@atlashub/smartstack-cli 4.17.0 → 4.18.0

package/templates/skills/business-analyse/steps/step-03d-validate.md

@@ -5,7 +5,7 @@ model: sonnet
 next_step: steps/step-03a1-setup.md OR steps/step-04a-collect.md (conditional)
 ---
 
-> **Context files:** `_shared.md` | `_module-loop.md`
+> **Context files:** `_shared.md` | `_module-loop.md` | `_rules.md`
 
 # Step 3d: Validation & Loop
 
@@ -15,29 +15,24 @@ next_step: steps/step-03a1-setup.md OR steps/step-04a-collect.md (conditional)
 - This step VALIDATES the specification from step-03c, writes it to feature.json, and decides loop continuation
 - ALWAYS verify specification completeness before writing
 - ALL communication in `{language}`
+- ALWAYS run the iteration safety guard BEFORE the loop decision (max 30 modules hard cap, 15 warning)
 
 ## MODE DETECTION (inherited from step-03a1)
 
 > **CRITICAL: Re-check your execution mode before proceeding.**
 
 **IF you are running as a TEAM AGENT** (your prompt contains `PROPOSE & REVIEW` or `team-lead` as recipient):
-  → **NEVER** use `AskUserQuestion` in ANY section below (sections 9d, 10, 12)
-  → Section 9d: if validation fails, AUTO-CORRECT silently (no user options)
-  → Section 12: **SKIP ENTIRELY** — go directly to section 12-bis (Agent Mode)
+  → **NEVER** use `AskUserQuestion` in ANY phase below
+  → Phase 3: if validation fails, AUTO-CORRECT silently (no user options)
+  → Phase 6: **SKIP section 12** — go directly to section 12-bis (Agent Mode)
   → After writing feature.json, send `PROPOSAL_READY` to team lead via SendMessage
   → NEVER present options/menus to the user — you are an autonomous agent
 
 **IF you are running in the MAIN CONVERSATION** (classic inline mode):
   → Normal interactive mode — use `AskUserQuestion` as documented
   → Section 12-bis does NOT apply to you
-- **ID NAMING RULE (MANDATORY, NO EXCEPTION):**
-  All IDs MUST include a module prefix to guarantee application-wide uniqueness.
-  The prefix is derived from the module code initials (2-4 chars):
-    UserManagement → UM | VehicleManagement → VM | PartsInventory → PI
-    RepairManagement → RM | MaintenanceSchedule → MS | DataSync → DS
-    Notifications → NT | Dashboard → DB | Orders → OR | Customers → CU
 
-  NEVER use bare IDs (UC-001, BR-VAL-001) in multi-module mode.
+- **Rules:** See `_rules.md` § "ID Naming Convention" (MANDATORY, NO EXCEPTION)
 
 ## YOUR TASK
 
@@ -45,150 +40,126 @@ Validate the module specification for completeness and consistency, write to fea
 
 ---
 
-### 9. Per-Module Validation
+## Phase 1: AUTO-FIX (silent — no output)
 
-#### 9a. Completeness Checks
+> **Apply all auto-fix rules BEFORE validation. No user interaction, no display.**
+
+**1a. Wireframe field names** — Apply `_rules.md` § "Auto-Fix: Wireframe Field Names":
+- For each wireframe in `specification.uiWireframes` (or `specification.wireframes`):
+  - Rename `title` → `screen`, `name` → `screen`, `ascii` → `mockup`, `content` → `mockup` (only if canonical field absent)
+- Store normalized wireframes under `specification.uiWireframes`
+
+**1b. Entity attribute types** — Apply `_rules.md` § "Auto-Fix: Entity Attribute Type Inference":
+- For each entity attribute missing a `type` field, infer from the name pattern table
+- Normalize free-text `validation` into structured `maxLength` where applicable
+- Default `required` to `true` if undefined
+- Log count of auto-fixed attributes as a warning (defense-in-depth — step-03c should have caught these)
+
+---
+
+## Phase 2: VALIDATE (single pass)
 
 > **CRITICAL:** Checks MUST count ACTUAL elements in arrays, NOT declarative values.
 > A check that reports PASS when the array is empty is a LIE and BLOCKS downstream quality.
+> **Minimums:** See `_rules.md` § "Minimum Counts (Authoritative)" for all thresholds.
+
+Run ALL checks in a single pass. Each check has: name | minimum | blocking? | how to verify.
+
+### Completeness Checks
+
+| Check | Min | Blocking | How to verify |
+|-------|-----|----------|---------------|
+| entities | ≥ 2 | YES | `analysis.entities.length >= 2` |
+| entity attributes (each) | ≥ 3 | YES | Every entity has `attributes.length >= 3` |
+| entitySchemaFormat | attributes[] not fields[] | YES | `analysis.entities.every(e => e.attributes?.length > 0)` — no `tableName` or `primaryKey` |
+| entityAttributeTypes | ALL have `type` | YES | `analysis.entities.every(e => e.attributes.every(a => a.type))` |
+| actors | ≥ 2 | YES | `specification.actors.length >= 2` |
+| useCases | ≥ 6 | YES | `specification.useCases.length >= 6` |
+| functionalRequirements | ≥ 4 | YES | `specification.functionalRequirements.length >= 4` |
+| permissionMatrix | ≥ 5 perms, ≥ 2 roles | YES | `permissionMatrix.permissions.length >= 5 && permissionMatrix.roleAssignments.length >= 2` |
+| sections | ≥ 2 | YES | `specification.sections.length >= 2` |
+| wireframes | 1 per section | YES | `uiWireframes.length >= sections.length` (check BOTH key names) |
+| wireframeSchema | All required fields | YES | Every wireframe has: `screen`, `section`, `mockupFormat`, `elements[]` (non-empty), `componentMapping[]`, `layout` (object), `permissionsRequired[]` |
+| navigation | entries[] present | YES | `specification.navigation?.entries?.length >= 1` |
+| seedDataCore | 9 arrays present | YES | See seedDataCore detail below |
+| messages | ≥ 4 | YES | `specification.messages.length >= 4` |
+| validations | ≥ 1 | YES | `specification.validations.length >= 1` |
+| apiEndpoints | ≥ 5 | YES | `specification.apiEndpoints.length >= 5` |
+| i18nKeys | ≥ 42 leaves, 4 langs | YES | All leaf keys have fr/en/it/de |
+| gherkinScenarios | array, ≥ 1 entry | YES | `Array.isArray(gherkinScenarios) && gherkinScenarios.length >= 1` |
+| gherkinCount | ≥ 2 scenarios | NO (WARN) | Total scenario count across all entries |
+| lifeCycles | ≥ 1 (if entity has status) | YES | `specification.lifeCycles.length >= 1` if applicable |
+| dataLifecycle | present | YES | `analysis.dataLifecycle !== undefined` |
+| navigationIcons | non-null | YES | All navigation modules have non-null icon |
+
+**seedDataCore detail:** Verify all 9 arrays per `_rules.md` § "Minimum Counts":
+
+| Array | Min (1st module) | Min (2nd+ module) |
+|---|---|---|
+| navigationApplications | 1 | 0 |
+| applicationRoles | 1 | 0 |
+| navigationModules | 1 | 1 |
+| navigationSections | 1 | 1 |
+| navigationResources | 1 | 1 |
+| navigationTranslations | 2 | 2 |
+| permissions | 1 | 1 |
+| rolePermissions | 1 | 1 |
+| permissionConstants | 1 | 1 |
+
+### Consistency Checks
+
+| Check | Blocking | Rule |
+|-------|----------|------|
+| UC-FR linkage | YES | Every UC has ≥ 1 linked FR |
+| FR-BR linkage | NO (WARN) | Every FR has ≥ 1 linked BR |
+| BR references valid | YES | All BR references exist in `analysis.businessRules` |
+| Actors in permissions | YES | All actors appear in `permissionMatrix` |
+| Permission path format | YES | Module-level `{app}.{module}.{action}` or section-level `{app}.{module}.{section}.{action}` |
+| rolePermissions paths | YES | All paths match `permissions` paths |
+| API route prefix | YES | Consistent prefix across endpoints |
+
+### Convention Checks
+
+| Check | Blocking | Rule |
+|-------|----------|------|
+| UC ID format | YES | `UC-{PREFIX}-{NNN}` with module prefix |
+| FR ID format | YES | `FR-{PREFIX}-{NNN}` |
+| BR ID format | YES | `BR-{CAT}-{PREFIX}-{NNN}` |
+| Entity names | YES | PascalCase |
+| Field names | YES | camelCase |
+| Permission paths | YES | Dot-separated lowercase |
+| Navigation routes | YES | No `/list` or `/detail/:id` suffixes |
+
+### Format Checks
+
+> See `_rules.md` § "Format Checks" for canonical rules.
+
+| Check | Blocking | Rule |
+|-------|----------|------|
+| gherkinFormat | YES | Array `[{feature, scenarios}]`, not single object |
+| gherkinContent | YES | Each entry has `feature` (string) + `scenarios` (array) |
+| validationFormat | YES | `validations[].rules` is array, not singular string |
+| messageFormat | YES | `messages[]` has `message` field |
+| wireframeFields | YES | Uses `screen` (not `title`/`name`), `mockup` (not `ascii`/`content`) |
+
+### Failure Handling
+
+IF any blocking check fails:
+- **CONDITIONAL LOAD:** Read `references/validation-checklist.md` for detailed fix guidance
+- Display table of failures with details and fix recommendations
+- **BLOCKING ERROR:** Module specification incomplete → fix all failures before proceeding
+
+IF all blocking checks pass:
+- Display warning count (non-blocking)
+- Proceed to Phase 3
 
-| Section | Minimum | How to verify | Status |
-|---------|---------|---------------|--------|
-| actors | 2 | `specification.actors.length >= 2` | PASS/FAIL |
-| useCases | 2 | `specification.useCases.length >= 2` | PASS/FAIL |
-| functionalRequirements | 4 | `specification.functionalRequirements.length >= 4` | PASS/FAIL |
-| permissionMatrix | 1 resource × 2 roles | `specification.permissionMatrix.permissions.length >= 1 && specification.permissionMatrix.roleAssignments.length >= 2` | PASS/FAIL |
-| entities | 1 | `analysis.entities.length >= 1` | PASS/FAIL |
-| entitySchemaFormat | attributes[] not fields[] (BLOCKING) | `analysis.entities.every(e => e.attributes?.length > 0)` | PASS/FAIL |
-| entityAttributeTypes | ALL attributes have `type` field (BLOCKING) | `analysis.entities.every(e => e.attributes.every(a => a.type))` — **NOTE:** Entities in analysis phase may NOT have `type`. Step-03c auto-fix MUST have run first. If types are missing, RE-RUN step-03c auto-fix algorithm. | PASS/FAIL |
-| navigation | entries[] present (BLOCKING) | `specification.navigation?.entries?.length >= 1` | PASS/FAIL |
-| dataLifecycle | present in analysis (BLOCKING) | `analysis.dataLifecycle !== undefined` | PASS/FAIL |
-| wireframes | 1 per section (BLOCKING) | `(specification.uiWireframes \|\| specification.wireframes \|\| []).length >= (specification.sections \|\| []).length` (count REAL elements, check BOTH key names) | PASS/FAIL |
-| wireframeSchema | All required fields present (BLOCKING) | `(specification.uiWireframes \|\| specification.wireframes \|\| []).every(w => (w.screen \|\| w.title) && w.section && (w.mockup \|\| w.ascii \|\| w.content))` | PASS/FAIL |
-| sections | 1 (BLOCKING) | `specification.sections.length >= 1` (EVERY module needs at least 1 section) | PASS/FAIL |
-| gherkinScenarios | 1 array entry | `Array.isArray(specification.gherkinScenarios) && specification.gherkinScenarios.length >= 1` | PASS/FAIL |
-| gherkinFormat | Array not object (BLOCKING) | `Array.isArray(specification.gherkinScenarios)` (NOT a single object) | PASS/FAIL |
-| validations | 1 | `specification.validations.length >= 1` | PASS/FAIL |
-| validationFormat | rules[] array (BLOCKING) | `specification.validations.every(v => Array.isArray(v.rules))` (NOT singular `rule`) | PASS/FAIL |
-| messages | 4 | `specification.messages.length >= 4` | PASS/FAIL |
-| messageFormat | `message` field present (BLOCKING) | `specification.messages.every(m => m.message)` | PASS/FAIL |
-| lifeCycles | 1 (if entity has status) | `specification.lifeCycles.length >= 1` (if any entity has status/state field) | PASS/FAIL |
-| seedDataCore | 9 arrays present with content | See detailed check below | PASS/FAIL (BLOCKING) |
-| apiEndpoints | 1 | `specification.apiEndpoints.length >= 1` | PASS/FAIL |
-| i18nKeys | present | `specification.i18nKeys !== undefined && specification.i18nKeys !== null` | PASS/FAIL |
-| navigationIcons | non-null | `specification.seedDataCore.navigationModules.every(m => m.icon !== null)` | PASS/FAIL |
-
-**seedDataCore detailed check (BLOCKING):**
-```javascript
-const sdc = specification.seedDataCore;
-const currentModuleIndex = metadata.workflow?.currentModuleIndex || 0;
-const checks = [
-  // navigationApplications and applicationRoles: required for first module (index 0), can be empty for subsequent modules
-  { key: "navigationApplications", actual: sdc.navigationApplications?.length || 0, min: currentModuleIndex === 0 ? 1 : 0 },
-  { key: "applicationRoles",      actual: sdc.applicationRoles?.length || 0,       min: currentModuleIndex === 0 ? 1 : 0 },
-  { key: "navigationModules",      actual: sdc.navigationModules?.length || 0,      min: 1 },
-  { key: "navigationSections",     actual: sdc.navigationSections?.length || 0,     min: 1 },  // EVERY module needs ≥1 section
-  { key: "navigationResources",    actual: sdc.navigationResources?.length || 0,    min: 1 },
-  { key: "navigationTranslations", actual: sdc.navigationTranslations?.length || 0, min: 2 },  // min fr+en
-  { key: "permissions",            actual: sdc.permissions?.length || 0,            min: 1 },
-  { key: "rolePermissions",        actual: sdc.rolePermissions?.length || 0,        min: 1 },
-  { key: "permissionConstants",    actual: sdc.permissionConstants?.length || 0,    min: 1 }
-];
-const failures = checks.filter(c => c.actual < c.min);
-IF failures.length > 0:
-  BLOCKING ERROR: "seedDataCore incomplete — empty arrays: {failures.map(f => f.key).join(', ')}"
-  → Fix: Ensure specification.sections[] has ≥1 entry, then re-run 8f-bis transform
-```
-
-#### 9b. Consistency Checks
-
-- Every UC has ≥1 linked FR
-- Every FR has ≥1 linked BR
-- All BR references exist in analysis.businessRules
-- All actors appear in permissionMatrix
-- Permission paths use correct format: module-level `{app}.{module}.{action}` or section-level `{app}.{module}.{section}.{action}`
-- rolePermissions paths match permissions paths
-- API routes use consistent prefix
-
-#### 9c. Convention Checks
-
-- UC-NNN format
-- FR-NNN format
-- BR-{CATEGORY}-NNN format
-- Entity names PascalCase
-- Field names camelCase
-- Entity attribute format: `attributes[]` with {name, description}, NOT `fields[]` with {name, type} — entities must NOT have tableName or primaryKey
-- Wireframe structure: `screen` (not `name`/`title`), `mockup` (not `ascii`/`content`), `componentMapping` is array of {wireframeElement, reactComponent} (not plain key-value object), `layout` is object with regions (not string)
-- Wireframe field naming: uses `screen` (not `title`), `mockup` (not `ascii`) — auto-fix if wrong (see 9c-fix below)
-- Permission paths dot-separated lowercase
-
-#### 9c-fix. Auto-Fix Wireframe Field Names (MANDATORY before writing)
-
-> **CRITICAL:** The agent may use non-canonical field names (`title`, `ascii`, `name`, `content`).
-> These MUST be normalized to canonical names before writing to feature.json.
-
-```javascript
-// AUTO-FIX: Normalize wireframe field names before writing
-const wireframes = specification.uiWireframes || specification.wireframes || [];
-for (const wf of wireframes) {
-  if (wf.title && !wf.screen) { wf.screen = wf.title; delete wf.title; }
-  if (wf.ascii && !wf.mockup) { wf.mockup = wf.ascii; delete wf.ascii; }
-  if (wf.content && !wf.mockup) { wf.mockup = wf.content; delete wf.content; }
-  if (wf.name && !wf.screen) { wf.screen = wf.name; delete wf.name; }
-}
-// Store normalized wireframes back under canonical key
-specification.uiWireframes = wireframes;
-```
+---
 
-#### 9c-fix-entities. Auto-Fix Entity Attribute Types (MANDATORY before writing)
-
-> **DEFENSE-IN-DEPTH:** step-03c POST-CHECK should catch attributes without `type`,
-> but if any slip through to step-03d, auto-fix them here before writing to feature.json.
-> Uses the same type inference algorithm as step-03c POST-CHECK.
-
-```javascript
-// AUTO-FIX: Ensure all entity attributes have structured type
-const entities = analysis.entities || [];
-let entityAutoFixCount = 0;
-for (const entity of entities) {
-  for (const attr of entity.attributes || []) {
-    if (!attr.type) {
-      // Infer type from attribute name pattern
-      if (attr.validation?.match(/max\s*\d+/i) || attr.name.match(/name|title|code|description|label|email|phone|address/i)) {
-        attr.type = "string";
-        const maxMatch = attr.validation?.match(/max\s*(\d+)/i);
-        if (maxMatch) attr.maxLength = parseInt(maxMatch[1]);
-      } else if (attr.name.match(/id$/i)) {
-        attr.type = "Guid";
-      } else if (attr.name.match(/date|At$/i)) {
-        attr.type = "DateTime";
-      } else if (attr.name.match(/is[A-Z]|has[A-Z]|active|enabled/)) {
-        attr.type = "bool";
-      } else if (attr.name.match(/amount|salary|rate|price|total/i)) {
-        attr.type = "decimal";
-      } else if (attr.name.match(/count|number|order|sort|index/i)) {
-        attr.type = "int";
-      } else {
-        attr.type = "string"; // safe default
-      }
-      // Normalize free-text maxLength
-      if (typeof attr.validation === 'string' && !attr.maxLength) {
-        const m = attr.validation.match(/max\s*(\d+)/i);
-        if (m) attr.maxLength = parseInt(m[1]);
-      }
-      if (attr.required === undefined) attr.required = true;
-      entityAutoFixCount++;
-    }
-  }
-}
-if (entityAutoFixCount > 0) {
-  console.warn(`DEFENSE-IN-DEPTH: auto-fixed ${entityAutoFixCount} attributes without type in step-03d`);
-}
-```
+## Phase 3: DECIDE + WRITE VALIDATION
 
-#### 9d. Decision
+### 3a. Decision
 
-> **TEAM AGENT MODE:** If running as team agent, SKIP AskUserQuestion. On FAIL → auto-correct silently. On PASS → proceed directly to section 11 (write). NEVER present options to the user.
+> **TEAM AGENT MODE:** If running as team agent, SKIP AskUserQuestion. On FAIL → auto-correct silently. On PASS → proceed directly. NEVER present options to the user.
 
 **INLINE MODE ONLY (main conversation):**
 
@@ -207,9 +178,9 @@ IF validation FAIL:
       description: "Accepter malgré les erreurs (risqué)"
   ```
 
-#### 9e. Write Module Validation Section (MANDATORY)
+### 3b. Write Module Validation Section (MANDATORY)
 
-> **The module feature.json MUST have a `validation` section recording the results of steps 9a-9d.**
+> **The module feature.json MUST have a `validation` section recording the results of Phase 2.**
 
 ```
 ba-writer.enrichSection({
@@ -218,10 +189,10 @@ ba-writer.enrichSection({
   data: {
     validatedAt: "{ISO timestamp}",
     completenessChecks: [
-      { "section": "useCases", "count": {count}, "minimum": 2, "status": "PASS|FAIL" },
+      { "section": "useCases", "count": {count}, "minimum": 6, "status": "PASS|FAIL" },
       { "section": "functionalRequirements", "count": {count}, "minimum": 4, "status": "PASS|FAIL" },
       { "section": "wireframes", "count": {count}, "minimum": {section_count}, "status": "PASS|FAIL" },
-      { "section": "seedDataCore", "count": 7, "minimum": 7, "status": "PASS|FAIL" }
+      { "section": "seedDataCore", "count": 9, "minimum": 9, "status": "PASS|FAIL" }
     ],
     consistencyChecks: [
       { "check": "UC-FR linkage", "passed": {n}, "warnings": {n}, "errors": {n}, "status": "PASS|FAIL" },
@@ -249,73 +220,11 @@ ba-writer.enrichSection({
 })
 ```
 
-#### 9e-POST-CHECK: Validation Section Persistence (BLOCKING)
-
-> **CRITICAL:** The `validation` section MUST be persisted to feature.json. Without it, consolidation checks fail.
-
-```bash
-MODULE_JSON="{module_feature_json_path}"
-node -e "const d=JSON.parse(require('fs').readFileSync(process.argv[1],'utf-8'));
-if(!d.validation||!d.validation.decision) { console.error('FAIL: validation section missing or incomplete'); process.exit(1); }
-console.log('PASS: validation section present with decision');" "$MODULE_JSON"
-```
-
-IF this check FAILS → re-execute section 9e write and re-run this check.
-
-#### 9f. Module Specification Checklist (BLOCKING)
-
-> **CRITICAL:** This checklist MUST be FULLY COMPLETED before marking module status = "specified".
-
-**Execute the comprehensive validation checklist:**
-
-Run the 29-check validation process across 10 categories:
-- Data Model (4 checks) | Business Rules (3 checks) | Use Cases & FRs (4 checks)
-- Permissions (3 checks) | UI & Navigation (4 checks) | I18N & Messages (3 checks)
-- Seed Data (2 checks) | API Endpoints (2 checks) | Validations (1 check) | Gherkin (3 checks)
-
-```javascript
-const blockingFailures = checks.filter(c => c.blocking && c.status === "FAIL");
-
-IF blockingFailures.length > 0:
-  // CONDITIONAL LOAD: Only load detailed checklist on validation failure
-  Read references/validation-checklist.md
-  Display:
-    - Full validation logic for FAILED checks
-    - Exact requirements (minimums, patterns, formats)
-    - Fix recommendations for each failure
-
-  BLOCKING ERROR: Module specification incomplete
-  → Fix all failures before proceeding
-
-ELSE:
-  All blocking checks passed ✓
-  Display: "{warnings_count} warnings (non-blocking)"
-  → Proceed to mark module as "specified"
-```
-
-**Optimization:** The detailed 280-line validation-checklist.md is loaded **only when validation fails** (saves ~10,000 tokens on success path).
-
 ---
 
-### 9g. Anti-Premature-Completion Guard (MANDATORY)
-
-> **CRITICAL — NEVER say "the analysis is complete" or "ready for /ralph-loop" at this point.**
-> Step-03d is the END of SPECIFICATION, NOT the end of the BA workflow.
-> Steps 04a → 04b → 04c (consolidation) + 05a → 05b → 05c (handoff) are STILL REQUIRED.
-> Without handoff, /ralph-loop will generate an INCOMPLETE PRD (no frontend, no tests).
-
-**FORBIDDEN phrases in step-03d output:**
-- "L'analyse métier est complète" / "The business analysis is complete"
-- "Prêt pour /ralph-loop" / "Ready for /ralph-loop"
-- "Vous pouvez maintenant lancer /ralph-loop"
-- Any variation suggesting the BA is finished or /ralph-loop can be invoked
-
-**REQUIRED phrasing:**
-- "Module {name} spécifié. {Remaining} modules restants." (if more modules)
-- "Tous les modules spécifiés. Passage à la consolidation (étapes 04a-04c)..." (if last module)
-- NEVER mention /ralph-loop — only step-05c (ralph readiness) validates the handoff
+## Phase 4: SUMMARY + WRITE FEATURE.JSON
 
-### 10. Module Summary with Roles & Permissions
+### 4a. Module Summary with Roles & Permissions
 
 Display comprehensive summary:
 
@@ -349,15 +258,19 @@ Display comprehensive summary:
 
 {IF validation PASS}:
   → Module validé automatiquement
-  → Passage automatique au module suivant (section 12)
+  → Passage automatique au module suivant (Phase 6)
 
 {IF validation FAIL}:
-  → Afficher les erreurs et offrir les options de correction (section 9d)
+  → Afficher les erreurs et offrir les options de correction (Phase 3)
 ```
 
----
+> **Anti-Premature-Completion Guard:** NEVER say "the analysis is complete" or "ready for /ralph-loop" at this point.
+> Step-03d is the END of SPECIFICATION, NOT the end of the BA workflow.
+> Steps 04a → 04b → 04c (consolidation) + 05a → 05b → 05c (handoff) are STILL REQUIRED.
+> **FORBIDDEN phrases:** "L'analyse métier est complète", "Prêt pour /ralph-loop", "Vous pouvez maintenant lancer /ralph-loop"
+> **REQUIRED phrasing:** "Module {name} spécifié. {Remaining} modules restants." or "Tous les modules spécifiés. Passage à la consolidation (étapes 04a-04c)..."
 
-### 11. Write Module Feature.json
+### 4b. Write Module Feature.json
 
 ```
 // Write analysis section with ALL subsections
@@ -383,7 +296,7 @@ ba-writer.enrichSection({
     functionalRequirements: [{id, statement, priority, linkedRules, linkedUseCases, acceptanceCriteria}],  // 8c
     permissionMatrix: {permissions: [], roleAssignments: []},     // 8d
     navigation: {entries: []},                                    // 8e
-    seedDataCore: {navigationModules, navigationSections, navigationResources, navigationTranslations, permissions, rolePermissions, permissionConstants},  // 8f (7 arrays)
+    seedDataCore: {navigationApplications, applicationRoles, navigationModules, navigationSections, navigationResources, navigationTranslations, permissions, rolePermissions, permissionConstants},  // 8f (9 arrays)
     gherkinScenarios: [{feature, scenarios: [{name, tags, given, when, then}]}],  // 8g
     validations: [{entity, field, rules, errorMessageKey}],       // 8h
     messages: [{code, type, title, message, i18nKey}],            // 8i
@@ -396,8 +309,8 @@ ba-writer.enrichSection({
   }
 })
 
-// Write validation results from step 9
-// (Already written in step 9e above)
+// Write validation results from Phase 3
+// (Already written in Phase 3b above)
 
 ba-writer.updateStatus({module_feature_id}, "specified")
 
@@ -405,52 +318,21 @@ ba-writer.updateStatus({module_feature_id}, "specified")
 ba-writer.updateModuleStatus({feature_id}, {currentModule.code}, "specified")
 ```
 
-#### 11-POST-CHECK: Verify Written Data (BLOCKING)
-
-> **CRITICAL — Data loss prevention.** After writing, READ BACK the module feature.json and verify the following arrays are **non-empty**:
-
-```javascript
-// READ BACK the written feature.json
-const written = ba-reader.read({module_feature_id});
-
-// BLOCKING checks — if ANY fails, the write was incomplete
-const checks = [
-  { key: "specification.actors",          actual: written.specification?.actors?.length,          min: 2 },
-  { key: "specification.useCases",        actual: written.specification?.useCases?.length,        min: 2 },
-  { key: "specification.wireframes",      actual: (written.specification?.uiWireframes?.length || written.specification?.wireframes?.length || 0), min: 1 },
-  { key: "specification.sections",        actual: written.specification?.sections?.length,        min: 1 },
-  { key: "specification.seedDataCore",    actual: Object.keys(written.specification?.seedDataCore || {}).length, min: 7 },
-  { key: "specification.lifeCycles",      actual: written.specification?.lifeCycles?.length,      min: 0 },
-  { key: "specification.gherkinScenarios",actual: written.specification?.gherkinScenarios?.length,min: 1 },
-  { key: "specification.apiEndpoints",    actual: written.specification?.apiEndpoints?.length,    min: 1 }
-];
-
-const failures = checks.filter(c => (c.actual || 0) < c.min);
-
-IF failures.length > 0:
-  BLOCKING ERROR: "Feature.json write INCOMPLETE — missing data in: {failures.map(f => f.key).join(', ')}"
-  → Re-execute section 11 write with ALL specification data
-  → DO NOT proceed to next module until ALL checks pass
-
-// SPECIAL CHECK: wireframes content verification (check BOTH key names)
-const wireframes = written.specification?.uiWireframes || written.specification?.wireframes || [];
-IF wireframes.length > 0:
-  const emptyMockups = wireframes.filter(wf => !wf.mockup && !wf.ascii && !wf.content);
-  IF emptyMockups.length > 0:
-    WARNING: "{emptyMockups.length} wireframes have empty mockup content — verify step-03b data"
-
-// SPECIAL CHECK: wireframes >= sections
-const sectionCount = written.specification?.sections?.length || 0;
-IF wireframes.length < sectionCount:
-  BLOCKING ERROR: "{wireframes.length} wireframes < {sectionCount} sections — wireframes MISSING for some sections"
-  → Re-read wireframes from conversation context and re-write to feature.json
-```
+---
 
-#### 11-POST-CHECK-BASH: Acceptance Criteria Verification (BLOCKING)
+## Phase 5: VERIFY (bash)
 
-> **CRITICAL:** The pseudocode checks above are interpreted by the model — they can be "passed" incorrectly.
+> **CRITICAL:** The validation checks in Phase 2 are interpreted by the model — they can be "passed" incorrectly.
 > This bash check reads the REAL file on disk and provides an objective verification.
-> See [references/acceptance-criteria.md](../references/acceptance-criteria.md) for the full acceptance criteria definition.
+>
+> **Canonical acceptance criteria (AC-01 to AC-17):** See [references/acceptance-criteria.md](../references/acceptance-criteria.md).
+> The script below EXTENDS those criteria with step-03d-specific checks:
+> - Navigation entries present (`specification.navigation.entries`)
+> - `analysis.dataLifecycle` section present
+> - `validation` section recorded
+> - i18n 4-language completeness (AC-18)
+>
+> If you need the standalone script (for debugging or handoff gate), use the one in `acceptance-criteria.md`.
 
 ```bash
 MODULE_JSON="{module_feature_json_path}"
@@ -462,13 +344,15 @@ const analysis = data.analysis || {};
 const wf = spec.uiWireframes || spec.wireframes || [];
 const sections = spec.sections || [];
 const checks = [
-  ['entities >= 1',          (analysis.entities||[]).length,          1],
+  ['entities >= 2',          (analysis.entities||[]).length,          2],
   ['useCases >= 2',          (spec.useCases||[]).length,              2],
   ['FRs >= 4',               (spec.functionalRequirements||[]).length,4],
   ['wireframes >= 1',        wf.length,                               1],
   ['wireframes >= sections', wf.length,                               sections.length],
   ['sections >= 1',          sections.length,                          1],
-  ['seedDataCore 7 arrays',  Object.keys(spec.seedDataCore||{}).filter(k=>(spec.seedDataCore||{})[k]&&(spec.seedDataCore||{})[k].length>0).length, 7],
+  // CP-02: modules 2+ may have navigationApplications=[] and applicationRoles=[] (correct per _rules.md)
+  // Minimum = 9 for first module, 7 for subsequent modules
+  ['seedDataCore arrays', (() => { const sdc=spec.seedDataCore||{}; return Object.keys(sdc).filter(k=>Array.isArray(sdc[k])&&sdc[k].length>0).length; })(), (() => { const sdc=spec.seedDataCore||{}; const hasApp=(sdc.navigationApplications||[]).length>0||(sdc.applicationRoles||[]).length>0; return hasApp?9:7; })()],
   ['gherkin is array',       Array.isArray(spec.gherkinScenarios)?1:0, 1],
   ['apiEndpoints >= 1',      (spec.apiEndpoints||[]).length,           1],
   ['messages >= 4',          (spec.messages||[]).length,               4],
@@ -516,15 +400,13 @@ IF this check FAILS:
 - Identify which criteria failed from the output
 - Fix the corresponding data (re-read from conversation context, re-generate, or re-run the step that produces it)
 - Re-write to feature.json
-- Re-run the POST-CHECK until PASS
-
-> **WHY:** Step-03b now writes wireframes intermediately (since fix), but step-03d section 11 does the FULL write.
-> This bash POST-CHECK is the ultimate safety net — it reads the REAL file and verifies ALL acceptance criteria.
-> The pseudocode checks (section 9a) catch issues early; this bash check catches anything the model missed.
+- Re-run this check until PASS
 
 ---
 
-### 11-bis. Deploy Incremental Interactive HTML (MANDATORY)
+## Phase 6: DEPLOY + ROUTE
+
+### 6a. Deploy Incremental Interactive HTML (MANDATORY)
 
 > **After each module is specified, deploy/update the interactive HTML document with all available data.**
 > The client can review completed modules while the next module is being specified.
@@ -535,7 +417,46 @@ Uses the **same mapping** as step-05b-deploy.md — only difference is `moduleSp
 
 ---
 
-### 12. Loop Decision
+### 6b. Iteration Safety Guard (MAX MODULES CHECK)
+
+> **DEFENSIVE CHECK — Run BEFORE loop decision to prevent infinite loops.**
+
+```
+// Read loop state from feature.json
+const moduleOrder = metadata.workflow.moduleOrder || [];
+const completedModules = metadata.workflow.completedModules || [];
+const currentModuleIndex = metadata.workflow.currentModuleIndex || 0;
+const totalModules = moduleOrder.length;
+
+// Guard thresholds
+const MAX_MODULES_WARN = 15;
+const MAX_MODULES_BLOCK = 30;
+
+IF totalModules > MAX_MODULES_BLOCK:
+  BLOCKING ERROR:
+  "Module count ({totalModules}) exceeds maximum allowed ({MAX_MODULES_BLOCK}).
+   This is likely a decomposition error. Return to step-02-decomposition.md
+   and consolidate or split into multiple applications."
+  STOP — do not continue loop
+
+IF totalModules > MAX_MODULES_WARN:
+  WARNING (non-blocking):
+  "Module count ({totalModules}) is high. Consider whether some modules
+   could be grouped or split into separate applications.
+   Continuing with {totalModules - completedModules.length} modules remaining."
+
+// Sanity check: currentModuleIndex should never exceed totalModules
+IF currentModuleIndex >= totalModules AND completedModules.length < totalModules:
+  BLOCKING ERROR:
+  "Loop state inconsistency: currentModuleIndex ({currentModuleIndex}) >= totalModules ({totalModules})
+   but only {completedModules.length} modules are marked complete.
+   Fix: Check metadata.workflow in feature.json and correct the state manually."
+  STOP
+```
+
+---
+
+### 6c. Loop Decision (section 12)
 
 > **TEAM AGENT MODE: SKIP THIS ENTIRE SECTION.** If you are a team agent (your prompt contains `PROPOSE & REVIEW`), go directly to **section 12-bis** below. Section 12 is for inline mode ONLY. You MUST NOT load the next step or advance the module loop — the team lead handles orchestration.
 
@@ -654,7 +575,7 @@ SendMessage({
 - **`REVISION:{moduleCode}\n{feedback}`** → Apply changes:
   1. Read the feedback
   2. Update the relevant sections in feature.json via ba-writer
-  3. Re-run validation checks (section 9)
+  3. Re-run validation checks (Phase 2)
   4. Re-build summary and send new `PROPOSAL_READY`
   5. Max **3 revision cycles** — after 3, send `ERROR:{moduleCode}:Max revisions reached` and stop
 
@@ -696,19 +617,6 @@ This terminates your process. Do NOT output any text after `shutdown_response`.
 
 ---
 
-## SELF-VERIFICATION (MANDATORY before loading next step)
-
-Before proceeding to step-03a (next module) or step-04 (consolidation), VERIFY:
-
-1. **Module feature.json has specification section** with ALL sub-sections (actors, useCases, functionalRequirements, permissionMatrix, navigation, seedDataCore, gherkinScenarios, validations, messages, lifeCycles, apiEndpoints, i18nKeys, sections, uiWireframes)
-2. **Module feature.json status** = "specified" (set by section 11)
-3. **Master modules[].status** for this module = "specified" (set by section 11)
-4. **ba-interactive.html exists** and includes data for this module (set by section 11-bis)
-
-**IF any check fails → FIX before proceeding.** Do NOT advance the module loop with incomplete data.
-
----
-
 ## SINGLE-MODULE MODE
 
 When only 1 module in moduleOrder:
@@ -737,8 +645,8 @@ Read metadata.workflow.currentModule
 | Loaded | Not Loaded |
 |--------|------------|
 | _shared.md | Other module feature.json (full) |
-| feature-schema.json | Questionnaires not needed |
-| Questionnaires for this module | Templates |
+| _rules.md | Questionnaires not needed |
+| feature-schema.json | Templates |
 | Completed modules summary (100 lines max) | React viewer files |
 
 ---