clavix 4.10.0 → 4.11.2

package/dist/templates/slash-commands/_components/agent-protocols/decision-rules.md

@@ -7,11 +7,11 @@ These rules define deterministic agent behavior. Follow exactly - no interpretat
 ```
 IF quality < 60%:
   IF (completeness < 50%) OR (clarity < 50%) OR (actionability < 50%):
-    → ACTION: Strongly recommend /clavix:deep
-    → SAY: "Quality is [X]%. Deep mode strongly recommended for: [low dimensions]"
+    → ACTION: Strongly recommend comprehensive depth
+    → SAY: "Quality is [X]%. Comprehensive depth strongly recommended for: [low dimensions]"
   ELSE:
-    → ACTION: Suggest /clavix:deep
-    → SAY: "Quality is [X]%. Consider deep mode for better results."
+    → ACTION: Suggest comprehensive depth
+    → SAY: "Quality is [X]%. Consider comprehensive depth for better results."
 
 IF quality >= 60% AND quality < 80%:
   → ACTION: Proceed with optimization
@@ -46,19 +46,19 @@ IF confidence < 50%:
 
 ```
 IF escalation_score >= 75:
-  → ACTION: Strongly recommend deep mode
+  → ACTION: Strongly recommend comprehensive depth
   → SHOW: Top 3 contributing factors
 
 IF escalation_score 60-74:
-  → ACTION: Recommend deep mode
+  → ACTION: Recommend comprehensive depth
   → SHOW: Primary contributing factor
 
 IF escalation_score 45-59:
-  → ACTION: Suggest deep mode as option
-  → SAY: "Deep mode available for more thorough analysis"
+  → ACTION: Suggest comprehensive depth as option
+  → SAY: "Comprehensive depth available for more thorough analysis"
 
 IF escalation_score < 45:
-  → ACTION: Fast mode sufficient
+  → ACTION: Standard depth sufficient
   → NO escalation mention
 ```
 
@@ -120,7 +120,7 @@ IF pattern not applicable to intent:
 IF pattern applicable but skipped:
   → EXPLAIN: "Skipped [pattern] because [reason]"
 
-DEEP MODE ONLY:
+COMPREHENSIVE DEPTH ONLY:
   → MUST include alternatives (2-3)
   → MUST include validation checklist
   → MUST include edge cases
@@ -129,15 +129,15 @@ DEEP MODE ONLY:
 ### Rule 8: Mode Transition Decision
 
 ```
-IF user requests /clavix:fast but quality < 50%:
-  → ACTION: Warn and suggest deep
-  → SAY: "Quality is [X]%. Fast mode may be insufficient."
+IF user requests standard depth but quality < 50%:
+  → ACTION: Warn and suggest comprehensive
+  → SAY: "Quality is [X]%. Standard depth may be insufficient."
   → ALLOW: User can override and proceed
 
-IF user in /clavix:deep but prompt is simple (quality > 85%):
+IF user requests comprehensive depth but prompt is simple (quality > 85%):
   → ACTION: Note efficiency
-  → SAY: "Prompt is already high quality. Fast mode would suffice."
-  → CONTINUE: With deep analysis anyway
+  → SAY: "Prompt is already high quality. Standard depth would suffice."
+  → CONTINUE: With comprehensive analysis anyway
 
 IF strategic keywords detected (3+ architecture/security/scalability):
   → ACTION: Suggest PRD mode

package/dist/templates/slash-commands/_components/agent-protocols/self-correction.md

@@ -17,8 +17,8 @@
 - Providing optimization without quality analysis
 - Jumping directly to improved prompt without showing scores
 
-### Mistake Type 3: Wrong Mode Selection
-- Not suggesting `/clavix:deep` when quality scores are low
+### Mistake Type 3: Wrong Depth Selection
+- Not suggesting comprehensive depth when quality scores are low
 - Not recommending `/clavix:prd` for strategic decisions
 - Ignoring triage indicators and escalation factors
 
@@ -27,8 +27,8 @@
 - Skipping patterns without explanation
 - Not showing which patterns were applied
 
-### Mistake Type 5: Missing Validation (Deep Mode)
-- Not generating validation checklist in deep mode
+### Mistake Type 5: Missing Validation (Comprehensive Depth)
+- Not generating validation checklist in comprehensive depth
 - Not identifying edge cases
 - Not providing alternative approaches
 

package/dist/templates/slash-commands/_components/agent-protocols/state-assertion.md

@@ -17,8 +17,7 @@ Implementation: [BLOCKED|ALLOWED]
 
 | Mode | Type | Implementation | Purpose |
 |------|------|----------------|---------|
-| /clavix:fast | planning | BLOCKED | Prompt optimization |
-| /clavix:deep | planning | BLOCKED | Comprehensive prompt analysis |
+| /clavix:improve | planning | BLOCKED | Prompt optimization (smart depth selection) |
 | /clavix:prd | planning | BLOCKED | PRD development |
 | /clavix:plan | planning | BLOCKED | Task breakdown generation |
 | /clavix:start | planning | BLOCKED | Requirements gathering |
@@ -37,9 +36,9 @@ Implementation: [BLOCKED|ALLOWED]
 
 **Planning Mode (Implementation BLOCKED):**
 ```
-**CLAVIX MODE: Fast Optimization**
+**CLAVIX MODE: Improve**
 Mode: planning
-Purpose: Optimizing user prompt with Clavix Intelligence™
+Purpose: Optimizing user prompt with Clavix Intelligence
 Implementation: BLOCKED - I will analyze and improve the prompt, not implement it
 ```
 

package/dist/templates/slash-commands/_components/agent-protocols/state-awareness.md

@@ -50,7 +50,7 @@ Always output current state when starting a workflow:
 NO_PROJECT:
   → /clavix:prd creates PRD_EXISTS
   → /clavix:start + /clavix:summarize creates PRD_EXISTS
-  → /clavix:fast or /clavix:deep creates prompt (not PRD_EXISTS)
+  → /clavix:improve creates prompt (not PRD_EXISTS)
 
 PRD_EXISTS:
   → /clavix:plan creates TASKS_EXIST

package/dist/templates/slash-commands/_components/sections/escalation-factors.md

@@ -1,17 +1,17 @@
 ## When Your Prompt Needs More Attention
 
-Sometimes a quick cleanup isn't enough. Here's how to know when to recommend deep analysis, and how to explain it to users.
+Sometimes a quick cleanup isn't enough. Here's how to know when to recommend comprehensive analysis, and how to explain it to users.
 
 ---
 
-### Quick Check: Is Fast Mode Enough?
+### Quick Check: Is Standard Depth Enough?
 
-**Fast mode works great when:**
+**Standard depth works great when:**
 - User knows what they want
 - Request is straightforward
 - Prompt just needs cleanup/polish
 
-**Suggest deep mode when:**
+**Suggest comprehensive depth when:**
 - Prompt is vague or confusing
 - Missing lots of important details
 - Complex request (architecture, migration, security)
@@ -22,7 +22,7 @@ Sometimes a quick cleanup isn't enough. Here's how to know when to recommend dee
 ### How to Decide (No Numbers to Users)
 
 **Instead of showing:**
-> "Escalation: 78/100 [STRONGLY RECOMMEND DEEP]"
+> "Escalation: 78/100 [STRONGLY RECOMMEND COMPREHENSIVE]"
 
 **Say this:**
 > "This prompt needs more work than a quick cleanup. I'd recommend
@@ -31,7 +31,7 @@ Sometimes a quick cleanup isn't enough. Here's how to know when to recommend dee
 
 ---
 
-### What Triggers Deep Mode Recommendation
+### What Triggers Comprehensive Depth Recommendation
 
 | What You Notice | What to Say |
 |-----------------|-------------|
@@ -44,12 +44,12 @@ Sometimes a quick cleanup isn't enough. Here's how to know when to recommend dee
 
 ---
 
-### Deep Mode Value (What to Tell Users)
+### Comprehensive Depth Value (What to Tell Users)
 
-When recommending deep mode, explain what they'll get:
+When recommending comprehensive depth, explain what they'll get:
 
 **For vague prompts:**
-> "With deep analysis, I'll explore different ways to interpret this and
+> "With comprehensive analysis, I'll explore different ways to interpret this and
 > give you options to choose from."
 
 **For incomplete prompts:**
@@ -66,21 +66,21 @@ When recommending deep mode, explain what they'll get:
 
 ---
 
-### How to Transition to Deep Mode
+### How to Transition Depth Levels
 
-**If user accepts:**
+**If user accepts comprehensive:**
 > "Great, let me take a closer look at this..."
-> [Switch to deep mode analysis]
+> [Switch to comprehensive depth analysis]
 
 **If user declines:**
 > "No problem! I'll do what I can with a quick cleanup. You can always
-> run deep mode later if you want more detail."
-> [Continue with fast mode]
+> run with --comprehensive later if you want more detail."
+> [Continue with standard depth]
 
 **If user is unsure:**
 > "Here's the difference:
-> - **Quick mode:** Clean up and improve what's there (2 minutes)
-> - **Deep mode:** Full analysis with alternatives and checklist (5 minutes)
+> - **Standard:** Clean up and improve what's there (2 minutes)
+> - **Comprehensive:** Full analysis with alternatives and checklist (5 minutes)
 >
 > Which sounds better for this?"
 
@@ -88,7 +88,7 @@ When recommending deep mode, explain what they'll get:
 
 ### Internal Reference: Escalation Factors
 
-The 8 escalation factors for calculating when to recommend deep mode:
+The 8 escalation factors for calculating when to recommend comprehensive depth:
 
 | Factor | Trigger Condition | Points |
 |--------|-------------------|--------|
@@ -104,16 +104,16 @@ The 8 escalation factors for calculating when to recommend deep mode:
 **Recommendation thresholds:**
 | Score | Recommendation |
 |-------|----------------|
-| 75+ | `[STRONGLY RECOMMEND DEEP]` |
-| 60-74 | `[RECOMMEND DEEP]` |
-| 45-59 | `[DEEP MODE AVAILABLE]` |
-| <45 | No escalation - Fast mode sufficient |
+| 75+ | `[STRONGLY RECOMMEND COMPREHENSIVE]` (high confidence) |
+| 60-74 | `[RECOMMEND COMPREHENSIVE]` (medium confidence) |
+| 45-59 | `[COMPREHENSIVE AVAILABLE]` (low confidence) |
+| <45 | No escalation - Standard depth sufficient |
 
 ---
 
 ### Example Conversations
 
-**Prompt clearly needs deep mode:**
+**Prompt clearly needs comprehensive depth:**
 ```
 User: "help with auth"
 
@@ -133,17 +133,17 @@ User: "build a REST API for user management"
 Agent: "I can definitely improve this! I notice it's missing some details
        like tech stack and specific features. I could either:
        - Quick cleanup: Add the obvious improvements
-       - Deep analysis: Fill in all the gaps and give you a complete spec
+       - Comprehensive analysis: Fill in all the gaps and give you a complete spec
 
        Which works better for you?"
 ```
 
-**Prompt is good enough for fast:**
+**Prompt is good enough for standard:**
 ```
 User: "Create a React component that shows a list of products
        with name, price, and add-to-cart button. Use TypeScript
        and styled-components."
 
-Agent: [No escalation needed - proceed with fast mode]
+Agent: [No escalation needed - proceed with standard depth]
        "Nice clear prompt! Let me just polish it up a bit..."
 ```

package/dist/templates/slash-commands/_components/sections/pattern-visibility.md

@@ -5,25 +5,25 @@ Show which optimization patterns were applied and their effects.
 ### Compact Output Format
 
 ```
-Patterns: [N] applied ([MODE] mode)
+Patterns: [N] applied ([DEPTH] depth)
   [PATTERN1] → [ONE-LINE EFFECT]
   [PATTERN2] → [ONE-LINE EFFECT]
 ```
 
 ### Example Outputs
 
-**Fast mode optimization:**
+**Standard depth optimization:**
 ```
-Patterns: 4 applied (fast mode)
+Patterns: 4 applied (standard depth)
   ConcisenessFilter → Removed 3 pleasantries, 2 filler phrases
   ObjectiveClarifier → Added clear objective statement
   StructureOrganizer → Reordered to context→requirements→output
   ActionabilityEnhancer → Replaced 2 vague terms with specifics
 ```
 
-**Deep mode optimization:**
+**Comprehensive depth optimization:**
 ```
-Patterns: 7 applied (deep mode)
+Patterns: 7 applied (comprehensive depth)
   ConcisenessFilter → Removed 5 pleasantries
   ObjectiveClarifier → Added objective section
   StructureOrganizer → Reorganized into 4 sections
@@ -43,7 +43,7 @@ Patterns: 7 applied (deep mode)
 
 ### Available Patterns Reference
 
-**Core Patterns (fast + deep):**
+**Standard Patterns (both scopes):**
 | Pattern | Priority | What It Does |
 |---------|----------|--------------|
 | ConcisenessFilter | 4 | Removes pleasantries, filler words, redundant phrases |
@@ -54,8 +54,12 @@ Patterns: 7 applied (deep mode)
 | CompletenessValidator | 6 | Identifies and flags missing required elements |
 | StepDecomposer | 5 | Breaks complex prompts into sequential steps |
 | ContextPrecisionBooster | 6 | Adds precise context when missing |
+| AmbiguityDetector | 9 | Identifies and flags ambiguous terms |
+| OutputFormatEnforcer | 7 | Adds explicit output format specifications |
+| SuccessCriteriaEnforcer | 7 | Adds measurable success criteria |
+| DomainContextEnricher | 5 | Adds domain-specific best practices |
 
-**Deep Mode Exclusive Patterns:**
+**Comprehensive Depth Exclusive Patterns:**
 | Pattern | Priority | What It Does |
 |---------|----------|--------------|
 | AlternativePhrasingGenerator | 3 | Generates 2-3 alternative prompt structures |
@@ -67,15 +71,7 @@ Patterns: 7 applied (deep mode)
 | ErrorToleranceEnhancer | 5 | Adds error handling requirements |
 | PrerequisiteIdentifier | 6 | Identifies prerequisites and dependencies |
 
-**v4.1 Agent Transparency Patterns (both modes):**
-| Pattern | Priority | What It Does |
-|---------|----------|--------------|
-| AmbiguityDetector | 9 | Identifies and flags ambiguous terms |
-| OutputFormatEnforcer | 7 | Adds explicit output format specifications |
-| SuccessCriteriaEnforcer | 7 | Adds measurable success criteria |
-| DomainContextEnricher | 5 | Adds domain-specific best practices |
-
-**v4.3.2 PRD Mode Patterns (deep mode):**
+**v4.3.2 PRD Mode Patterns (comprehensive):**
 | Pattern | Priority | What It Does |
 |---------|----------|--------------|
 | RequirementPrioritizer | 7 | Separates must-have from nice-to-have requirements |
@@ -83,7 +79,7 @@ Patterns: 7 applied (deep mode)
 | SuccessMetricsEnforcer | 7 | Ensures measurable success criteria exist |
 | DependencyIdentifier | 5 | Identifies technical and external dependencies |
 
-**v4.3.2 Conversational Mode Patterns (deep mode):**
+**v4.3.2 Conversational Mode Patterns (comprehensive):**
 | Pattern | Priority | What It Does |
 |---------|----------|--------------|
 | ConversationSummarizer | 8 | Extracts structured requirements from messages |
@@ -93,14 +89,14 @@ Patterns: 7 applied (deep mode)
 ### Pattern Selection Logic
 
 Patterns are selected based on:
-1. **Mode**: Fast mode gets core patterns only; deep mode gets all
+1. **Depth**: Standard gets core patterns; comprehensive gets all
 2. **Intent**: Some patterns are intent-specific (e.g., PRDStructureEnforcer for prd-generation)
 3. **Priority**: Higher priority patterns run first (10→1)
 4. **Applicability**: Pattern checks if it can improve the prompt
 
 ### Why Patterns Were Skipped
 
-In deep mode, show skipped patterns with reasons:
+In comprehensive depth, show skipped patterns with reasons:
 
 ```
 Skipped patterns:
@@ -111,35 +107,33 @@ Skipped patterns:
 ### Pattern Categories Summary
 
 ```
-Core (always available):
+Standard (both scopes):
   ConcisenessFilter, ObjectiveClarifier, StructureOrganizer,
-  ActionabilityEnhancer, TechnicalContextEnricher, CompletenessValidator
-
-Both modes (fast & deep):
+  ActionabilityEnhancer, TechnicalContextEnricher, CompletenessValidator,
   StepDecomposer, ContextPrecisionBooster,
   AmbiguityDetector, OutputFormatEnforcer, SuccessCriteriaEnforcer,
   DomainContextEnricher
 
-Deep mode only:
+Comprehensive only:
   AlternativePhrasingGenerator, EdgeCaseIdentifier, ValidationChecklistCreator,
   AssumptionExplicitizer, ScopeDefiner, PRDStructureEnforcer,
   ErrorToleranceEnhancer, PrerequisiteIdentifier
 
-v4.3.2 PRD mode (deep):
+v4.3.2 PRD mode (comprehensive):
   RequirementPrioritizer, UserPersonaEnricher, SuccessMetricsEnforcer,
   DependencyIdentifier
 
-v4.3.2 Conversational mode (deep):
+v4.3.2 Conversational mode (comprehensive):
   ConversationSummarizer, TopicCoherenceAnalyzer, ImplicitRequirementExtractor
 ```
 
-### Pattern Count by Mode
+### Pattern Count by Depth
 
-| Mode | Patterns Available | Typical Applied |
+| Depth | Patterns Available | Typical Applied |
 |------|-------------------|-----------------|
-| Fast | 12 patterns | 4-7 patterns |
-| Deep | 27 patterns | 8-14 patterns |
-| PRD | 12 patterns | 8-12 patterns |
-| Conversational | 3 patterns | 1-3 patterns |
+| Standard | 12 patterns | 4-7 patterns |
+| Comprehensive | 27 patterns | 8-14 patterns |
+| PRD mode | 12+ patterns | 8-12 patterns |
+| Conversational | 3+ patterns | 1-3 patterns |
 
-**Note:** Deep mode has access to all 27 patterns. Pattern selection varies by intent - some patterns only apply to specific intents (e.g., PRDStructureEnforcer only for prd-generation), so typical applied count is 8-14.
+**Note:** Comprehensive depth has access to all 27 patterns. Pattern selection varies by intent - some patterns only apply to specific intents (e.g., PRDStructureEnforcer only for prd-generation), so typical applied count is 8-14.

package/dist/templates/slash-commands/_components/troubleshooting/mode-confusion.md

@@ -41,6 +41,6 @@
 1. Ask user to clarify current intent
 2. Check last Clavix command run
 3. Mode determination:
-   - `/clavix:fast`, `/clavix:deep`, `/clavix:prd`, `/clavix:start`, `/clavix:summarize`, `/clavix:plan` → PLANNING
+   - `/clavix:improve`, `/clavix:prd`, `/clavix:start`, `/clavix:summarize`, `/clavix:plan` → PLANNING
    - `/clavix:implement`, `/clavix:execute` → IMPLEMENTATION
 4. If still unclear, default to PLANNING and ask for clarification

package/dist/templates/slash-commands/_components/troubleshooting/triage-escalation.md

@@ -1,26 +1,26 @@
-### Issue: Triage keeps recommending deep mode
+### Issue: Triage keeps recommending comprehensive depth
 
 **Cause**: Prompt has low quality scores + multiple secondary indicators
 
 **Solution**:
-- Accept the recommendation - deep mode will provide better analysis
-- OR improve prompt manually before running fast mode again
+- Accept the recommendation - comprehensive depth will provide better analysis
+- OR improve prompt manually before running with standard depth again
 - Check which quality dimension is scoring low and address it
 
-### Issue: Can't determine if prompt is complex enough for deep mode
+### Issue: Can't determine if prompt is complex enough for comprehensive depth
 
 **Cause**: Borderline quality scores or unclear content quality
 
 **Solution**:
-- Err on side of fast mode first
-- If output feels insufficient, escalate to `/clavix:deep`
+- Err on side of standard depth first
+- If output feels insufficient, escalate to `/clavix:improve --comprehensive`
 - Use triage as guidance, not absolute rule
 
 ### Issue: Improved prompt still feels incomplete
 
-**Cause**: Fast mode only applies basic optimizations
+**Cause**: Standard depth only applies basic optimizations
 
 **Solution**:
-- Use `/clavix:deep` for alternative approaches, edge cases, and validation checklists
+- Use `/clavix:improve --comprehensive` for alternative approaches, edge cases, and validation checklists
 - OR use `/clavix:prd` if strategic planning is needed
-- Fast mode is for quick cleanup, not comprehensive analysis
+- Standard depth is for quick cleanup, not comprehensive analysis

package/dist/types/config.d.ts

@@ -13,12 +13,11 @@ export interface ClavixConfig {
 /**
  * v4.4 Intelligence Configuration
  * Configure pattern behavior, enable/disable patterns, adjust priorities
+ * v4.11: Removed defaultMode (fast/deep replaced by improve with auto-detection)
  */
 export interface IntelligenceConfig {
     /** Pattern-specific settings */
     patterns?: PatternSettingsConfig;
-    /** Default mode for optimization */
-    defaultMode?: 'fast' | 'deep';
     /** Enable verbose pattern logging */
     verbosePatternLogs?: boolean;
 }

package/dist/types/verification.d.ts

@@ -2,9 +2,10 @@
  * Clavix v4.8: Verification System Types
  *
  * Type definitions for the checklist verification system that ensures
- * checklists generated by deep/fast modes are verified after implementation.
+ * checklists generated by improve mode are verified after implementation.
+ * v4.11: Updated to use DepthLevel instead of fast/deep source distinction.
  */
-import { PromptIntent } from '../core/intelligence/types.js';
+import { PromptIntent, DepthLevel } from '../core/intelligence/types.js';
 /**
  * Category of checklist item
  */
@@ -154,12 +155,12 @@ export interface VerificationSummary {
  * Full verification report
  */
 export interface VerificationReport {
-    /** Report version */
-    version: '1.0';
+    /** Report version (v4.11: Allow 2.0 for unified storage format) */
+    version: '1.0' | '2.0';
     /** ID of the prompt being verified */
     promptId: string;
-    /** Source of the prompt (fast or deep) */
-    source: 'fast' | 'deep';
+    /** v4.11: Depth level used for this prompt (replaces source: 'fast' | 'deep') */
+    depthUsed: DepthLevel;
     /** When verification started */
     startedAt: string;
     /** When verification completed (all items done) */

package/dist/types/verification.js

@@ -2,7 +2,8 @@
  * Clavix v4.8: Verification System Types
  *
  * Type definitions for the checklist verification system that ensures
- * checklists generated by deep/fast modes are verified after implementation.
+ * checklists generated by improve mode are verified after implementation.
+ * v4.11: Updated to use DepthLevel instead of fast/deep source distinction.
  */
 export {};
 //# sourceMappingURL=verification.js.map

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "clavix",
-  "version": "4.10.0",
+  "version": "4.11.2",
   "description": "Clavix Intelligence™ for AI coding. Automatically optimizes prompts with intent detection, quality assessment, and adaptive patterns—no framework to learn. Works with Claude Code, Cursor, Windsurf, and 19+ other AI coding tools.",
   "type": "module",
   "main": "dist/index.js",
@@ -24,6 +24,8 @@
     "test:watch": "NODE_OPTIONS=\"--experimental-vm-modules --no-warnings\" jest --watch",
     "test:coverage": "NODE_OPTIONS=\"--experimental-vm-modules --no-warnings\" jest --coverage",
     "test:changed": "NODE_OPTIONS=\"--experimental-vm-modules --no-warnings\" jest --changedSince=HEAD~1 --passWithNoTests",
+    "test:parity": "NODE_OPTIONS=\"--experimental-vm-modules --no-warnings\" jest tests/consistency/cli-template-parity.test.ts",
+    "test:consistency": "NODE_OPTIONS=\"--experimental-vm-modules --no-warnings\" jest tests/consistency/",
     "lint": "eslint",
     "lint:fix": "eslint --fix",
     "format": "prettier --write \"src/**/*.ts\"",