prizmkit 1.1.76 → 1.1.78

package/bundled/VERSION.json

@@ -1,5 +1,5 @@
 {
-  "frameworkVersion": "1.1.76",
-  "bundledAt": "2026-06-13T04:58:49.240Z",
-  "bundledFrom": "17f8257"
+  "frameworkVersion": "1.1.78",
+  "bundledAt": "2026-06-14T15:40:03.496Z",
+  "bundledFrom": "190a723"
 }

package/bundled/skills/_metadata.json

@@ -1,5 +1,5 @@
 {
-  "version": "1.1.76",
+  "version": "1.1.78",
   "skills": {
     "prizm-kit": {
       "description": "Full-lifecycle dev toolkit. Covers spec-driven development, Prizm context docs, code quality, debugging, deployment, and knowledge management.",

package/bundled/skills/app-planner/SKILL.md

@@ -332,22 +332,23 @@ For each selected layer, run the rules Q&A workflow. This follows the 4-phase ru
 
 **Phase A — Load layer resources:**
 - Read `${SKILL_DIR}/references/rules/<layer>/fixed-rules.md` — industry-consensus rules injected without asking
-- Read `${SKILL_DIR}/references/rules/<layer>/question-bank.md` — interactive questions organized in groups (G1→G10)
+- Read `${SKILL_DIR}/references/rules/<layer>/question-bank.md` — interactive questions organized in groups (G1→G10): authoritative source for question text, options, "Recommended" markers, and Notes
+- Read `${SKILL_DIR}/references/rules/<layer>/question-manifest.json` — machine-readable structure for this layer. **This is your asking checklist.** It lists, per question: `group`, `required`, `maps_to` (which template placeholders the answer fills), and conditional fields (`required_if`, `auto_derived_when`, `options_vary_by`). Its `groups[]` carries each group's `quick_mode` flag, and `template_placeholders` is the expected-set for the Phase D self-check. Use the manifest to track coverage; use question-bank.md for the actual wording you present to the user. If a question id in one file is absent from the other, trust question-bank.md for content and note the drift.
 
 **Phase B — Interactive Q&A:**
 - Ask questions one group at a time (max 3 questions per message), as defined in question-bank.md
 - Each question shows a "Recommended" option to reduce decision cost
-- **Quick mode**: ask only the following groups per layer. All other groups adopt recommended defaults silently.
-  - **Frontend**: G1 (Tech Stack), G2 (Styling), G3 (State & Data Fetching), G7 (Testing & Quality). Skip: G4 (Design System), G5 (Responsive), G6 (i18n), G8 (AI Vibecoding), G9 (Performance).
-  - **Backend**: G1 (Language & Runtime), G2 (Framework & Architecture), G3 (API Style), G4 (Data Layer), G7 (Testing & Quality). Skip: G5 (Auth), G6 (Infrastructure), G8 (Observability), G9 (AI Constraints).
-  - **Database**: G1 (Database Selection), G2 (Data Modeling), G3 (Migration), G7 (AI Constraints). Skip: G4 (Index & Performance), G5 (Security & Compliance), G6 (High Availability & Ops).
-  - **Mobile**: G1 (Platform & Language), G2 (Architecture), G3 (UI Framework), G4 (Navigation & State), G7 (Testing). Skip: G5 (Networking & Data), G6 (Platform Features), G8 (App Distribution), G9 (Performance & Accessibility), G10 (AI Constraints).
-- **Full mode**: ask all groups in order (G1→G9 for frontend/backend, G1→G7 for database, G1→G10 for mobile)
+- **Quick mode**: ask only the groups whose `quick_mode` is `true` in `question-manifest.json`. All other groups adopt recommended defaults silently. (The manifest is the single source of truth for quick-mode membership — do not hardcode group lists here.)
+- **Full mode**: ask all groups in manifest order (`groups[]`).
+- **Conditional questions** (driven by the manifest's per-question fields):
+  - `required_if: "<expr>"` — ask this question only when the expression over prior answers holds (e.g. Q14 `required_if: Q13 != D`). If the condition is false, the question is legitimately skipped — not a coverage gap.
+  - `auto_derived_when: "<expr>"` — when this holds, fill the mapped placeholder(s) from the prior answer without asking (e.g. backend Q6 `auto_derived_when: Q5 in [GraphQL, gRPC]`). Count as satisfied, not skipped.
+  - `options_vary_by: "<Qid>"` — the question is still asked; only its option list depends on that prior answer (e.g. framework/ORM options vary by language). Never affects whether the question is required.
 - Shortcut commands work at any point:
   - `recommended` / `default` → adopt all recommended for current group
   - `all recommended` → adopt all recommended for all remaining groups
   - `skip` → mark current group as "Not required at this stage"
-- Record answers in memory after each group.
+- Record answers in memory after each group. Track which manifest questions are answered, auto-derived, or conditionally skipped so Phase D can verify coverage.
 
 **Phase C — Auto-derivation:**
 - Read `${SKILL_DIR}/references/rules/<layer>/derivation-rules.md`
@@ -357,8 +358,10 @@ For each selected layer, run the rules Q&A workflow. This follows the 4-phase ru
 **Phase D — Render and write:**
 - Read `${SKILL_DIR}/references/rules/<layer>/template.md`
 - Fill all template placeholders with accumulated content from Phases A+B+C
-- **Post-render self-check**: scan for residual `{{ ` or ` }}` — count must be 0 before writing
-- Generate Appendix A (Deny List) and Appendix B (Recommended Tools) per template instructions
+- **Post-render self-check** (driven by `question-manifest.json` → `template_placeholders`):
+  1. **Coverage pass** — for every placeholder in `from_questions`, confirm it traces to an answered question OR an `auto_derived_when` path OR a conditionally-skipped question (`required_if` false). If a `from_questions` placeholder has no source, you skipped a required question — go back and ask it before writing.
+  2. **Residual pass** — scan the rendered document for any residual `{{ ` or ` }}`; count must be 0. Placeholders in `from_fixed_rules` / `auto_generated` / `metadata` are filled from fixed-rules.md, Phase D generation, and project metadata respectively — they are NOT expected to come from Q&A, but they MUST still be rendered (no residual braces).
+- Generate Appendix A (Deny List) and Appendix B (Recommended Tools) per template instructions — these fill the `auto_generated` placeholders
 - Create `.prizmkit/rules/` directory if it doesn't exist
 - Write `.prizmkit/rules/<layer>-rules.md`
 

package/bundled/skills/app-planner/references/rules/backend/question-manifest.json

@@ -0,0 +1,46 @@
+{
+  "schema_version": "app-planner-question-manifest-v1",
+  "layer": "backend",
+  "total_questions": 20,
+  "_doc": "Machine-readable structure for backend question-bank.md. Question TEXT/options/Recommended/Notes are authoritative in question-bank.md; this file carries ONLY structure: group membership, quick-mode, question->placeholder mapping, and conditional logic. Keep Qids and group ids in sync with question-bank.md. The AI reads this as its asking checklist (Phase A) and self-check expected-set (Phase D).",
+  "_conditions": "required_if / auto_derived_when use simple expressions over recorded answers, e.g. 'Q5 == RESTful', 'Q13 != D', 'Q5 in [GraphQL, gRPC]'. options_vary_by names a prior answer that changes the OPTION LIST only (question is still asked; never affects required).",
+  "groups": [
+    { "id": "G1", "topic": "Language & Runtime", "quick_mode": true },
+    { "id": "G2", "topic": "Framework & Architecture", "quick_mode": true },
+    { "id": "G3", "topic": "API Style", "quick_mode": true },
+    { "id": "G4", "topic": "Data Layer", "quick_mode": true },
+    { "id": "G5", "topic": "Auth", "quick_mode": false },
+    { "id": "G6", "topic": "Infrastructure", "quick_mode": false },
+    { "id": "G7", "topic": "Testing & Quality", "quick_mode": true },
+    { "id": "G8", "topic": "Observability", "quick_mode": false },
+    { "id": "G9", "topic": "AI Constraints", "quick_mode": false }
+  ],
+  "questions": [
+    { "id": "Q1", "group": "G1", "topic": "Programming Language", "maps_to": ["language", "tech_stack_rules"], "required": true },
+    { "id": "Q2", "group": "G1", "topic": "Runtime Version", "maps_to": ["runtime_version"], "required": true },
+    { "id": "Q3", "group": "G2", "topic": "Web Framework", "maps_to": ["framework", "tech_stack_rules"], "required": true, "options_vary_by": "Q1", "note_open_ended_when": "Q1 == Custom" },
+    { "id": "Q4", "group": "G2", "topic": "Architecture Pattern", "maps_to": ["architecture", "arch_rules"], "required": true },
+    { "id": "Q5", "group": "G3", "topic": "API Style", "maps_to": ["api_style", "api_rules"], "required": true },
+    { "id": "Q6", "group": "G3", "topic": "API Documentation", "maps_to": ["api_docs"], "required": true, "required_if": "Q5 == RESTful", "auto_derived_when": "Q5 in [GraphQL, gRPC]" },
+    { "id": "Q7", "group": "G4", "topic": "ORM / Data Access", "maps_to": ["orm", "data_rules"], "required": true, "options_vary_by": "Q1", "note_open_ended_when": "Q1 == Custom" },
+    { "id": "Q8", "group": "G4", "topic": "Database", "maps_to": ["database"], "required": true },
+    { "id": "Q9", "group": "G5", "topic": "Authentication Scheme", "maps_to": ["auth_scheme", "auth_rules"], "required": true },
+    { "id": "Q10", "group": "G6", "topic": "Caching", "maps_to": ["cache", "cache_rules"], "required": true },
+    { "id": "Q11", "group": "G6", "topic": "Message Queue", "maps_to": ["mq", "mq_rules"], "required": true },
+    { "id": "Q12", "group": "G6", "topic": "Containerization & Deployment", "maps_to": ["container", "deploy_rules"], "required": true },
+    { "id": "Q13", "group": "G7", "topic": "Test Coverage Requirements", "maps_to": ["test_requirement", "test_rules"], "required": true },
+    { "id": "Q14", "group": "G7", "topic": "Test Framework", "maps_to": ["test_framework"], "required": true, "required_if": "Q13 != D", "options_vary_by": "Q1" },
+    { "id": "Q15", "group": "G7", "topic": "Mock Strategy", "maps_to": ["mock_strategy", "test_rules"], "required": true },
+    { "id": "Q16", "group": "G8", "topic": "Logging", "maps_to": ["logging", "observability_rules"], "required": true },
+    { "id": "Q17", "group": "G8", "topic": "Monitoring & Tracing", "maps_to": ["monitoring", "observability_rules"], "required": true },
+    { "id": "Q18", "group": "G9", "topic": "AI Permission to Add Dependencies", "maps_to": ["ai_dependency_rule"], "required": true },
+    { "id": "Q19", "group": "G9", "topic": "AI Modifying Shared Modules", "maps_to": ["ai_breaking_change_rule"], "required": true },
+    { "id": "Q20", "group": "G9", "topic": "AI Modifying Configuration", "maps_to": ["ai_config_rule"], "required": true }
+  ],
+  "template_placeholders": {
+    "from_questions": ["language", "runtime_version", "framework", "architecture", "api_style", "api_docs", "orm", "database", "auth_scheme", "cache", "mq", "container", "test_requirement", "test_framework", "mock_strategy", "logging", "monitoring", "ai_dependency_rule", "ai_breaking_change_rule", "ai_config_rule", "tech_stack_rules", "arch_rules", "api_rules", "auth_rules", "data_rules", "cache_rules", "mq_rules", "deploy_rules", "observability_rules", "test_rules"],
+    "from_fixed_rules": ["FIXED_RULES_STRUCTURE", "FIXED_RULES_API", "FIXED_RULES_ERROR", "FIXED_RULES_SECURITY", "FIXED_RULES_RATE_LIMITING", "FIXED_RULES_DATABASE", "FIXED_RULES_OBSERVABILITY", "FIXED_RULES_TRACING", "FIXED_RULES_CONFIG", "FIXED_RULES_ASYNC", "FIXED_RULES_MESSAGE_DELIVERY", "FIXED_RULES_GRACEFUL_SHUTDOWN", "FIXED_RULES_TEST", "FIXED_RULES_AI_BASE"],
+    "auto_generated": ["deny_list_summary", "recommended_libs"],
+    "metadata": ["project_name", "generated_at"]
+  }
+}

package/bundled/skills/app-planner/references/rules/database/question-manifest.json

@@ -0,0 +1,39 @@
+{
+  "schema_version": "app-planner-question-manifest-v1",
+  "layer": "database",
+  "total_questions": 15,
+  "_doc": "Machine-readable structure for database question-bank.md. Question TEXT/options/Recommended/Notes are authoritative in question-bank.md; this file carries ONLY structure: group membership, quick-mode, question->placeholder mapping, and conditional logic. Keep Qids and group ids in sync with question-bank.md. The AI reads this as its asking checklist (Phase A) and self-check expected-set (Phase D).",
+  "_conditions": "required_if / auto_derived_when use simple expressions over recorded answers. options_vary_by names a prior answer that changes the OPTION LIST only (question is still asked; never affects required). A single answer may fill more than one placeholder (a TL;DR value + a rules-block), both listed in maps_to.",
+  "groups": [
+    { "id": "G1", "topic": "Database Selection", "quick_mode": true },
+    { "id": "G2", "topic": "Data Modeling", "quick_mode": true },
+    { "id": "G3", "topic": "Migration", "quick_mode": true },
+    { "id": "G4", "topic": "Index & Performance", "quick_mode": false },
+    { "id": "G5", "topic": "Security & Compliance", "quick_mode": false },
+    { "id": "G6", "topic": "High Availability & Ops", "quick_mode": false },
+    { "id": "G7", "topic": "AI Constraints", "quick_mode": true }
+  ],
+  "questions": [
+    { "id": "Q1", "group": "G1", "topic": "Primary Database", "maps_to": ["database", "tech_rules"], "required": true },
+    { "id": "Q2", "group": "G1", "topic": "Cache Layer", "maps_to": ["cache", "cache_rules"], "required": true },
+    { "id": "Q3", "group": "G2", "topic": "Primary Key Strategy", "maps_to": ["pk_strategy", "schema_rules"], "required": true },
+    { "id": "Q4", "group": "G2", "topic": "Soft Delete", "maps_to": ["soft_delete", "schema_rules"], "required": true },
+    { "id": "Q5", "group": "G2", "topic": "Normalization Level", "maps_to": ["normalization", "schema_rules"], "required": true },
+    { "id": "Q6", "group": "G3", "topic": "Migration Tool", "maps_to": ["migration_tool", "migration_rules"], "required": true },
+    { "id": "Q7", "group": "G4", "topic": "Query Complexity", "maps_to": ["workload_type", "performance_rules"], "required": true },
+    { "id": "Q8", "group": "G4", "topic": "Estimated Data Volume", "maps_to": ["data_scale", "performance_rules"], "required": true },
+    { "id": "Q9", "group": "G5", "topic": "Data Sensitivity Level", "maps_to": ["data_sensitivity", "security_rules"], "required": true },
+    { "id": "Q10", "group": "G5", "topic": "Audit Requirements", "maps_to": ["audit", "audit_rules"], "required": true, "multi_select": true },
+    { "id": "Q11", "group": "G6", "topic": "Deployment Method", "maps_to": ["deployment", "ops_rules"], "required": true },
+    { "id": "Q12", "group": "G6", "topic": "Backup Strategy", "maps_to": ["backup", "ops_rules"], "required": true },
+    { "id": "Q13", "group": "G6", "topic": "High Availability Requirements", "maps_to": ["ha", "ops_rules"], "required": true },
+    { "id": "Q14", "group": "G7", "topic": "AI Permission to Modify Database Structure", "maps_to": ["ai_ddl_rule", "ai_ddl_permission"], "required": true },
+    { "id": "Q15", "group": "G7", "topic": "AI Safety Constraints", "maps_to": ["ai_safety_rule", "ai_safety_constraint"], "required": true }
+  ],
+  "template_placeholders": {
+    "from_questions": ["database", "tech_rules", "cache", "cache_rules", "pk_strategy", "schema_rules", "soft_delete", "normalization", "migration_tool", "migration_rules", "workload_type", "performance_rules", "data_scale", "data_sensitivity", "security_rules", "audit", "audit_rules", "deployment", "ops_rules", "backup", "ha", "ai_ddl_rule", "ai_ddl_permission", "ai_safety_rule", "ai_safety_constraint"],
+    "from_fixed_rules": ["FIXED_RULES_AI_BASE", "FIXED_RULES_BACKUP", "FIXED_RULES_CONNECTION", "FIXED_RULES_INDEX", "FIXED_RULES_MIGRATION", "FIXED_RULES_PERFORMANCE", "FIXED_RULES_QUERY", "FIXED_RULES_SCHEMA", "FIXED_RULES_SECURITY", "FIXED_RULES_TRANSACTION", "FIXED_RULES_TYPES"],
+    "auto_generated": ["deny_list_summary", "recommended_libs"],
+    "metadata": ["project_name", "generated_at"]
+  }
+}

package/bundled/skills/app-planner/references/rules/frontend/question-manifest.json

@@ -0,0 +1,51 @@
+{
+  "schema_version": "app-planner-question-manifest-v1",
+  "layer": "frontend",
+  "total_questions": 25,
+  "_doc": "Machine-readable structure for frontend question-bank.md. Question TEXT/options/Recommended/Notes are authoritative in question-bank.md; this file carries ONLY structure: group membership, quick-mode, question->placeholder mapping, and conditional logic. Keep Qids and group ids in sync with question-bank.md. The AI reads this as its asking checklist (Phase A) and self-check expected-set (Phase D).",
+  "_conditions": "required_if / auto_derived_when use simple expressions over recorded answers, e.g. 'Q15 in [A, B]'. options_vary_by names a prior answer that changes the OPTION LIST/recommendation only (question is still asked; never affects required).",
+  "groups": [
+    { "id": "G1", "topic": "Tech Stack", "quick_mode": true },
+    { "id": "G2", "topic": "Styling", "quick_mode": true },
+    { "id": "G3", "topic": "State & Data Fetching", "quick_mode": true },
+    { "id": "G4", "topic": "Design System", "quick_mode": false },
+    { "id": "G5", "topic": "Responsive & Adaptation", "quick_mode": false },
+    { "id": "G6", "topic": "i18n & Accessibility", "quick_mode": false },
+    { "id": "G7", "topic": "Testing & Quality", "quick_mode": true },
+    { "id": "G8", "topic": "AI Vibecoding Constraints", "quick_mode": false },
+    { "id": "G9", "topic": "Performance Baseline", "quick_mode": false }
+  ],
+  "questions": [
+    { "id": "Q1", "group": "G1", "topic": "Frontend Framework", "maps_to": ["framework", "tech_stack_rules"], "required": true },
+    { "id": "Q2", "group": "G1", "topic": "Meta-Framework", "maps_to": ["meta_framework", "tech_stack_rules"], "required": true, "options_vary_by": "Q1" },
+    { "id": "Q3", "group": "G1", "topic": "Package Manager", "maps_to": ["package_manager", "tech_stack_rules"], "required": true },
+    { "id": "Q4", "group": "G2", "topic": "Styling Solution", "maps_to": ["style_solution", "style_specific_rules"], "required": true },
+    { "id": "Q4b", "group": "G2", "topic": "Font Loading Strategy", "maps_to": ["font_strategy", "performance_rules"], "required": true },
+    { "id": "Q5", "group": "G3", "topic": "Global State Library", "maps_to": ["state_lib", "state_rules"], "required": true, "options_vary_by": "Q1" },
+    { "id": "Q6", "group": "G3", "topic": "Server State Library", "maps_to": ["server_state_lib", "server_state_rules"], "required": true },
+    { "id": "Q7", "group": "G3", "topic": "API Type Source", "maps_to": ["api_type_source", "server_state_rules"], "required": true },
+    { "id": "Q8", "group": "G4", "topic": "Primary Design/Mockup Source", "maps_to": ["design_source"], "required": true },
+    { "id": "Q9", "group": "G4", "topic": "Token Naming Layers", "maps_to": ["token_layering", "token_layering_rules"], "required": true },
+    { "id": "Q10", "group": "G4", "topic": "Dark Mode", "maps_to": ["dark_mode", "dark_mode_rules"], "required": true },
+    { "id": "Q11", "group": "G5", "topic": "Adaptation Strategy", "maps_to": ["responsive_strategy", "breakpoint_rules"], "required": true },
+    { "id": "Q12", "group": "G5", "topic": "Breakpoint Scheme", "maps_to": ["breakpoint_scheme", "breakpoint_rules"], "required": true },
+    { "id": "Q13", "group": "G6", "topic": "Internationalization", "maps_to": ["i18n", "i18n_rules"], "required": true },
+    { "id": "Q14", "group": "G6", "topic": "Accessibility Target", "maps_to": ["a11y_level", "a11y_extra_rules"], "required": true },
+    { "id": "Q15", "group": "G7", "topic": "Test Coverage Requirements", "maps_to": ["test_coverage", "test_rules"], "required": true },
+    { "id": "Q16", "group": "G7", "topic": "Unit Test Framework", "maps_to": ["unit_test_framework", "test_rules"], "required": true, "required_if": "Q15 in [A, B]" },
+    { "id": "Q17", "group": "G7", "topic": "E2E Framework", "maps_to": ["e2e_framework", "test_rules"], "required": true, "required_if": "Q15 in [A, C]" },
+    { "id": "Q18", "group": "G8", "topic": "AI Component Index Sync", "maps_to": ["ai_index_rule"], "required": true },
+    { "id": "Q19", "group": "G8", "topic": "AI Permission to Add Dependencies", "maps_to": ["ai_dependency_rule"], "required": true },
+    { "id": "Q20", "group": "G8", "topic": "AI Impact Analysis Before Modifying Shared Components", "maps_to": ["ai_breaking_change_rule"], "required": true },
+    { "id": "Q21", "group": "G8", "topic": "AI Permission to Modify Config Files", "maps_to": ["ai_config_rule"], "required": true },
+    { "id": "Q22", "group": "G8", "topic": "AI Single File Generation Limit", "maps_to": ["ai_max_lines"], "required": true },
+    { "id": "Q23", "group": "G9", "topic": "First Screen LCP Target", "maps_to": ["lcp_target", "performance_rules"], "required": true },
+    { "id": "Q24", "group": "G9", "topic": "Single Chunk Size Limit", "maps_to": ["bundle_size", "performance_rules"], "required": true }
+  ],
+  "template_placeholders": {
+    "from_questions": ["framework", "meta_framework", "package_manager", "style_solution", "style_specific_rules", "font_strategy", "performance_rules", "state_lib", "state_rules", "server_state_lib", "server_state_rules", "api_type_source", "design_source", "token_layering", "token_layering_rules", "dark_mode", "dark_mode_rules", "responsive_strategy", "breakpoint_rules", "breakpoint_scheme", "i18n", "i18n_rules", "a11y_level", "a11y_extra_rules", "test_coverage", "test_rules", "unit_test_framework", "e2e_framework", "ai_index_rule", "ai_dependency_rule", "ai_breaking_change_rule", "ai_config_rule", "ai_max_lines", "lcp_target", "bundle_size", "tech_stack_rules"],
+    "from_fixed_rules": ["FIXED_RULES_A11Y", "FIXED_RULES_AI_BASE", "FIXED_RULES_COMPONENT_CONTRACT", "FIXED_RULES_DENY_LIST", "FIXED_RULES_ERROR_HANDLING", "FIXED_RULES_GIT", "FIXED_RULES_I18N_BASELINE", "FIXED_RULES_NAMING", "FIXED_RULES_PERFORMANCE", "FIXED_RULES_SECURITY", "FIXED_RULES_TYPESCRIPT"],
+    "auto_generated": ["deny_list_summary", "recommended_libs"],
+    "metadata": ["project_name", "generated_at", "project_scope"]
+  }
+}

package/bundled/skills/app-planner/references/rules/mobile/question-manifest.json

@@ -0,0 +1,47 @@
+{
+  "schema_version": "app-planner-question-manifest-v1",
+  "layer": "mobile",
+  "total_questions": 20,
+  "_doc": "Machine-readable structure for mobile question-bank.md. Question TEXT/options/Recommended/Notes are authoritative in question-bank.md; this file carries ONLY structure: group membership, quick-mode, question->placeholder mapping, and conditional logic. Keep Qids and group ids in sync with question-bank.md. The AI reads this as its asking checklist (Phase A) and self-check expected-set (Phase D).",
+  "_conditions": "required_if / auto_derived_when use simple expressions over recorded answers, e.g. 'Q12 in [A, B]'. options_vary_by names a prior answer that changes the OPTION LIST only (question is still asked; never affects required). dual_native_repeat_when notes Q1=E (both native) repeats the question per platform.",
+  "groups": [
+    { "id": "G1", "topic": "Platform & Language", "quick_mode": true },
+    { "id": "G2", "topic": "Architecture", "quick_mode": true },
+    { "id": "G3", "topic": "UI Framework", "quick_mode": true },
+    { "id": "G4", "topic": "Navigation & State", "quick_mode": true },
+    { "id": "G5", "topic": "Networking & Data", "quick_mode": false },
+    { "id": "G6", "topic": "Platform Features", "quick_mode": false },
+    { "id": "G7", "topic": "Testing", "quick_mode": true },
+    { "id": "G8", "topic": "App Distribution", "quick_mode": false },
+    { "id": "G9", "topic": "Performance & Accessibility", "quick_mode": false },
+    { "id": "G10", "topic": "AI Constraints", "quick_mode": false }
+  ],
+  "questions": [
+    { "id": "Q1", "group": "G1", "topic": "Target Platform", "maps_to": ["platform", "tech_stack_rules"], "required": true },
+    { "id": "Q2", "group": "G1", "topic": "Minimum OS Version", "maps_to": ["min_os_version", "tech_stack_rules"], "required": true },
+    { "id": "Q3", "group": "G2", "topic": "Architecture Pattern", "maps_to": ["architecture", "arch_rules"], "required": true },
+    { "id": "Q4", "group": "G3", "topic": "UI Framework", "maps_to": ["ui_framework", "ui_rules"], "required": true, "options_vary_by": "Q1", "dual_native_repeat_when": "Q1 == E" },
+    { "id": "Q5", "group": "G4", "topic": "Navigation Strategy", "maps_to": ["navigation", "navigation_rules"], "required": true },
+    { "id": "Q6", "group": "G4", "topic": "State Management", "maps_to": ["state_management", "state_rules"], "required": true, "options_vary_by": "Q1", "dual_native_repeat_when": "Q1 == E" },
+    { "id": "Q7", "group": "G5", "topic": "Networking Library", "maps_to": ["networking", "networking_rules"], "required": true, "options_vary_by": "Q1", "dual_native_repeat_when": "Q1 == E" },
+    { "id": "Q8", "group": "G5", "topic": "Local Persistence", "maps_to": ["persistence", "persistence_rules"], "required": true, "options_vary_by": "Q1", "dual_native_repeat_when": "Q1 == E" },
+    { "id": "Q9", "group": "G6", "topic": "Push Notifications", "maps_to": ["push_notifications", "platform_features_rules"], "required": true },
+    { "id": "Q10", "group": "G6", "topic": "Background Tasks", "maps_to": ["background_tasks", "platform_features_rules"], "required": true },
+    { "id": "Q11", "group": "G6", "topic": "Permissions Strategy", "maps_to": ["permissions_strategy"], "required": true },
+    { "id": "Q12", "group": "G7", "topic": "Test Coverage Requirements", "maps_to": ["test_coverage", "test_rules"], "required": true },
+    { "id": "Q13", "group": "G7", "topic": "Unit Test Framework", "maps_to": ["unit_test_framework"], "required": true, "required_if": "Q12 in [A, B]", "options_vary_by": "Q1", "dual_native_repeat_when": "Q1 == E" },
+    { "id": "Q14", "group": "G7", "topic": "UI/E2E Test Framework", "maps_to": ["e2e_framework"], "required": true, "required_if": "Q12 in [A, C]", "options_vary_by": "Q1", "dual_native_repeat_when": "Q1 == E" },
+    { "id": "Q15", "group": "G8", "topic": "Distribution Method", "maps_to": ["distribution", "distribution_rules"], "required": true },
+    { "id": "Q16", "group": "G9", "topic": "Performance Targets", "maps_to": ["performance_target", "performance_rules"], "required": true },
+    { "id": "Q17", "group": "G9", "topic": "Accessibility Targets", "maps_to": ["a11y_target", "a11y_rules"], "required": true },
+    { "id": "Q18", "group": "G10", "topic": "AI Permission to Add Dependencies", "maps_to": ["ai_dependency_rule"], "required": true },
+    { "id": "Q19", "group": "G10", "topic": "AI Impact Analysis Before Modifying Shared Code", "maps_to": ["ai_breaking_change_rule"], "required": true },
+    { "id": "Q20", "group": "G10", "topic": "AI Platform-Specific Code Generation", "maps_to": ["ai_platform_rule"], "required": true }
+  ],
+  "template_placeholders": {
+    "from_questions": ["platform", "tech_stack_rules", "min_os_version", "architecture", "arch_rules", "ui_framework", "ui_rules", "navigation", "navigation_rules", "state_management", "state_rules", "networking", "networking_rules", "persistence", "persistence_rules", "push_notifications", "platform_features_rules", "background_tasks", "permissions_strategy", "test_coverage", "test_rules", "unit_test_framework", "e2e_framework", "distribution", "distribution_rules", "performance_target", "performance_rules", "a11y_target", "a11y_rules", "ai_dependency_rule", "ai_breaking_change_rule", "ai_platform_rule"],
+    "from_fixed_rules": ["FIXED_RULES_A11Y", "FIXED_RULES_AI_BASE", "FIXED_RULES_DISTRIBUTION", "FIXED_RULES_NAVIGATION", "FIXED_RULES_NETWORKING", "FIXED_RULES_PERFORMANCE", "FIXED_RULES_PERSISTENCE", "FIXED_RULES_PLATFORM_FEATURES", "FIXED_RULES_SECURITY", "FIXED_RULES_STATE", "FIXED_RULES_STRUCTURE", "FIXED_RULES_TEST", "FIXED_RULES_UI"],
+    "auto_generated": ["deny_list_summary", "recommended_libs"],
+    "metadata": ["project_name", "generated_at"]
+  }
+}

package/bundled/skills/bugfix-pipeline-launcher/SKILL.md

@@ -152,7 +152,7 @@ Detect user intent from their message, then follow the corresponding workflow:
 
    **Question 4 — Advanced config?** (multiSelect: false):
    - No (default) — Use defaults for session timeout and failure behavior
-   - Yes — Configure session timeout and stop-on-failure options
+   - Yes — Configure session timeout, stop-on-failure, and reasoning effort options
 
    Note: Bug filter defaults to all bugs (by severity order). Default Critic to Off unless bugs have `severity: "critical"` or `severity: "high"` (in which case default to On). If the user selects "Other" on any option, handle their custom input.
 
@@ -172,6 +172,14 @@ Detect user intent from their message, then follow the corresponding workflow:
    - No (default) — Skip deployment after pipeline completes
    - Yes — Run /prizmkit-deploy automatically after all bugs fixed successfully (`ENABLE_DEPLOY=1`). Deployment is blocked if any bug was not fixed (status not 'completed', 'skipped', or 'needs_info').
 
+   **Question 4 — Reasoning effort** (multiSelect: false):
+   - Default (none) — Use CLI default
+   - low — Minimize reasoning, fastest output (`PRIZMKIT_EFFORT=low`)
+   - medium — Moderate reasoning (`PRIZMKIT_EFFORT=medium`)
+   - high — Thorough reasoning for complex tasks (`PRIZMKIT_EFFORT=high`)
+   - xhigh — Extensive reasoning (`PRIZMKIT_EFFORT=xhigh`)
+   - max — Maximum reasoning, Claude Code only (`PRIZMKIT_EFFORT=max`)
+
    **Environment variable mapping** (for translating user responses → env vars):
 
    | Config choice | Environment variable |
@@ -183,13 +191,13 @@ Detect user intent from their message, then follow the corresponding workflow:
    | Timeout: value | `SESSION_TIMEOUT=<seconds>` |
    | Stop on failure: On | `STOP_ON_FAILURE=1` |
    | Deploy: Yes | `ENABLE_DEPLOY=1` |
+   | Effort: value | `PRIZMKIT_EFFORT=<value>` |
 
    **Advanced environment variables** (not exposed in interactive menu, pass via `--env`):
 
    | Variable | Default | Purpose |
    |----------|---------|---------|
    | `MODEL` | (none) | AI model override (e.g. `claude-opus-4.6`) |
-   | `PRIZMKIT_EFFORT` | (none) | AI reasoning effort: `low`\|`medium`\|`high`\|`xhigh`\|`max` (max = Claude Code only) |
    | `AUTO_PUSH` | `0` | Auto-push to remote after successful bug fix (`1` to enable) |
    | `DEV_BRANCH` | auto-generated | Custom dev branch name (default: `bugfix/pipeline-{run_id}`) |
    | `HEARTBEAT_INTERVAL` | `30` | Heartbeat log interval in seconds |
@@ -208,7 +216,7 @@ Detect user intent from their message, then follow the corresponding workflow:
    ```
    With all options:
    ```bash
-   VERBOSE=1 MAX_RETRIES=5 SESSION_TIMEOUT=3600 ENABLE_DEPLOY=1 \
+   VERBOSE=1 MAX_RETRIES=5 SESSION_TIMEOUT=3600 ENABLE_DEPLOY=1 PRIZMKIT_EFFORT=high \
      .prizmkit/dev-pipeline/run-bugfix.sh run .prizmkit/plans/bug-fix-list.json
    ```
 

package/bundled/skills/feature-pipeline-launcher/SKILL.md

@@ -169,7 +169,7 @@ Detect user intent from their message, then follow the corresponding workflow:
 
    **Question 4 — Advanced config?** (multiSelect: false):
    - No (default) — Use defaults for session timeout and failure behavior
-   - Yes — Configure session timeout, stop-on-failure, and deploy-after-completion options
+   - Yes — Configure session timeout, stop-on-failure, deploy-after-completion, and reasoning effort options
 
    Default Critic to Off unless features have `estimated_complexity: "high"` or above (in which case default to On).
 
@@ -189,6 +189,14 @@ Detect user intent from their message, then follow the corresponding workflow:
    - No (default) — Skip deployment after pipeline completes
    - Yes — Run /prizmkit-deploy automatically after all features complete successfully (`ENABLE_DEPLOY=1`). Deployment is blocked if any feature did not complete successfully (status not 'completed' or manually 'skipped').
 
+   **Question 4 — Reasoning effort** (multiSelect: false):
+   - Default (none) — Use CLI default
+   - low — Minimize reasoning, fastest output (`PRIZMKIT_EFFORT=low`)
+   - medium — Moderate reasoning (`PRIZMKIT_EFFORT=medium`)
+   - high — Thorough reasoning for complex tasks (`PRIZMKIT_EFFORT=high`)
+   - xhigh — Extensive reasoning (`PRIZMKIT_EFFORT=xhigh`)
+   - max — Maximum reasoning, Claude Code only (`PRIZMKIT_EFFORT=max`)
+
    **Environment variable mapping** (for translating user responses → env vars):
 
    | Config choice | Environment variable |
@@ -200,13 +208,13 @@ Detect user intent from their message, then follow the corresponding workflow:
    | Timeout: value | `SESSION_TIMEOUT=<seconds>` |
    | Stop on failure: On | `STOP_ON_FAILURE=1` |
    | Deploy: Yes | `ENABLE_DEPLOY=1` |
+   | Effort: value | `PRIZMKIT_EFFORT=<value>` |
 
    **Advanced environment variables** (not exposed in interactive menu, pass via `--env`):
 
    | Variable | Default | Purpose |
    |----------|---------|---------|
    | `MODEL` | (none) | AI model override (e.g. `claude-opus-4.6`) |
-   | `PRIZMKIT_EFFORT` | (none) | AI reasoning effort: `low`\|`medium`\|`high`\|`xhigh`\|`max` (max = Claude Code only) |
    | `AUTO_PUSH` | `0` | Auto-push to remote after successful feature (`1` to enable) |
    | `DEV_BRANCH` | auto-generated | Custom dev branch name (default: `dev/{feature_id}-YYYYMMDDHHmm`) |
    | `HEARTBEAT_INTERVAL` | `30` | Heartbeat log interval in seconds |
@@ -226,7 +234,7 @@ Detect user intent from their message, then follow the corresponding workflow:
    ```
    With all options:
    ```bash
-   VERBOSE=1 ENABLE_CRITIC=true MAX_RETRIES=5 SESSION_TIMEOUT=3600 ENABLE_DEPLOY=1 \
+   VERBOSE=1 ENABLE_CRITIC=true MAX_RETRIES=5 SESSION_TIMEOUT=3600 ENABLE_DEPLOY=1 PRIZMKIT_EFFORT=high \
      .prizmkit/dev-pipeline/run-feature.sh run .prizmkit/plans/feature-list.json --features F-001:F-005
    ```
 
@@ -237,7 +245,7 @@ Detect user intent from their message, then follow the corresponding workflow:
    With all options:
    ```bash
    .prizmkit/dev-pipeline/launch-feature-daemon.sh start .prizmkit/plans/feature-list.json --features F-001:F-005 \
-     --env "VERBOSE=1 ENABLE_CRITIC=true MAX_RETRIES=5 ENABLE_DEPLOY=1"
+     --env "VERBOSE=1 ENABLE_CRITIC=true MAX_RETRIES=5 ENABLE_DEPLOY=1 PRIZMKIT_EFFORT=high"
    ```
 
    **Manual mode**: Print the assembled command(s) and **stop here**. Do not execute anything. Do not proceed to step 8.

package/bundled/skills/refactor-pipeline-launcher/SKILL.md

@@ -170,7 +170,7 @@ Detect user intent from their message, then follow the corresponding workflow:
 
    **Question 4 — Advanced config?** (multiSelect: false):
    - No (default) — Use defaults for critic review, session timeout, and failure behavior
-   - Yes — Configure critic review, session timeout, and stop-on-failure options
+   - Yes — Configure critic review, session timeout, stop-on-failure, and reasoning effort options
 
    Note: Refactor filter defaults to all refactor items (by priority order). If the user selects "Other" on any option, handle their custom input.
 
@@ -196,6 +196,16 @@ Detect user intent from their message, then follow the corresponding workflow:
 
    Default Critic to Off unless refactor items have `priority: "critical"` (in which case default to On).
 
+   **If advanced config was selected, also ask about reasoning effort** in a follow-up `AskUserQuestion` call:
+
+   **Question — Reasoning effort** (multiSelect: false):
+   - Default (none) — Use CLI default
+   - low — Minimize reasoning, fastest output (`PRIZMKIT_EFFORT=low`)
+   - medium — Moderate reasoning (`PRIZMKIT_EFFORT=medium`)
+   - high — Thorough reasoning for complex tasks (`PRIZMKIT_EFFORT=high`)
+   - xhigh — Extensive reasoning (`PRIZMKIT_EFFORT=xhigh`)
+   - max — Maximum reasoning, Claude Code only (`PRIZMKIT_EFFORT=max`)
+
    **Environment variable mapping** (for translating user responses → env vars):
 
    | Config choice | Environment variable |
@@ -209,13 +219,13 @@ Detect user intent from their message, then follow the corresponding workflow:
    | Timeout: value | `SESSION_TIMEOUT=<seconds>` |
    | Stop on failure: On | `STOP_ON_FAILURE=1` |
    | Deploy: Yes | `ENABLE_DEPLOY=1` |
+   | Effort: value | `PRIZMKIT_EFFORT=<value>` |
 
    **Advanced environment variables** (not exposed in interactive menu, pass via `--env`):
 
    | Variable | Default | Purpose |
    |----------|---------|---------|
    | `MODEL` | (none) | AI model override (e.g. `claude-opus-4.6`) |
-   | `PRIZMKIT_EFFORT` | (none) | AI reasoning effort: `low`\|`medium`\|`high`\|`xhigh`\|`max` (max = Claude Code only) |
    | `AUTO_PUSH` | `0` | Auto-push to remote after successful refactor (`1` to enable) |
    | `DEV_BRANCH` | auto-generated | Custom dev branch name (default: `refactor/pipeline-{run_id}`) |
    | `HEARTBEAT_INTERVAL` | `30` | Heartbeat log interval in seconds |
@@ -234,7 +244,7 @@ Detect user intent from their message, then follow the corresponding workflow:
    ```
    With all options:
    ```bash
-   VERBOSE=1 STRICT_BEHAVIOR_CHECK=1 MAX_RETRIES=5 SESSION_TIMEOUT=3600 ENABLE_DEPLOY=1 \
+   VERBOSE=1 STRICT_BEHAVIOR_CHECK=1 MAX_RETRIES=5 SESSION_TIMEOUT=3600 ENABLE_DEPLOY=1 PRIZMKIT_EFFORT=high \
      .prizmkit/dev-pipeline/run-refactor.sh run .prizmkit/plans/refactor-list.json
    ```
 

package/bundled/skills-windows/app-planner/SKILL.md

@@ -332,22 +332,23 @@ For each selected layer, run the rules Q&A workflow. This follows the 4-phase ru
 
 **Phase A — Load layer resources:**
 - Read `${SKILL_DIR}/references/rules/<layer>/fixed-rules.md` — industry-consensus rules injected without asking
-- Read `${SKILL_DIR}/references/rules/<layer>/question-bank.md` — interactive questions organized in groups (G1→G10)
+- Read `${SKILL_DIR}/references/rules/<layer>/question-bank.md` — interactive questions organized in groups (G1→G10): authoritative source for question text, options, "Recommended" markers, and Notes
+- Read `${SKILL_DIR}/references/rules/<layer>/question-manifest.json` — machine-readable structure for this layer. **This is your asking checklist.** It lists, per question: `group`, `required`, `maps_to` (which template placeholders the answer fills), and conditional fields (`required_if`, `auto_derived_when`, `options_vary_by`). Its `groups[]` carries each group's `quick_mode` flag, and `template_placeholders` is the expected-set for the Phase D self-check. Use the manifest to track coverage; use question-bank.md for the actual wording you present to the user. If a question id in one file is absent from the other, trust question-bank.md for content and note the drift.
 
 **Phase B — Interactive Q&A:**
 - Ask questions one group at a time (max 3 questions per message), as defined in question-bank.md
 - Each question shows a "Recommended" option to reduce decision cost
-- **Quick mode**: ask only the following groups per layer. All other groups adopt recommended defaults silently.
-  - **Frontend**: G1 (Tech Stack), G2 (Styling), G3 (State & Data Fetching), G7 (Testing & Quality). Skip: G4 (Design System), G5 (Responsive), G6 (i18n), G8 (AI Vibecoding), G9 (Performance).
-  - **Backend**: G1 (Language & Runtime), G2 (Framework & Architecture), G3 (API Style), G4 (Data Layer), G7 (Testing & Quality). Skip: G5 (Auth), G6 (Infrastructure), G8 (Observability), G9 (AI Constraints).
-  - **Database**: G1 (Database Selection), G2 (Data Modeling), G3 (Migration), G7 (AI Constraints). Skip: G4 (Index & Performance), G5 (Security & Compliance), G6 (High Availability & Ops).
-  - **Mobile**: G1 (Platform & Language), G2 (Architecture), G3 (UI Framework), G4 (Navigation & State), G7 (Testing). Skip: G5 (Networking & Data), G6 (Platform Features), G8 (App Distribution), G9 (Performance & Accessibility), G10 (AI Constraints).
-- **Full mode**: ask all groups in order (G1→G9 for frontend/backend, G1→G7 for database, G1→G10 for mobile)
+- **Quick mode**: ask only the groups whose `quick_mode` is `true` in `question-manifest.json`. All other groups adopt recommended defaults silently. (The manifest is the single source of truth for quick-mode membership — do not hardcode group lists here.)
+- **Full mode**: ask all groups in manifest order (`groups[]`).
+- **Conditional questions** (driven by the manifest's per-question fields):
+  - `required_if: "<expr>"` — ask this question only when the expression over prior answers holds (e.g. Q14 `required_if: Q13 != D`). If the condition is false, the question is legitimately skipped — not a coverage gap.
+  - `auto_derived_when: "<expr>"` — when this holds, fill the mapped placeholder(s) from the prior answer without asking (e.g. backend Q6 `auto_derived_when: Q5 in [GraphQL, gRPC]`). Count as satisfied, not skipped.
+  - `options_vary_by: "<Qid>"` — the question is still asked; only its option list depends on that prior answer (e.g. framework/ORM options vary by language). Never affects whether the question is required.
 - Shortcut commands work at any point:
   - `recommended` / `default` → adopt all recommended for current group
   - `all recommended` → adopt all recommended for all remaining groups
   - `skip` → mark current group as "Not required at this stage"
-- Record answers in memory after each group.
+- Record answers in memory after each group. Track which manifest questions are answered, auto-derived, or conditionally skipped so Phase D can verify coverage.
 
 **Phase C — Auto-derivation:**
 - Read `${SKILL_DIR}/references/rules/<layer>/derivation-rules.md`
@@ -357,8 +358,10 @@ For each selected layer, run the rules Q&A workflow. This follows the 4-phase ru
 **Phase D — Render and write:**
 - Read `${SKILL_DIR}/references/rules/<layer>/template.md`
 - Fill all template placeholders with accumulated content from Phases A+B+C
-- **Post-render self-check**: scan for residual `{{ ` or ` }}` — count must be 0 before writing
-- Generate Appendix A (Deny List) and Appendix B (Recommended Tools) per template instructions
+- **Post-render self-check** (driven by `question-manifest.json` → `template_placeholders`):
+  1. **Coverage pass** — for every placeholder in `from_questions`, confirm it traces to an answered question OR an `auto_derived_when` path OR a conditionally-skipped question (`required_if` false). If a `from_questions` placeholder has no source, you skipped a required question — go back and ask it before writing.
+  2. **Residual pass** — scan the rendered document for any residual `{{ ` or ` }}`; count must be 0. Placeholders in `from_fixed_rules` / `auto_generated` / `metadata` are filled from fixed-rules.md, Phase D generation, and project metadata respectively — they are NOT expected to come from Q&A, but they MUST still be rendered (no residual braces).
+- Generate Appendix A (Deny List) and Appendix B (Recommended Tools) per template instructions — these fill the `auto_generated` placeholders
 - Create `.prizmkit/rules/` directory if it doesn't exist
 - Write `.prizmkit/rules/<layer>-rules.md`
 

package/bundled/skills-windows/app-planner/references/rules/backend/question-manifest.json

@@ -0,0 +1,46 @@
+{
+  "schema_version": "app-planner-question-manifest-v1",
+  "layer": "backend",
+  "total_questions": 20,
+  "_doc": "Machine-readable structure for backend question-bank.md. Question TEXT/options/Recommended/Notes are authoritative in question-bank.md; this file carries ONLY structure: group membership, quick-mode, question->placeholder mapping, and conditional logic. Keep Qids and group ids in sync with question-bank.md. The AI reads this as its asking checklist (Phase A) and self-check expected-set (Phase D).",
+  "_conditions": "required_if / auto_derived_when use simple expressions over recorded answers, e.g. 'Q5 == RESTful', 'Q13 != D', 'Q5 in [GraphQL, gRPC]'. options_vary_by names a prior answer that changes the OPTION LIST only (question is still asked; never affects required).",
+  "groups": [
+    { "id": "G1", "topic": "Language & Runtime", "quick_mode": true },
+    { "id": "G2", "topic": "Framework & Architecture", "quick_mode": true },
+    { "id": "G3", "topic": "API Style", "quick_mode": true },
+    { "id": "G4", "topic": "Data Layer", "quick_mode": true },
+    { "id": "G5", "topic": "Auth", "quick_mode": false },
+    { "id": "G6", "topic": "Infrastructure", "quick_mode": false },
+    { "id": "G7", "topic": "Testing & Quality", "quick_mode": true },
+    { "id": "G8", "topic": "Observability", "quick_mode": false },
+    { "id": "G9", "topic": "AI Constraints", "quick_mode": false }
+  ],
+  "questions": [
+    { "id": "Q1", "group": "G1", "topic": "Programming Language", "maps_to": ["language", "tech_stack_rules"], "required": true },
+    { "id": "Q2", "group": "G1", "topic": "Runtime Version", "maps_to": ["runtime_version"], "required": true },
+    { "id": "Q3", "group": "G2", "topic": "Web Framework", "maps_to": ["framework", "tech_stack_rules"], "required": true, "options_vary_by": "Q1", "note_open_ended_when": "Q1 == Custom" },
+    { "id": "Q4", "group": "G2", "topic": "Architecture Pattern", "maps_to": ["architecture", "arch_rules"], "required": true },
+    { "id": "Q5", "group": "G3", "topic": "API Style", "maps_to": ["api_style", "api_rules"], "required": true },
+    { "id": "Q6", "group": "G3", "topic": "API Documentation", "maps_to": ["api_docs"], "required": true, "required_if": "Q5 == RESTful", "auto_derived_when": "Q5 in [GraphQL, gRPC]" },
+    { "id": "Q7", "group": "G4", "topic": "ORM / Data Access", "maps_to": ["orm", "data_rules"], "required": true, "options_vary_by": "Q1", "note_open_ended_when": "Q1 == Custom" },
+    { "id": "Q8", "group": "G4", "topic": "Database", "maps_to": ["database"], "required": true },
+    { "id": "Q9", "group": "G5", "topic": "Authentication Scheme", "maps_to": ["auth_scheme", "auth_rules"], "required": true },
+    { "id": "Q10", "group": "G6", "topic": "Caching", "maps_to": ["cache", "cache_rules"], "required": true },
+    { "id": "Q11", "group": "G6", "topic": "Message Queue", "maps_to": ["mq", "mq_rules"], "required": true },
+    { "id": "Q12", "group": "G6", "topic": "Containerization & Deployment", "maps_to": ["container", "deploy_rules"], "required": true },
+    { "id": "Q13", "group": "G7", "topic": "Test Coverage Requirements", "maps_to": ["test_requirement", "test_rules"], "required": true },
+    { "id": "Q14", "group": "G7", "topic": "Test Framework", "maps_to": ["test_framework"], "required": true, "required_if": "Q13 != D", "options_vary_by": "Q1" },
+    { "id": "Q15", "group": "G7", "topic": "Mock Strategy", "maps_to": ["mock_strategy", "test_rules"], "required": true },
+    { "id": "Q16", "group": "G8", "topic": "Logging", "maps_to": ["logging", "observability_rules"], "required": true },
+    { "id": "Q17", "group": "G8", "topic": "Monitoring & Tracing", "maps_to": ["monitoring", "observability_rules"], "required": true },
+    { "id": "Q18", "group": "G9", "topic": "AI Permission to Add Dependencies", "maps_to": ["ai_dependency_rule"], "required": true },
+    { "id": "Q19", "group": "G9", "topic": "AI Modifying Shared Modules", "maps_to": ["ai_breaking_change_rule"], "required": true },
+    { "id": "Q20", "group": "G9", "topic": "AI Modifying Configuration", "maps_to": ["ai_config_rule"], "required": true }
+  ],
+  "template_placeholders": {
+    "from_questions": ["language", "runtime_version", "framework", "architecture", "api_style", "api_docs", "orm", "database", "auth_scheme", "cache", "mq", "container", "test_requirement", "test_framework", "mock_strategy", "logging", "monitoring", "ai_dependency_rule", "ai_breaking_change_rule", "ai_config_rule", "tech_stack_rules", "arch_rules", "api_rules", "auth_rules", "data_rules", "cache_rules", "mq_rules", "deploy_rules", "observability_rules", "test_rules"],
+    "from_fixed_rules": ["FIXED_RULES_STRUCTURE", "FIXED_RULES_API", "FIXED_RULES_ERROR", "FIXED_RULES_SECURITY", "FIXED_RULES_RATE_LIMITING", "FIXED_RULES_DATABASE", "FIXED_RULES_OBSERVABILITY", "FIXED_RULES_TRACING", "FIXED_RULES_CONFIG", "FIXED_RULES_ASYNC", "FIXED_RULES_MESSAGE_DELIVERY", "FIXED_RULES_GRACEFUL_SHUTDOWN", "FIXED_RULES_TEST", "FIXED_RULES_AI_BASE"],
+    "auto_generated": ["deny_list_summary", "recommended_libs"],
+    "metadata": ["project_name", "generated_at"]
+  }
+}

package/bundled/skills-windows/app-planner/references/rules/database/question-manifest.json

@@ -0,0 +1,39 @@
+{
+  "schema_version": "app-planner-question-manifest-v1",
+  "layer": "database",
+  "total_questions": 15,
+  "_doc": "Machine-readable structure for database question-bank.md. Question TEXT/options/Recommended/Notes are authoritative in question-bank.md; this file carries ONLY structure: group membership, quick-mode, question->placeholder mapping, and conditional logic. Keep Qids and group ids in sync with question-bank.md. The AI reads this as its asking checklist (Phase A) and self-check expected-set (Phase D).",
+  "_conditions": "required_if / auto_derived_when use simple expressions over recorded answers. options_vary_by names a prior answer that changes the OPTION LIST only (question is still asked; never affects required). A single answer may fill more than one placeholder (a TL;DR value + a rules-block), both listed in maps_to.",
+  "groups": [
+    { "id": "G1", "topic": "Database Selection", "quick_mode": true },
+    { "id": "G2", "topic": "Data Modeling", "quick_mode": true },
+    { "id": "G3", "topic": "Migration", "quick_mode": true },
+    { "id": "G4", "topic": "Index & Performance", "quick_mode": false },
+    { "id": "G5", "topic": "Security & Compliance", "quick_mode": false },
+    { "id": "G6", "topic": "High Availability & Ops", "quick_mode": false },
+    { "id": "G7", "topic": "AI Constraints", "quick_mode": true }
+  ],
+  "questions": [
+    { "id": "Q1", "group": "G1", "topic": "Primary Database", "maps_to": ["database", "tech_rules"], "required": true },
+    { "id": "Q2", "group": "G1", "topic": "Cache Layer", "maps_to": ["cache", "cache_rules"], "required": true },
+    { "id": "Q3", "group": "G2", "topic": "Primary Key Strategy", "maps_to": ["pk_strategy", "schema_rules"], "required": true },
+    { "id": "Q4", "group": "G2", "topic": "Soft Delete", "maps_to": ["soft_delete", "schema_rules"], "required": true },
+    { "id": "Q5", "group": "G2", "topic": "Normalization Level", "maps_to": ["normalization", "schema_rules"], "required": true },
+    { "id": "Q6", "group": "G3", "topic": "Migration Tool", "maps_to": ["migration_tool", "migration_rules"], "required": true },
+    { "id": "Q7", "group": "G4", "topic": "Query Complexity", "maps_to": ["workload_type", "performance_rules"], "required": true },
+    { "id": "Q8", "group": "G4", "topic": "Estimated Data Volume", "maps_to": ["data_scale", "performance_rules"], "required": true },
+    { "id": "Q9", "group": "G5", "topic": "Data Sensitivity Level", "maps_to": ["data_sensitivity", "security_rules"], "required": true },
+    { "id": "Q10", "group": "G5", "topic": "Audit Requirements", "maps_to": ["audit", "audit_rules"], "required": true, "multi_select": true },
+    { "id": "Q11", "group": "G6", "topic": "Deployment Method", "maps_to": ["deployment", "ops_rules"], "required": true },
+    { "id": "Q12", "group": "G6", "topic": "Backup Strategy", "maps_to": ["backup", "ops_rules"], "required": true },
+    { "id": "Q13", "group": "G6", "topic": "High Availability Requirements", "maps_to": ["ha", "ops_rules"], "required": true },
+    { "id": "Q14", "group": "G7", "topic": "AI Permission to Modify Database Structure", "maps_to": ["ai_ddl_rule", "ai_ddl_permission"], "required": true },
+    { "id": "Q15", "group": "G7", "topic": "AI Safety Constraints", "maps_to": ["ai_safety_rule", "ai_safety_constraint"], "required": true }
+  ],
+  "template_placeholders": {
+    "from_questions": ["database", "tech_rules", "cache", "cache_rules", "pk_strategy", "schema_rules", "soft_delete", "normalization", "migration_tool", "migration_rules", "workload_type", "performance_rules", "data_scale", "data_sensitivity", "security_rules", "audit", "audit_rules", "deployment", "ops_rules", "backup", "ha", "ai_ddl_rule", "ai_ddl_permission", "ai_safety_rule", "ai_safety_constraint"],
+    "from_fixed_rules": ["FIXED_RULES_AI_BASE", "FIXED_RULES_BACKUP", "FIXED_RULES_CONNECTION", "FIXED_RULES_INDEX", "FIXED_RULES_MIGRATION", "FIXED_RULES_PERFORMANCE", "FIXED_RULES_QUERY", "FIXED_RULES_SCHEMA", "FIXED_RULES_SECURITY", "FIXED_RULES_TRANSACTION", "FIXED_RULES_TYPES"],
+    "auto_generated": ["deny_list_summary", "recommended_libs"],
+    "metadata": ["project_name", "generated_at"]
+  }
+}

package/bundled/skills-windows/app-planner/references/rules/frontend/question-manifest.json

@@ -0,0 +1,51 @@
+{
+  "schema_version": "app-planner-question-manifest-v1",
+  "layer": "frontend",
+  "total_questions": 25,
+  "_doc": "Machine-readable structure for frontend question-bank.md. Question TEXT/options/Recommended/Notes are authoritative in question-bank.md; this file carries ONLY structure: group membership, quick-mode, question->placeholder mapping, and conditional logic. Keep Qids and group ids in sync with question-bank.md. The AI reads this as its asking checklist (Phase A) and self-check expected-set (Phase D).",
+  "_conditions": "required_if / auto_derived_when use simple expressions over recorded answers, e.g. 'Q15 in [A, B]'. options_vary_by names a prior answer that changes the OPTION LIST/recommendation only (question is still asked; never affects required).",
+  "groups": [
+    { "id": "G1", "topic": "Tech Stack", "quick_mode": true },
+    { "id": "G2", "topic": "Styling", "quick_mode": true },
+    { "id": "G3", "topic": "State & Data Fetching", "quick_mode": true },
+    { "id": "G4", "topic": "Design System", "quick_mode": false },
+    { "id": "G5", "topic": "Responsive & Adaptation", "quick_mode": false },
+    { "id": "G6", "topic": "i18n & Accessibility", "quick_mode": false },
+    { "id": "G7", "topic": "Testing & Quality", "quick_mode": true },
+    { "id": "G8", "topic": "AI Vibecoding Constraints", "quick_mode": false },
+    { "id": "G9", "topic": "Performance Baseline", "quick_mode": false }
+  ],
+  "questions": [
+    { "id": "Q1", "group": "G1", "topic": "Frontend Framework", "maps_to": ["framework", "tech_stack_rules"], "required": true },
+    { "id": "Q2", "group": "G1", "topic": "Meta-Framework", "maps_to": ["meta_framework", "tech_stack_rules"], "required": true, "options_vary_by": "Q1" },
+    { "id": "Q3", "group": "G1", "topic": "Package Manager", "maps_to": ["package_manager", "tech_stack_rules"], "required": true },
+    { "id": "Q4", "group": "G2", "topic": "Styling Solution", "maps_to": ["style_solution", "style_specific_rules"], "required": true },
+    { "id": "Q4b", "group": "G2", "topic": "Font Loading Strategy", "maps_to": ["font_strategy", "performance_rules"], "required": true },
+    { "id": "Q5", "group": "G3", "topic": "Global State Library", "maps_to": ["state_lib", "state_rules"], "required": true, "options_vary_by": "Q1" },
+    { "id": "Q6", "group": "G3", "topic": "Server State Library", "maps_to": ["server_state_lib", "server_state_rules"], "required": true },
+    { "id": "Q7", "group": "G3", "topic": "API Type Source", "maps_to": ["api_type_source", "server_state_rules"], "required": true },
+    { "id": "Q8", "group": "G4", "topic": "Primary Design/Mockup Source", "maps_to": ["design_source"], "required": true },
+    { "id": "Q9", "group": "G4", "topic": "Token Naming Layers", "maps_to": ["token_layering", "token_layering_rules"], "required": true },
+    { "id": "Q10", "group": "G4", "topic": "Dark Mode", "maps_to": ["dark_mode", "dark_mode_rules"], "required": true },
+    { "id": "Q11", "group": "G5", "topic": "Adaptation Strategy", "maps_to": ["responsive_strategy", "breakpoint_rules"], "required": true },
+    { "id": "Q12", "group": "G5", "topic": "Breakpoint Scheme", "maps_to": ["breakpoint_scheme", "breakpoint_rules"], "required": true },
+    { "id": "Q13", "group": "G6", "topic": "Internationalization", "maps_to": ["i18n", "i18n_rules"], "required": true },
+    { "id": "Q14", "group": "G6", "topic": "Accessibility Target", "maps_to": ["a11y_level", "a11y_extra_rules"], "required": true },
+    { "id": "Q15", "group": "G7", "topic": "Test Coverage Requirements", "maps_to": ["test_coverage", "test_rules"], "required": true },
+    { "id": "Q16", "group": "G7", "topic": "Unit Test Framework", "maps_to": ["unit_test_framework", "test_rules"], "required": true, "required_if": "Q15 in [A, B]" },
+    { "id": "Q17", "group": "G7", "topic": "E2E Framework", "maps_to": ["e2e_framework", "test_rules"], "required": true, "required_if": "Q15 in [A, C]" },
+    { "id": "Q18", "group": "G8", "topic": "AI Component Index Sync", "maps_to": ["ai_index_rule"], "required": true },
+    { "id": "Q19", "group": "G8", "topic": "AI Permission to Add Dependencies", "maps_to": ["ai_dependency_rule"], "required": true },
+    { "id": "Q20", "group": "G8", "topic": "AI Impact Analysis Before Modifying Shared Components", "maps_to": ["ai_breaking_change_rule"], "required": true },
+    { "id": "Q21", "group": "G8", "topic": "AI Permission to Modify Config Files", "maps_to": ["ai_config_rule"], "required": true },
+    { "id": "Q22", "group": "G8", "topic": "AI Single File Generation Limit", "maps_to": ["ai_max_lines"], "required": true },
+    { "id": "Q23", "group": "G9", "topic": "First Screen LCP Target", "maps_to": ["lcp_target", "performance_rules"], "required": true },
+    { "id": "Q24", "group": "G9", "topic": "Single Chunk Size Limit", "maps_to": ["bundle_size", "performance_rules"], "required": true }
+  ],
+  "template_placeholders": {
+    "from_questions": ["framework", "meta_framework", "package_manager", "style_solution", "style_specific_rules", "font_strategy", "performance_rules", "state_lib", "state_rules", "server_state_lib", "server_state_rules", "api_type_source", "design_source", "token_layering", "token_layering_rules", "dark_mode", "dark_mode_rules", "responsive_strategy", "breakpoint_rules", "breakpoint_scheme", "i18n", "i18n_rules", "a11y_level", "a11y_extra_rules", "test_coverage", "test_rules", "unit_test_framework", "e2e_framework", "ai_index_rule", "ai_dependency_rule", "ai_breaking_change_rule", "ai_config_rule", "ai_max_lines", "lcp_target", "bundle_size", "tech_stack_rules"],
+    "from_fixed_rules": ["FIXED_RULES_A11Y", "FIXED_RULES_AI_BASE", "FIXED_RULES_COMPONENT_CONTRACT", "FIXED_RULES_DENY_LIST", "FIXED_RULES_ERROR_HANDLING", "FIXED_RULES_GIT", "FIXED_RULES_I18N_BASELINE", "FIXED_RULES_NAMING", "FIXED_RULES_PERFORMANCE", "FIXED_RULES_SECURITY", "FIXED_RULES_TYPESCRIPT"],
+    "auto_generated": ["deny_list_summary", "recommended_libs"],
+    "metadata": ["project_name", "generated_at", "project_scope"]
+  }
+}

package/bundled/skills-windows/app-planner/references/rules/mobile/question-manifest.json

@@ -0,0 +1,47 @@
+{
+  "schema_version": "app-planner-question-manifest-v1",
+  "layer": "mobile",
+  "total_questions": 20,
+  "_doc": "Machine-readable structure for mobile question-bank.md. Question TEXT/options/Recommended/Notes are authoritative in question-bank.md; this file carries ONLY structure: group membership, quick-mode, question->placeholder mapping, and conditional logic. Keep Qids and group ids in sync with question-bank.md. The AI reads this as its asking checklist (Phase A) and self-check expected-set (Phase D).",
+  "_conditions": "required_if / auto_derived_when use simple expressions over recorded answers, e.g. 'Q12 in [A, B]'. options_vary_by names a prior answer that changes the OPTION LIST only (question is still asked; never affects required). dual_native_repeat_when notes Q1=E (both native) repeats the question per platform.",
+  "groups": [
+    { "id": "G1", "topic": "Platform & Language", "quick_mode": true },
+    { "id": "G2", "topic": "Architecture", "quick_mode": true },
+    { "id": "G3", "topic": "UI Framework", "quick_mode": true },
+    { "id": "G4", "topic": "Navigation & State", "quick_mode": true },
+    { "id": "G5", "topic": "Networking & Data", "quick_mode": false },
+    { "id": "G6", "topic": "Platform Features", "quick_mode": false },
+    { "id": "G7", "topic": "Testing", "quick_mode": true },
+    { "id": "G8", "topic": "App Distribution", "quick_mode": false },
+    { "id": "G9", "topic": "Performance & Accessibility", "quick_mode": false },
+    { "id": "G10", "topic": "AI Constraints", "quick_mode": false }
+  ],
+  "questions": [
+    { "id": "Q1", "group": "G1", "topic": "Target Platform", "maps_to": ["platform", "tech_stack_rules"], "required": true },
+    { "id": "Q2", "group": "G1", "topic": "Minimum OS Version", "maps_to": ["min_os_version", "tech_stack_rules"], "required": true },
+    { "id": "Q3", "group": "G2", "topic": "Architecture Pattern", "maps_to": ["architecture", "arch_rules"], "required": true },
+    { "id": "Q4", "group": "G3", "topic": "UI Framework", "maps_to": ["ui_framework", "ui_rules"], "required": true, "options_vary_by": "Q1", "dual_native_repeat_when": "Q1 == E" },
+    { "id": "Q5", "group": "G4", "topic": "Navigation Strategy", "maps_to": ["navigation", "navigation_rules"], "required": true },
+    { "id": "Q6", "group": "G4", "topic": "State Management", "maps_to": ["state_management", "state_rules"], "required": true, "options_vary_by": "Q1", "dual_native_repeat_when": "Q1 == E" },
+    { "id": "Q7", "group": "G5", "topic": "Networking Library", "maps_to": ["networking", "networking_rules"], "required": true, "options_vary_by": "Q1", "dual_native_repeat_when": "Q1 == E" },
+    { "id": "Q8", "group": "G5", "topic": "Local Persistence", "maps_to": ["persistence", "persistence_rules"], "required": true, "options_vary_by": "Q1", "dual_native_repeat_when": "Q1 == E" },
+    { "id": "Q9", "group": "G6", "topic": "Push Notifications", "maps_to": ["push_notifications", "platform_features_rules"], "required": true },
+    { "id": "Q10", "group": "G6", "topic": "Background Tasks", "maps_to": ["background_tasks", "platform_features_rules"], "required": true },
+    { "id": "Q11", "group": "G6", "topic": "Permissions Strategy", "maps_to": ["permissions_strategy"], "required": true },
+    { "id": "Q12", "group": "G7", "topic": "Test Coverage Requirements", "maps_to": ["test_coverage", "test_rules"], "required": true },
+    { "id": "Q13", "group": "G7", "topic": "Unit Test Framework", "maps_to": ["unit_test_framework"], "required": true, "required_if": "Q12 in [A, B]", "options_vary_by": "Q1", "dual_native_repeat_when": "Q1 == E" },
+    { "id": "Q14", "group": "G7", "topic": "UI/E2E Test Framework", "maps_to": ["e2e_framework"], "required": true, "required_if": "Q12 in [A, C]", "options_vary_by": "Q1", "dual_native_repeat_when": "Q1 == E" },
+    { "id": "Q15", "group": "G8", "topic": "Distribution Method", "maps_to": ["distribution", "distribution_rules"], "required": true },
+    { "id": "Q16", "group": "G9", "topic": "Performance Targets", "maps_to": ["performance_target", "performance_rules"], "required": true },
+    { "id": "Q17", "group": "G9", "topic": "Accessibility Targets", "maps_to": ["a11y_target", "a11y_rules"], "required": true },
+    { "id": "Q18", "group": "G10", "topic": "AI Permission to Add Dependencies", "maps_to": ["ai_dependency_rule"], "required": true },
+    { "id": "Q19", "group": "G10", "topic": "AI Impact Analysis Before Modifying Shared Code", "maps_to": ["ai_breaking_change_rule"], "required": true },
+    { "id": "Q20", "group": "G10", "topic": "AI Platform-Specific Code Generation", "maps_to": ["ai_platform_rule"], "required": true }
+  ],
+  "template_placeholders": {
+    "from_questions": ["platform", "tech_stack_rules", "min_os_version", "architecture", "arch_rules", "ui_framework", "ui_rules", "navigation", "navigation_rules", "state_management", "state_rules", "networking", "networking_rules", "persistence", "persistence_rules", "push_notifications", "platform_features_rules", "background_tasks", "permissions_strategy", "test_coverage", "test_rules", "unit_test_framework", "e2e_framework", "distribution", "distribution_rules", "performance_target", "performance_rules", "a11y_target", "a11y_rules", "ai_dependency_rule", "ai_breaking_change_rule", "ai_platform_rule"],
+    "from_fixed_rules": ["FIXED_RULES_A11Y", "FIXED_RULES_AI_BASE", "FIXED_RULES_DISTRIBUTION", "FIXED_RULES_NAVIGATION", "FIXED_RULES_NETWORKING", "FIXED_RULES_PERFORMANCE", "FIXED_RULES_PERSISTENCE", "FIXED_RULES_PLATFORM_FEATURES", "FIXED_RULES_SECURITY", "FIXED_RULES_STATE", "FIXED_RULES_STRUCTURE", "FIXED_RULES_TEST", "FIXED_RULES_UI"],
+    "auto_generated": ["deny_list_summary", "recommended_libs"],
+    "metadata": ["project_name", "generated_at"]
+  }
+}

package/bundled/skills-windows/bugfix-pipeline-launcher/SKILL.md

@@ -177,7 +177,7 @@ Detect user intent from their message, then follow the corresponding workflow:
 
    **Question 4 — Advanced config?** (multiSelect: false):
    - No (default) — Use defaults for session timeout and failure behavior
-   - Yes — Configure session timeout and stop-on-failure options
+   - Yes — Configure session timeout, stop-on-failure, and reasoning effort options
 
    Note: Bug filter defaults to all bugs (by severity order). Default Critic to Off unless bugs have `severity: "critical"` or `severity: "high"` (in which case default to On). If the user selects "Other" on any option, handle their custom input.
 
@@ -193,6 +193,14 @@ Detect user intent from their message, then follow the corresponding workflow:
    - Off (default) — Pipeline continues to next task after failure
    - On — Pipeline halts immediately when a task exhausts all retries (`STOP_ON_FAILURE=1`)
 
+   **Question 3 — Reasoning effort** (multiSelect: false):
+   - Default (none) — Use CLI default
+   - low — Minimize reasoning, fastest output (`PRIZMKIT_EFFORT=low`)
+   - medium — Moderate reasoning (`PRIZMKIT_EFFORT=medium`)
+   - high — Thorough reasoning for complex tasks (`PRIZMKIT_EFFORT=high`)
+   - xhigh — Extensive reasoning (`PRIZMKIT_EFFORT=xhigh`)
+   - max — Maximum reasoning, Claude Code only (`PRIZMKIT_EFFORT=max`)
+
    **Environment variable mapping** (for translating user responses → env vars):
 
    | Config choice | Environment variable |
@@ -203,6 +211,7 @@ Detect user intent from their message, then follow the corresponding workflow:
    | Critic: On | `ENABLE_CRITIC=true` |
    | Timeout: value | `SESSION_TIMEOUT=<seconds>` |
    | Stop on failure: On | `STOP_ON_FAILURE=1` |
+   | Effort: value | `PRIZMKIT_EFFORT=<value>` |
 
    **Advanced environment variables** (not exposed in interactive menu, pass via `--env`):
 
@@ -220,7 +229,7 @@ Detect user intent from their message, then follow the corresponding workflow:
    ```
    With all options:
    ```powershell
-   $env:VERBOSE = "1"; $env:MAX_RETRIES = "5"; $env:SESSION_TIMEOUT = "3600"
+   $env:VERBOSE = "1"; $env:MAX_RETRIES = "5"; $env:SESSION_TIMEOUT = "3600"; $env:PRIZMKIT_EFFORT = "high"
    .\.prizmkit\dev-pipeline\run-bugfix.ps1 run .prizmkit/plans/bug-fix-list.json
    ```
 
@@ -231,7 +240,7 @@ Detect user intent from their message, then follow the corresponding workflow:
    With all options:
    ```powershell
    .\.prizmkit\dev-pipeline\launch-bugfix-daemon.ps1 start .prizmkit/plans/bug-fix-list.json `
-     --env "VERBOSE=1 MAX_RETRIES=5"
+     --env "VERBOSE=1 MAX_RETRIES=5 PRIZMKIT_EFFORT=high"
    ```
 
    **Manual mode**: Print the assembled command(s) and **stop here**. Do not execute anything. Do not proceed to step 7.

package/bundled/skills-windows/feature-pipeline-launcher/SKILL.md

@@ -195,7 +195,7 @@ Detect user intent from their message, then follow the corresponding workflow:
 
    **Question 4 — Advanced config?** (multiSelect: false):
    - No (default) — Use defaults for session timeout and failure behavior
-   - Yes — Configure session timeout and stop-on-failure options
+   - Yes — Configure session timeout, stop-on-failure, and reasoning effort options
 
    Default Critic to Off unless features have `estimated_complexity: "high"` or above (in which case default to On).
 
@@ -211,6 +211,14 @@ Detect user intent from their message, then follow the corresponding workflow:
    - Off (default) — Pipeline continues to next task after failure
    - On — Pipeline halts immediately when a task exhausts all retries (`STOP_ON_FAILURE=1`)
 
+   **Question 3 — Reasoning effort** (multiSelect: false):
+   - Default (none) — Use CLI default
+   - low — Minimize reasoning, fastest output (`PRIZMKIT_EFFORT=low`)
+   - medium — Moderate reasoning (`PRIZMKIT_EFFORT=medium`)
+   - high — Thorough reasoning for complex tasks (`PRIZMKIT_EFFORT=high`)
+   - xhigh — Extensive reasoning (`PRIZMKIT_EFFORT=xhigh`)
+   - max — Maximum reasoning, Claude Code only (`PRIZMKIT_EFFORT=max`)
+
    **Environment variable mapping** (for translating user responses → env vars):
 
    | Config choice | Environment variable |
@@ -221,6 +229,7 @@ Detect user intent from their message, then follow the corresponding workflow:
    | Max retries: N | `MAX_RETRIES=N` |
    | Timeout: value | `SESSION_TIMEOUT=<seconds>` |
    | Stop on failure: On | `STOP_ON_FAILURE=1` |
+   | Effort: value | `PRIZMKIT_EFFORT=<value>` |
 
    **Advanced environment variables** (not exposed in interactive menu, pass via `--env`):
 
@@ -239,7 +248,7 @@ Detect user intent from their message, then follow the corresponding workflow:
    ```
    With all options:
    ```powershell
-   $env:VERBOSE = "1"; $env:ENABLE_CRITIC = "true"; $env:MAX_RETRIES = "5"; $env:SESSION_TIMEOUT = "3600"
+   $env:VERBOSE = "1"; $env:ENABLE_CRITIC = "true"; $env:MAX_RETRIES = "5"; $env:SESSION_TIMEOUT = "3600"; $env:PRIZMKIT_EFFORT = "high"
    .\.prizmkit\dev-pipeline\run-feature.ps1 run .prizmkit/plans/feature-list.json --features F-001:F-005
    ```
 
@@ -250,7 +259,7 @@ Detect user intent from their message, then follow the corresponding workflow:
    With all options:
    ```powershell
    .\.prizmkit\dev-pipeline\launch-feature-daemon.ps1 start .prizmkit/plans/feature-list.json --features F-001:F-005 `
-     --env "VERBOSE=1 ENABLE_CRITIC=true MAX_RETRIES=5"
+     --env "VERBOSE=1 ENABLE_CRITIC=true MAX_RETRIES=5 PRIZMKIT_EFFORT=high"
    ```
 
    **Manual mode**: Print the assembled command(s) and **stop here**. Do not execute anything. Do not proceed to step 8.

package/bundled/skills-windows/refactor-pipeline-launcher/SKILL.md

@@ -192,7 +192,7 @@ Detect user intent from their message, then follow the corresponding workflow:
 
    **Question 3 — Advanced config?** (multiSelect: false):
    - No (default) — Use defaults for critic review, session timeout, and failure behavior
-   - Yes — Configure critic review, session timeout, and stop-on-failure options
+   - Yes — Configure critic review, session timeout, stop-on-failure, and reasoning effort options
 
    Note: Refactor filter defaults to all refactor items (by priority order). If the user selects "Other" on any option, handle their custom input.
 
@@ -212,6 +212,14 @@ Detect user intent from their message, then follow the corresponding workflow:
    - Off (default) — Skip adversarial review
    - On — Enable adversarial critic review: an independent AI agent reviews the refactor plan for completeness and the implementation for regressions, missing edge cases, and behavior violations. Adds ~5-10 min per refactor task.
 
+   **Question 4 — Reasoning effort** (multiSelect: false):
+   - Default (none) — Use CLI default
+   - low — Minimize reasoning, fastest output (`PRIZMKIT_EFFORT=low`)
+   - medium — Moderate reasoning (`PRIZMKIT_EFFORT=medium`)
+   - high — Thorough reasoning for complex tasks (`PRIZMKIT_EFFORT=high`)
+   - xhigh — Extensive reasoning (`PRIZMKIT_EFFORT=xhigh`)
+   - max — Maximum reasoning, Claude Code only (`PRIZMKIT_EFFORT=max`)
+
    Default Critic to Off unless refactor items have `priority: "critical"` (in which case default to On).
 
    **Environment variable mapping** (for translating user responses → env vars):
@@ -224,6 +232,7 @@ Detect user intent from their message, then follow the corresponding workflow:
    | Critic: On | `ENABLE_CRITIC=true` |
    | Timeout: value | `SESSION_TIMEOUT=<seconds>` |
    | Stop on failure: On | `STOP_ON_FAILURE=1` |
+   | Effort: value | `PRIZMKIT_EFFORT=<value>` |
 
    **Advanced environment variables** (not exposed in interactive menu, pass via `--env`):
 
@@ -241,7 +250,7 @@ Detect user intent from their message, then follow the corresponding workflow:
    ```
    With all options:
    ```powershell
-   $env:VERBOSE = "1"; $env:MAX_RETRIES = "5"; $env:SESSION_TIMEOUT = "3600"
+   $env:VERBOSE = "1"; $env:MAX_RETRIES = "5"; $env:SESSION_TIMEOUT = "3600"; $env:PRIZMKIT_EFFORT = "high"
    .\.prizmkit\dev-pipeline\run-refactor.ps1 run .prizmkit/plans/refactor-list.json
    ```
 

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "prizmkit",
-  "version": "1.1.76",
+  "version": "1.1.78",
   "description": "Create a new PrizmKit-powered project with clean initialization — no framework dev files, just what you need.",
   "type": "module",
   "bin": {