- **Routing metadata is required for all stories**
+- **Quality gates (typecheck, lint, test) are mandatory**
 - Fix critical issues immediately
 - Warnings can sometimes be deferred
 - Re-run after making fixes

package/.claude/skills/analyze/templates/analysis-report.md

@@ -0,0 +1,138 @@
+# Consistency Analysis Report
+
+**Feature:** [feature-name]
+**Date:** [date]
+**Status:** [PASS | FAIL | WARNINGS]
+
+---
+
+## Summary
+
+| Category | Status | Issues |
+|----------|--------|--------|
+| Completeness | ✅/❌ | [count] |
+| TDD Compliance | ✅/❌ | [count] |
+| Routing Validation | ✅/❌ | [count] |
+| Quality Gates | ✅/❌ | [count] |
+| Constitution | ✅/❌ | [count] |
+| Dependencies | ✅/❌ | [count] |
+
+---
+
+## TDD Compliance
+
+- [ ] Every story has test acceptance criteria
+- [ ] Test specifications in plan.md
+- [ ] Checklist includes test items
+- [ ] Given/When/Then format used
+
+**Issues Found:**
+- [List any TDD gaps]
+
+---
+
+## Routing Validation
+
+- [ ] Routing preference in spec.md
+- [ ] Routing carried to plan.md
+- [ ] prd.json has routing metadata for all stories
+- [ ] Complexity classifications reasonable
+
+**Stories with routing metadata:**
+| Story ID | Complexity | Harness | Model | Mode | Cost |
+|----------|------------|---------|-------|------|------|
+| US-001 | [value] | [value] | [value] | [value] | [value] |
+
+**Issues Found:**
+- [List any routing gaps]
+
+---
+
+## Quality Gates
+
+- [ ] Typecheck in acceptance criteria (0 errors)
+- [ ] Lint in acceptance criteria (0 errors, 0 warnings)
+- [ ] Test in acceptance criteria
+
+**Issues Found:**
+- [List any quality gate gaps]
+
+---
+
+## Critical Issues
+
+### CRIT-001: [Issue Title]
+**Location:** [file:line]
+**Details:** [description of the issue]
+**Impact:** [what breaks if not fixed]
+**Fix:** [required action]
+
+### CRIT-002: [Issue Title]
+**Location:** [file:line]
+**Details:** [description]
+**Impact:** [what breaks]
+**Fix:** [required action]
+
+---
+
+## Warnings
+
+### WARN-001: [Issue Title]
+**Location:** [file:line]
+**Details:** [description]
+**Suggestion:** [recommended fix]
+
+### WARN-002: [Issue Title]
+**Location:** [file:line]
+**Details:** [description]
+**Suggestion:** [recommended fix]
+
+---
+
+## Info
+
+### INFO-001: [Issue Title]
+**Location:** [file:line]
+**Details:** [description]
+**Suggestion:** [optional improvement]
+
+---
+
+## Completeness Matrix
+
+| Spec Requirement | Plan Section | Task(s) | Checklist Item |
+|------------------|--------------|---------|----------------|
+| REQ-001: [name] | [section] | US-XXX | CHK-XXX |
+| REQ-002: [name] | [section] | US-XXX | CHK-XXX |
+
+---
+
+## Recommendations
+
+1. [Action item 1 - priority]
+2. [Action item 2 - priority]
+3. [Action item 3 - priority]
+
+---
+
+## Next Steps
+
+**If PASS:**
+- Ready for `/relentless.implement`
+- All critical checks passed
+- TDD, routing, and quality gates validated
+
+**If FAIL:**
+1. Fix all CRITICAL issues
+2. Re-run `/relentless.analyze`
+3. Proceed to implement only after PASS
+
+**If WARNINGS:**
+- Can proceed with caution
+- Address warnings during implementation
+- Document any deferred items
+
+---
+
+**Analysis completed by:** /relentless.analyze
+**Timestamp:** [datetime]

package/.claude/skills/checklist/SKILL.md

@@ -9,12 +9,74 @@ Generate domain-specific quality checklists to validate implementation completen
 
 ---
 
+## SpecKit Workflow
+
+This skill runs **after tasks, before analyze**:
+
+specify → plan → tasks → convert → **checklist** → analyze → implement
+
+Purpose:
+- Generate validation checklist from spec/plan/tasks
+- **Ensure quality gates are defined**
+- **Ensure TDD requirements are included**
+- **Ensure routing compliance is checked**
+- Provide implement phase with verification criteria
+
+---
+
+## TDD is MANDATORY
+
+Every generated checklist MUST include these testing items:
+
+### Testing & TDD (Required for ALL stories)
+- [ ] Unit tests written BEFORE implementation
+- [ ] Unit tests verified to FAIL before coding
+- [ ] Integration tests for API/data flows
+- [ ] E2E tests for user-facing flows
+- [ ] Test coverage meets 80% target
+- [ ] All tests pass
+
+**These items are non-negotiable and must appear in every checklist.**
+
+---
+
+## Mandatory Quality Gates
+
+Every story in the checklist MUST include:
+
+### Quality Gates (Non-Negotiable)
+- [ ] `bun run typecheck` passes with 0 errors
+- [ ] `bun run lint` passes with 0 errors AND 0 warnings
+- [ ] `bun test` passes
+- [ ] No debug code (console.log, debugger)
+- [ ] No unused imports or variables
+
+**All three commands must pass - no exceptions.**
+
+---
+
+## Routing Validation Items
+
+Every checklist MUST include:
+
+### Routing Compliance
+- [ ] Routing preference documented in spec.md
+- [ ] prd.json has routing metadata for all stories
+- [ ] Complexity classifications match story scope
+- [ ] Estimated costs are reasonable
+- [ ] Mode selection (free/cheap/good/genius) is appropriate
+
+---
+
 ## The Job
 
 1. Read spec.md, plan.md, and tasks.md
 2. Extract quality requirements from constitution
-3. Generate comprehensive checklist
-4. Save to `checklist.md`
+3. **Include mandatory TDD items**
+4. **Include mandatory quality gate items**
+5. **Include routing compliance items**
+6. Generate comprehensive checklist
+7. Save to `checklist.md`
 
 **Important:** Checklist items get merged into prd.json acceptance criteria!
 
@@ -40,14 +102,18 @@ Read:
 
 ## Step 3: Generate Checklist Categories
 
-Create 5-7 categories based on feature domain:
+Create 7-10 categories based on feature domain:
 
-**Common Categories:**
+**Mandatory Categories (always include):**
+- **0. Quality Gates** - typecheck, lint, test
+- **1. TDD Compliance** - tests before code
+- **2. Routing Compliance** - metadata validation
+
+**Common Categories (include as needed):**
 - Schema & Database
 - Backend Logic
 - Frontend Components (if applicable)
 - API Integration
-- Testing & Validation
 - Security & Permissions
 - Performance & UX
 - Documentation
@@ -70,18 +136,18 @@ For each category, create 5-10 specific validation items:
 - 80% of items should reference specific user stories `[US-XXX]`
 - 20% should identify gaps, ambiguities, or edge cases
 - Each item must be specific and testable
-- Total: 20-40 items across all categories
+- Total: 30-50 items across all categories
 
 ---
 
 ## Step 5: Reference Constitution
 
 Ensure checklist includes items for constitution MUST rules:
-- Type safety requirements
-- Testing coverage
+- Type safety requirements (no `any` types)
+- Testing coverage (80% minimum)
 - Security standards
 - Performance expectations
-- Code quality standards
+- Code quality standards (0 lint warnings)
 
 ---
 
@@ -91,9 +157,10 @@ Ensure checklist includes items for constitution MUST rules:
 2. Report:
    - Total checklist items: N
    - Items per category
+   - Mandatory items included: TDD ✓, Quality Gates ✓, Routing ✓
    - Constitution compliance items: N
    - Gaps identified: N
-   - Next step: `relentless convert tasks.md`
+   - Next step: `/relentless.convert` (if not done) or `/relentless.analyze`
 
 ---
 
@@ -106,60 +173,84 @@ Ensure checklist includes items for constitution MUST rules:
 **Created:** 2026-01-11
 **Feature:** [spec.md](./spec.md)
 
-## Schema & Database
+## 0. Quality Gates (MANDATORY - Every Story)
+
+- [ ] CHK-001 `bun run typecheck` passes with 0 errors
+- [ ] CHK-002 `bun run lint` passes with 0 errors AND 0 warnings
+- [ ] CHK-003 `bun test` passes
+- [ ] CHK-004 No debug code (console.log, debugger statements)
+- [ ] CHK-005 No unused imports or variables
+
+## 1. TDD Compliance (MANDATORY)
+
+- [ ] CHK-006 Tests written BEFORE implementation code
+- [ ] CHK-007 Tests verified to FAIL before writing implementation
+- [ ] CHK-008 Unit test coverage ≥80%
+- [ ] CHK-009 Integration tests for all API endpoints
+- [ ] CHK-010 E2E tests for complete user flows
+
+## 2. Routing Compliance (MANDATORY)
+
+- [ ] CHK-011 Routing preference documented in spec.md
+- [ ] CHK-012 prd.json has routing metadata for all stories
+- [ ] CHK-013 Complexity classifications correct for story scope
+- [ ] CHK-014 Estimated costs are reasonable
+- [ ] CHK-015 Mode selection appropriate for complexity
+
+## 3. Schema & Database
 
-- [ ] CHK-001 [US-001] User table has all required fields (id, email, password_hash, confirmed, timestamps)
-- [ ] CHK-002 [US-001] Email field has UNIQUE constraint
-- [ ] CHK-003 [US-001] Indexes created on frequently queried fields (email)
-- [ ] CHK-004 [Gap] Consider adding last_login_at timestamp for analytics
-- [ ] CHK-005 [US-001] Migration script tested on clean database
+- [ ] CHK-016 [US-001] User table has all required fields (id, email, password_hash, confirmed, timestamps)
+- [ ] CHK-017 [US-001] Email field has UNIQUE constraint
+- [ ] CHK-018 [US-001] Indexes created on frequently queried fields (email)
+- [ ] CHK-019 [Gap] Consider adding last_login_at timestamp for analytics
+- [ ] CHK-020 [US-001] Migration script tested on clean database
 
-## Backend Logic
+## 4. Backend Logic
 
-- [ ] CHK-006 [US-001] Password hashing uses bcrypt with appropriate cost factor
-- [ ] CHK-007 [US-001] Email validation prevents common typos and invalid formats
-- [ ] CHK-008 [US-002] JWT tokens include user ID and expiration
-- [ ] CHK-009 [US-002] Token verification handles expired tokens gracefully
-- [ ] CHK-010 [Ambiguity] Password reset flow not specified - out of scope?
+- [ ] CHK-021 [US-001] Password hashing uses bcrypt with appropriate cost factor
+- [ ] CHK-022 [US-001] Email validation prevents common typos and invalid formats
+- [ ] CHK-023 [US-002] JWT tokens include user ID and expiration
+- [ ] CHK-024 [US-002] Token verification handles expired tokens gracefully
+- [ ] CHK-025 [Ambiguity] Password reset flow not specified - out of scope?
 
-## API Integration
+## 5. API Integration
 
-- [ ] CHK-011 [US-001] POST /api/auth/register returns 201 on success
-- [ ] CHK-012 [US-001] Register endpoint returns 400 for invalid email
-- [ ] CHK-013 [US-001] Register endpoint returns 409 for duplicate email
-- [ ] CHK-014 [US-002] POST /api/auth/login returns 401 for wrong password
-- [ ] CHK-015 [US-002] Login endpoint returns 403 for unconfirmed account
-- [ ] CHK-016 [Edge Case] Rate limiting on auth endpoints to prevent brute force
+- [ ] CHK-026 [US-001] POST /api/auth/register returns 201 on success
+- [ ] CHK-027 [US-001] Register endpoint returns 400 for invalid email
+- [ ] CHK-028 [US-001] Register endpoint returns 409 for duplicate email
+- [ ] CHK-029 [US-002] POST /api/auth/login returns 401 for wrong password
+- [ ] CHK-030 [US-002] Login endpoint returns 403 for unconfirmed account
+- [ ] CHK-031 [Edge Case] Rate limiting on auth endpoints to prevent brute force
 
-## Testing & Validation
+## 6. Testing & Validation
 
-- [ ] CHK-017 [US-001] Unit tests for password hashing utility
-- [ ] CHK-018 [US-001] Unit tests for email validation
-- [ ] CHK-019 [US-002] Integration test for full registration flow
-- [ ] CHK-020 [US-002] Integration test for login flow
-- [ ] CHK-021 [US-003] E2E test for email confirmation
-- [ ] CHK-022 [Constitution] Test coverage meets minimum 80% requirement
+- [ ] CHK-032 [US-001] Unit tests for password hashing utility
+- [ ] CHK-033 [US-001] Unit tests for email validation
+- [ ] CHK-034 [US-002] Integration test for full registration flow
+- [ ] CHK-035 [US-002] Integration test for login flow
+- [ ] CHK-036 [US-003] E2E test for email confirmation
+- [ ] CHK-037 [Constitution] Test coverage meets minimum 80% requirement
 
-## Security & Permissions
+## 7. Security & Permissions
 
-- [ ] CHK-023 [US-001] Passwords never logged or exposed in errors
-- [ ] CHK-024 [US-001] Password requirements enforced (min length, complexity)
-- [ ] CHK-025 [US-002] JWT secret stored in environment variable, not code
-- [ ] CHK-026 [US-002] Token expiration validated on every request
-- [ ] CHK-027 [Gap] Consider adding account lockout after N failed attempts
+- [ ] CHK-038 [US-001] Passwords never logged or exposed in errors
+- [ ] CHK-039 [US-001] Password requirements enforced (min length, complexity)
+- [ ] CHK-040 [US-002] JWT secret stored in environment variable, not code
+- [ ] CHK-041 [US-002] Token expiration validated on every request
+- [ ] CHK-042 [Gap] Consider adding account lockout after N failed attempts
 
-## Performance & UX
+## 8. Performance & UX
 
-- [ ] CHK-028 [US-001] Registration completes within 2 seconds
-- [ ] CHK-029 [US-002] Login completes within 1 second
-- [ ] CHK-030 [US-003] Confirmation email sent within 30 seconds
-- [ ] CHK-031 [Edge Case] Graceful handling when email service is down
+- [ ] CHK-043 [US-001] Registration completes within 2 seconds
+- [ ] CHK-044 [US-002] Login completes within 1 second
+- [ ] CHK-045 [US-003] Confirmation email sent within 30 seconds
+- [ ] CHK-046 [Edge Case] Graceful handling when email service is down
 
-## Documentation
+## 9. Documentation
 
-- [ ] CHK-032 API endpoints documented with examples
-- [ ] CHK-033 Environment variables documented in README
-- [ ] CHK-034 Database schema documented
+- [ ] CHK-047 API endpoints documented with examples
+- [ ] CHK-048 Environment variables documented in README
+- [ ] CHK-049 Database schema documented
 ```
 
 ---
@@ -171,3 +262,4 @@ Ensure checklist includes items for constitution MUST rules:
 - Identify gaps and ambiguities with `[Gap]` and `[Ambiguity]` tags
 - Each item must be independently verifiable
 - Balance between comprehensiveness and practicality
+- **Mandatory sections (Quality Gates, TDD, Routing) must always be included**