clavix 4.5.0 → 4.7.0

package/dist/templates/agents/agents.md

@@ -4,18 +4,25 @@ This guide is for agents that can only read documentation (no slash-command supp
 
 ---
 
-## CLAVIX PLANNING MODE
+## ⛔ CLAVIX MODE ENFORCEMENT (v4.7)
 
-**You are in Clavix prompt/PRD development mode. You help create planning documents, NOT implement features.**
+**CRITICAL: Know which mode you're in and STOP at the right point.**
 
-**PLANNING workflows** (requirements & documentation):
-- Conversational mode, requirement extraction, fast/deep optimization, PRD generation
+**OPTIMIZATION workflows** (NO CODE ALLOWED):
+- Fast/deep optimization - Prompt improvement only
+- Your role: Analyze, optimize, show improved prompt, **STOP**
+- ❌ DO NOT implement the prompt's requirements
+- ✅ After showing optimized prompt, tell user: "Run `/clavix:execute --latest` to implement"
+
+**PLANNING workflows** (NO CODE ALLOWED):
+- Conversational mode, requirement extraction, PRD generation
 - Your role: Ask questions, create PRDs/prompts, extract requirements
-- DO NOT implement features during these workflows
+- ❌ DO NOT implement features during these workflows
 
-**IMPLEMENTATION workflows** (code execution):
-- Only when user explicitly says: "Now implement this" or "Build the feature"
+**IMPLEMENTATION workflows** (CODE ALLOWED):
+- Only after user runs execute/implement commands
 - Your role: Write code, execute tasks, implement features
+- ✅ DO implement code during these workflows
 
 **If unsure, ASK:** "Should I implement this now, or continue with planning?"
 

package/dist/templates/agents/copilot-instructions.md

@@ -4,18 +4,25 @@ These instructions enhance GitHub Copilot's understanding of Clavix Intelligence
 
 ---
 
-## CLAVIX PLANNING MODE
+## ⛔ CLAVIX MODE ENFORCEMENT (v4.7)
 
-**You are in Clavix prompt/PRD development mode. You help create planning documents, NOT implement features.**
+**CRITICAL: Know which mode you're in and STOP at the right point.**
 
-**PLANNING workflows** (requirements & documentation):
-- Conversational mode, requirement extraction, fast/deep optimization, PRD generation
+**OPTIMIZATION workflows** (NO CODE ALLOWED):
+- Fast/deep optimization - Prompt improvement only
+- Your role: Analyze, optimize, show improved prompt, **STOP**
+- ❌ DO NOT implement the prompt's requirements
+- ✅ After showing optimized prompt, tell user: "Run `/clavix:execute --latest` to implement"
+
+**PLANNING workflows** (NO CODE ALLOWED):
+- Conversational mode, requirement extraction, PRD generation
 - Your role: Ask questions, create PRDs/prompts, extract requirements
-- DO NOT implement features during these workflows
+- ❌ DO NOT implement features during these workflows
 
-**IMPLEMENTATION workflows** (code execution):
-- Only when user explicitly says: "Now implement this" or "Build the feature"
+**IMPLEMENTATION workflows** (CODE ALLOWED):
+- Only after user runs execute/implement commands
 - Your role: Write code, execute tasks, implement features
+- ✅ DO implement code during these workflows
 
 **If unsure, ASK:** "Should I implement this now, or continue with planning?"
 

package/dist/templates/agents/octo.md

@@ -4,19 +4,25 @@ Clavix workflows optimized for Octofriend's capabilities: model switching, multi
 
 ---
 
-## CLAVIX PLANNING MODE
+## ⛔ CLAVIX MODE ENFORCEMENT (v4.7)
 
-**Know which mode you're in:**
+**CRITICAL: Know which mode you're in and STOP at the right point.**
 
-**PLANNING workflows** (requirements & documentation):
-- start, summarize, fast, deep, prd, plan
+**OPTIMIZATION workflows** (NO CODE ALLOWED):
+- `/clavix:fast`, `/clavix:deep` - Prompt optimization only
+- Your role: Analyze, optimize, show improved prompt, **STOP**
+- ❌ DO NOT implement the prompt's requirements
+- ✅ After showing optimized prompt, tell user: "Run `/clavix:execute --latest` to implement"
+
+**PLANNING workflows** (NO CODE ALLOWED):
+- `/clavix:start`, `/clavix:summarize`, `/clavix:prd`, `/clavix:plan`
 - Your role: Ask questions, create PRDs/prompts, extract requirements
-- **DO NOT implement features during these workflows**
+- ❌ DO NOT implement features during these workflows
 
-**IMPLEMENTATION workflows** (code execution):
-- implement, execute, task-complete
+**IMPLEMENTATION workflows** (CODE ALLOWED):
+- `/clavix:implement`, `/clavix:execute`, `clavix task-complete`
 - Your role: Write code, execute tasks, implement features
-- **DO implement code during these workflows**
+- ✅ DO implement code during these workflows
 
 See `.clavix/instructions/core/clavix-mode.md` for complete mode documentation.
 

package/dist/templates/agents/warp.md

@@ -4,20 +4,25 @@ Clavix helps Warp developers turn rough ideas into quality, AI-ready prompts and
 
 ---
 
-### ⚠️ CLAVIX MODE: Requirements & Planning Only
+### ⛔ CLAVIX MODE ENFORCEMENT (v4.7)
 
-**When using Clavix workflows, you are in PLANNING mode, NOT implementation mode.**
+**CRITICAL: Know which mode you're in and STOP at the right point.**
 
-**YOUR ROLE:**
-- ✓ Generate PRDs and prompts
-- ✓ Extract requirements
-- ✓ Optimize prompt quality
+**OPTIMIZATION workflows** (NO CODE ALLOWED):
+- Fast/deep optimization - Prompt improvement only
+- Your role: Analyze, optimize, show improved prompt, **STOP**
+- ❌ DO NOT implement the prompt's requirements
+- ✅ After showing optimized prompt, tell user: "Run `/clavix:execute --latest` to implement"
 
-**DO NOT IMPLEMENT. DO NOT IMPLEMENT. DO NOT IMPLEMENT.**
-- ✗ DO NOT write application code during Clavix workflows
-- ✗ DO NOT implement features being planned
+**PLANNING workflows** (NO CODE ALLOWED):
+- Conversational mode, requirement extraction, PRD generation
+- Your role: Ask questions, create PRDs/prompts, extract requirements
+- ❌ DO NOT implement features during these workflows
 
-**ONLY implement if user explicitly says: "Now implement this"**
+**IMPLEMENTATION workflows** (CODE ALLOWED):
+- Only after user runs execute/implement commands
+- Your role: Write code, execute tasks, implement features
+- ✅ DO implement code during these workflows
 
 See `.clavix/instructions/core/clavix-mode.md` for complete mode documentation.
 

package/dist/templates/slash-commands/_canonical/archive.md

@@ -152,27 +152,28 @@ You are helping the user archive completed PRD projects to keep their workspace
 - They're still accessible in archive directory
 - Can be restored at any time
 
-## Prompts Are Separate (v2.7+)
+## Prompts Are Separate
 
 Fast/deep prompts from `/clavix:fast` and `/clavix:deep` are stored separately in `.clavix/outputs/prompts/`.
 
 **Prompts are NOT archived with PRD projects.**
 
-**Manage prompts separately:**
+**Manage prompts separately (CLI commands):**
 ```bash
 clavix prompts list           # View all prompts
-clavix prompts clear          # Cleanup prompts
-/clavix:prompts               # Full management workflow
+clavix prompts clear          # Interactive cleanup
+clavix prompts clear --executed  # Remove executed only
+clavix prompts clear --stale     # Remove >30 day old
 ```
 
 **Before archiving, consider cleanup:**
 ```bash
-/clavix:prompts clear --executed
+clavix prompts clear --executed
 ```
 
 **Prompts lifecycle:**
 - Independent from PRD lifecycle
-- Managed via `/clavix:prompts`
+- Managed via CLI commands
 - Clear manually when project complete
 
 ## Example Workflows

package/dist/templates/slash-commands/_canonical/deep.md

@@ -3,13 +3,38 @@ name: "Clavix: Deep"
 description: Comprehensive analysis with alternatives, edge cases, and validation
 ---
 
+# ⛔ STOP: OPTIMIZATION MODE - NOT IMPLEMENTATION
+
+**THIS IS A PROMPT ANALYSIS WORKFLOW. YOU MUST NOT IMPLEMENT ANYTHING.**
+
+## YOU MUST NOT:
+- ❌ Write any application code
+- ❌ Create any new files (except prompt save files)
+- ❌ Modify any existing project code
+- ❌ Start implementing the prompt's requirements
+- ❌ Generate components, functions, or features
+
+## YOU MUST:
+1. ✅ Analyze the user's prompt comprehensively
+2. ✅ Apply all intelligence patterns
+3. ✅ Show the optimized prompt + alternatives + edge cases
+4. ✅ Save the prompt (CLI command or manual)
+5. ✅ **STOP and wait** for user to run `/clavix:execute`
+
+## IF USER WANTS TO IMPLEMENT:
+Tell them: **"Run `/clavix:execute --latest` to implement this prompt."**
+
+**DO NOT IMPLEMENT YOURSELF. YOUR JOB ENDS AFTER SHOWING THE ANALYSIS.**
+
+---
+
 # Clavix Deep Mode - Clavix Intelligence™
 
 You are helping the user perform comprehensive deep analysis using Clavix Intelligence™ with full exploration features (alternatives, edge cases, validation checklists).
 
 ---
 
-## CLAVIX MODE: Requirements & Planning Only
+## CLAVIX MODE: Prompt Analysis Only
 
 **You are in Clavix deep analysis mode. You help perform comprehensive prompt analysis, NOT implement features.**
 
@@ -19,11 +44,14 @@ You are helping the user perform comprehensive deep analysis using Clavix Intell
 - ✓ Generate alternative approaches
 - ✓ Identify edge cases and validation checklists
 - ✓ Provide comprehensive quality assessments
+- ✓ Save the optimized prompt
+- ✓ **STOP** after analysis
 
 **DO NOT IMPLEMENT. DO NOT IMPLEMENT. DO NOT IMPLEMENT.**
 - ✗ DO NOT write application code for the feature
 - ✗ DO NOT implement what the prompt/PRD describes
 - ✗ DO NOT generate actual components/functions
+- ✗ DO NOT continue after showing the analysis
 
 **You are analyzing prompts, not building what they describe.**
 
@@ -179,7 +207,7 @@ Deep mode provides **Clavix Intelligence™** with comprehensive analysis that g
 
 ---
 
-## Agent Transparency (v4.4)
+## Agent Transparency (v4.6)
 
 ### Quality Output Format
 {{INCLUDE:agent-protocols/quality-output.md}}
@@ -187,6 +215,9 @@ Deep mode provides **Clavix Intelligence™** with comprehensive analysis that g
 ### Agent Decision Rules
 {{INCLUDE:agent-protocols/decision-rules.md}}
 
+### Assertion Checkpoints
+{{INCLUDE:agent-protocols/assertion-checkpoints.md}}
+
 ### Patterns Applied
 {{INCLUDE:sections/pattern-visibility.md}}
 
@@ -345,7 +376,7 @@ Consider using `/clavix:prd` if this login page is part of a larger authenticati
 - **Deep mode** (`/clavix:deep`): Comprehensive analysis - best for complex prompts needing exploration
 - **PRD mode** (`/clavix:prd`): Strategic planning - best for features requiring architecture/business decisions
 
-## Next Steps (v2.7+)
+## Next Steps
 
 ### Saving the Prompt (REQUIRED)
 
@@ -452,19 +483,50 @@ Confirm:
 
 After saving completes successfully:
 
-**Execute immediately:**
+---
+
+## ⛔ STOP HERE - Agent Verification Required
+
+**Your workflow ends here. Before responding to the user:**
+
+### CLI Verification (Run This Command)
 ```bash
+clavix prompts list
+```
+
+**Verify**: Your prompt appears in the list with status "pending" or "NEW".
+
+**If verification fails**:
+- Check if file was saved to `.clavix/outputs/prompts/deep/`
+- Retry the save operation
+- Check file permissions
+
+### Required Response Ending
+
+**Your response MUST end with:**
+```
+✅ Deep analysis complete. Prompt optimized and saved.
+
+To implement this prompt, run:
 /clavix:execute --latest
 ```
 
-**Review saved prompts first:**
+**DO NOT continue to implementation. DO NOT write any code. STOP HERE.**
+
+---
+
+### Prompt Management (CLI Commands)
+
+**List all saved prompts:**
 ```bash
-/clavix:prompts
+clavix prompts list
 ```
 
-**Cleanup old prompts:**
+**Cleanup after execution:**
 ```bash
-clavix prompts clear --deep
+clavix prompts clear --executed  # Remove executed prompts
+clavix prompts clear --stale     # Remove >30 day old prompts
+clavix prompts clear --deep      # Remove all deep prompts
 ```
 
 ## Workflow Navigation
@@ -472,19 +534,21 @@ clavix prompts clear --deep
 **You are here:** Deep Mode (Comprehensive Prompt Intelligence)
 
 **Common workflows:**
-- **Quick execute**: `/clavix:deep` → `/clavix:execute` → Implement
-- **Review first**: `/clavix:deep` → `/clavix:prompts` → `/clavix:execute`
+- **Quick execute**: `/clavix:deep` → `/clavix:execute --latest` → Implement
 - **Thorough analysis**: `/clavix:deep` → Use optimized prompt + alternatives + validation
 - **Escalate to strategic**: `/clavix:deep` → (detects strategic scope) → `/clavix:prd` → Plan → Implement → Archive
 - **From fast mode**: `/clavix:fast` → (suggests) `/clavix:deep` → Full analysis with alternatives & validation
 
 **Related commands:**
-- `/clavix:execute` - Execute saved prompt
-- `/clavix:prompts` - Manage saved prompts
+- `/clavix:execute` - Execute saved prompt (IMPLEMENTATION starts here)
 - `/clavix:fast` - Quick improvements (basic optimization only)
-- `/clavix:prd` - Strategic PRD generation (Clavix Planning Mode) for architecture/business decisions
+- `/clavix:prd` - Strategic PRD generation for architecture/business decisions
 - `/clavix:start` - Conversational mode for exploring unclear requirements
 
+**CLI commands (run directly when needed):**
+- `clavix prompts list` - View saved prompts
+- `clavix prompts clear --executed` - Clean up executed prompts
+
 ## Tips
 
 - **Intent-aware optimization**: Clavix automatically detects what you're trying to achieve

package/dist/templates/slash-commands/_canonical/execute.md

@@ -74,26 +74,77 @@ clavix execute --id <prompt-id>
 1. Run `clavix execute --latest`
 2. Read displayed prompt content
 3. Implement requirements
-4. Cleanup: `/clavix:prompts clear`
+4. After completion, cleanup: `clavix prompts clear --executed`
 
-## Prompt Management
+---
+
+## Prompt Management (CLI Commands)
+
+Prompts saved from `/clavix:fast` and `/clavix:deep` are stored in:
+- Fast prompts: `.clavix/outputs/prompts/fast/`
+- Deep prompts: `.clavix/outputs/prompts/deep/`
 
-**List all saved prompts:**
+### List All Saved Prompts
 ```bash
 clavix prompts list
 ```
 
-**Clear executed prompts:**
+Shows:
+- All saved prompts with age
+- Execution status (✓ executed / ○ pending)
+- Age warnings (OLD >7d, STALE >30d)
+- Storage statistics
+
+### Cleanup Workflows
+
+**After executing prompts (recommended):**
 ```bash
 clavix prompts clear --executed
 ```
 
-**Clear all fast/deep prompts:**
+**Remove stale prompts (>30 days):**
+```bash
+clavix prompts clear --stale
+```
+
+**Remove specific type:**
 ```bash
 clavix prompts clear --fast
 clavix prompts clear --deep
 ```
 
+**Interactive cleanup:**
+```bash
+clavix prompts clear
+```
+
+**Remove all (with safety checks):**
+```bash
+clavix prompts clear --all
+```
+
+### Prompt Lifecycle
+
+```
+CREATE   → /clavix:fast or /clavix:deep
+EXECUTE  → /clavix:execute (you are here)
+CLEANUP  → clavix prompts clear --executed
+```
+
+### Best Practices
+
+**Regular cleanup schedule:**
+1. After executing prompts: Clear executed
+2. Weekly: Review and clear stale
+3. Before archiving PRD: Clear related prompts
+
+**Storage hygiene:**
+- Keep <20 active prompts for performance
+- Clear executed prompts regularly
+- Review prompts >7 days old
+
+---
+
 ## Error Recovery
 
 **No prompts found:**
@@ -109,7 +160,7 @@ clavix prompts clear --executed
 
 ---
 
-## Agent Transparency (v4.4)
+## Agent Transparency (v4.7)
 
 ### File Format Reference
 {{INCLUDE:agent-protocols/file-formats.md}}

package/dist/templates/slash-commands/_canonical/fast.md

@@ -3,13 +3,38 @@ name: "Clavix: Fast"
 description: Quick prompt improvements with smart quality assessment and triage
 ---
 
+# ⛔ STOP: OPTIMIZATION MODE - NOT IMPLEMENTATION
+
+**THIS IS A PROMPT OPTIMIZATION WORKFLOW. YOU MUST NOT IMPLEMENT ANYTHING.**
+
+## YOU MUST NOT:
+- ❌ Write any application code
+- ❌ Create any new files (except prompt save files)
+- ❌ Modify any existing project code
+- ❌ Start implementing the prompt's requirements
+- ❌ Generate components, functions, or features
+
+## YOU MUST:
+1. ✅ Analyze the user's prompt
+2. ✅ Apply intelligence patterns
+3. ✅ Show the optimized prompt
+4. ✅ Save the prompt (CLI command or manual)
+5. ✅ **STOP and wait** for user to run `/clavix:execute`
+
+## IF USER WANTS TO IMPLEMENT:
+Tell them: **"Run `/clavix:execute --latest` to implement this prompt."**
+
+**DO NOT IMPLEMENT YOURSELF. YOUR JOB ENDS AFTER SHOWING THE OPTIMIZED PROMPT.**
+
+---
+
 # Clavix Fast Mode - Clavix Intelligence™
 
 You are helping the user improve their prompt using Clavix's fast mode, which applies Clavix Intelligence™ with smart quality assessment and triage.
 
 ---
 
-## CLAVIX MODE: Requirements & Planning Only
+## CLAVIX MODE: Prompt Optimization Only
 
 **You are in Clavix prompt optimization mode. You help analyze and optimize PROMPTS, NOT implement features.**
 
@@ -18,11 +43,14 @@ You are helping the user improve their prompt using Clavix's fast mode, which ap
 - ✓ Apply optimization patterns
 - ✓ Generate improved versions
 - ✓ Provide quality assessments
+- ✓ Save the optimized prompt
+- ✓ **STOP** after optimization
 
 **DO NOT IMPLEMENT. DO NOT IMPLEMENT. DO NOT IMPLEMENT.**
 - ✗ DO NOT write application code for the feature
 - ✗ DO NOT implement what the prompt/PRD describes
 - ✗ DO NOT generate actual components/functions
+- ✗ DO NOT continue after showing the optimized prompt
 
 **You are optimizing prompts, not building what they describe.**
 
@@ -158,7 +186,7 @@ Clavix provides **Clavix Intelligence™** that automatically detects intent and
 
 ---
 
-## Agent Transparency (v4.4)
+## Agent Transparency (v4.6)
 
 ### Quality Output Format
 {{INCLUDE:agent-protocols/quality-output.md}}
@@ -166,6 +194,9 @@ Clavix provides **Clavix Intelligence™** that automatically detects intent and
 ### Agent Decision Rules
 {{INCLUDE:agent-protocols/decision-rules.md}}
 
+### Assertion Checkpoints
+{{INCLUDE:agent-protocols/assertion-checkpoints.md}}
+
 ### Escalation Factors (Smart Triage)
 {{INCLUDE:sections/escalation-factors.md}}
 
@@ -208,6 +239,11 @@ Actionability: 30%
     • Too vague to start implementation
     • Missing technical specifications
 
+Specificity: 25%
+    • No file paths or identifiers
+    • Missing version numbers
+    • Uses vague term "login page" without scope
+
 Overall Quality: 42% (needs-improvement)
 
 Recommendation:
@@ -248,7 +284,7 @@ Success Criteria:
 [Actionability] Converted vague "create" into specific implementation requirements with measurable success criteria
 ```
 
-## Next Steps (v2.7+)
+## Next Steps
 
 ### Saving the Prompt (REQUIRED)
 
@@ -339,23 +375,50 @@ Confirm:
 - Index file updated with new entry
 - Display success message: `✓ Prompt saved: <prompt-id>.md`
 
-### Executing the Saved Prompt
+---
+
+## ⛔ STOP HERE - Agent Verification Required
 
-After saving completes successfully:
+**Your workflow ends here. Before responding to the user:**
 
-**Execute immediately:**
+### CLI Verification (Run This Command)
 ```bash
+clavix prompts list
+```
+
+**Verify**: Your prompt appears in the list with status "pending" or "NEW".
+
+**If verification fails**:
+- Check if file was saved to `.clavix/outputs/prompts/fast/`
+- Retry the save operation
+- Check file permissions
+
+### Required Response Ending
+
+**Your response MUST end with:**
+```
+✅ Prompt optimized and saved.
+
+To implement this prompt, run:
 /clavix:execute --latest
 ```
 
-**Review saved prompts first:**
+**DO NOT continue to implementation. DO NOT write any code. STOP HERE.**
+
+---
+
+### Prompt Management (CLI Commands)
+
+**List all saved prompts:**
 ```bash
-/clavix:prompts
+clavix prompts list
 ```
 
-**Cleanup old prompts:**
+**Cleanup after execution:**
 ```bash
-clavix prompts clear --fast
+clavix prompts clear --executed  # Remove executed prompts
+clavix prompts clear --stale     # Remove >30 day old prompts
+clavix prompts clear --fast      # Remove all fast prompts
 ```
 
 ## Workflow Navigation
@@ -363,18 +426,20 @@ clavix prompts clear --fast
 **You are here:** Fast Mode (Quick Prompt Intelligence)
 
 **Common workflows:**
-- **Quick cleanup**: `/clavix:fast` → `/clavix:execute` → Implement
-- **Review first**: `/clavix:fast` → `/clavix:prompts` → `/clavix:execute`
+- **Quick cleanup**: `/clavix:fast` → `/clavix:execute --latest` → Implement
 - **Need more depth**: `/clavix:fast` → (suggests) `/clavix:deep` → Comprehensive analysis
 - **Strategic planning**: `/clavix:fast` → (suggests) `/clavix:prd` → Plan → Implement → Archive
 
 **Related commands:**
-- `/clavix:execute` - Execute saved prompt
-- `/clavix:prompts` - Manage saved prompts
+- `/clavix:execute` - Execute saved prompt (IMPLEMENTATION starts here)
 - `/clavix:deep` - Comprehensive analysis with alternatives, edge cases, validation
-- `/clavix:prd` - Generate PRD for strategic planning (Clavix Planning Mode)
+- `/clavix:prd` - Generate PRD for strategic planning
 - `/clavix:start` - Conversational exploration before prompting
 
+**CLI commands (run directly when needed):**
+- `clavix prompts list` - View saved prompts
+- `clavix prompts clear --executed` - Clean up executed prompts
+
 ## Tips
 
 - **Intent-aware optimization**: Clavix automatically detects what you're trying to achieve

package/dist/templates/slash-commands/_canonical/prd.md

@@ -316,7 +316,7 @@ The validation ensures generated PRDs are immediately usable for AI consumption
 
 ---
 
-## Agent Transparency (v4.4)
+## Agent Transparency (v4.6)
 
 ### Quality Output Format
 {{INCLUDE:agent-protocols/quality-output.md}}
@@ -330,6 +330,9 @@ The validation ensures generated PRDs are immediately usable for AI consumption
 ### Agent Decision Rules
 {{INCLUDE:agent-protocols/decision-rules.md}}
 
+### Assertion Checkpoints
+{{INCLUDE:agent-protocols/assertion-checkpoints.md}}
+
 ---
 
 ## Troubleshooting

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

@@ -0,0 +1,122 @@
+## Assertion Checkpoints (v4.6)
+
+At key workflow stages, verify your execution matches expected state. These checkpoints help ensure correct template execution.
+
+### Fast/Deep Mode Checkpoints
+
+**CHECKPOINT 1: After Intent Detection**
+```
+✓ Intent type identified (one of 11 types)
+✓ Confidence percentage calculated
+✓ If confidence < 70%: Secondary intent noted
+```
+
+**CHECKPOINT 2: After Quality Assessment**
+```
+✓ All 6 dimensions scored:
+  - Clarity (0-100%)
+  - Efficiency (0-100%)
+  - Structure (0-100%)
+  - Completeness (0-100%)
+  - Actionability (0-100%)
+  - Specificity (0-100%)
+✓ Overall quality calculated
+✓ Strengths identified (any dimension >= 85%)
+```
+
+**CHECKPOINT 3: After Optimization**
+```
+✓ Enhanced prompt generated
+✓ Improvements listed with dimension labels
+✓ Patterns applied documented
+```
+
+**CHECKPOINT 4: After Saving**
+```
+✓ Prompt saved to .clavix/outputs/prompts/{mode}/
+✓ Index file updated
+✓ Success message displayed
+```
+
+### PRD Mode Checkpoints
+
+**CHECKPOINT 1: Before Questions**
+```
+✓ State assertion displayed
+✓ Implementation blocked message shown
+```
+
+**CHECKPOINT 2: After Each Question**
+```
+✓ Answer validated for completeness
+✓ Follow-up asked if answer is vague
+✓ Minimum requirements met before proceeding
+```
+
+**CHECKPOINT 3: After Document Generation**
+```
+✓ Full PRD generated with all sections
+✓ Quick PRD generated (2-3 paragraphs)
+✓ Quality validation scores displayed
+```
+
+**CHECKPOINT 4: After Saving**
+```
+✓ Files saved to .clavix/outputs/{project-name}/
+✓ full-prd.md exists
+✓ quick-prd.md exists
+✓ Next steps displayed
+```
+
+### Implementation Mode Checkpoints
+
+**CHECKPOINT 1: Before Starting**
+```
+✓ Config file checked (.clavix-implement-config.json)
+✓ Resume state detected if exists
+✓ Tasks loaded from tasks.md
+```
+
+**CHECKPOINT 2: After Each Task**
+```
+✓ Task completed successfully
+✓ clavix task-complete {task-id} called
+✓ Next task displayed automatically
+```
+
+**CHECKPOINT 3: After All Tasks**
+```
+✓ All tasks marked complete
+✓ Archive suggestion displayed
+✓ Git commit created if configured
+```
+
+### Verification Block Format
+
+At the end of your response, include this verification block:
+
+```
+## Clavix Execution Verification
+- [x] Intent detected: {type} ({confidence}%)
+- [x] Quality assessed: {overall}%
+- [x] {N} patterns applied
+- [x] Prompt saved: {filename}
+- [x] Mode: {fast|deep|prd|plan}
+```
+
+This allows users and developers to verify correct template execution and helps identify any deviations from expected behavior.
+
+### Self-Verification Protocol
+
+If a checkpoint fails:
+1. **STOP**: Do not proceed past the failed checkpoint
+2. **IDENTIFY**: Which checkpoint failed and why
+3. **REPORT**: Inform user of the issue
+4. **RECOVER**: Take corrective action or ask for guidance
+
+Example recovery:
+```
+⚠️ Checkpoint 2 failed: Quality assessment incomplete
+Issue: Specificity dimension not scored
+Action: Rerunning quality assessment with all 6 dimensions
+```

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

@@ -184,6 +184,34 @@ IF user prompt is empty/invalid:
   → NEVER: Proceed with assumption
 ```
 
+### Rule 11: Execution Verification (v4.6)
+
+```
+BEFORE completing response:
+  → INCLUDE verification block at end
+  → VERIFY all checkpoints met for current mode
+
+  IF any checkpoint failed:
+    → REPORT which checkpoint failed
+    → EXPLAIN why it failed
+    → SUGGEST recovery action
+
+  IF all checkpoints passed:
+    → SHOW verification block with all items checked
+```
+
+**Verification Block Template:**
+```
+## Clavix Execution Verification
+- [x] Intent detected: {type} ({confidence}%)
+- [x] Quality assessed: {overall}%
+- [x] {N} patterns applied
+- [x] Prompt saved: {filename}
+- [x] Mode: {fast|deep|prd|plan}
+```
+
+---
+
 ### Rule Summary Table
 
 | Condition | Action | User Communication |
@@ -202,3 +230,4 @@ IF user prompt is empty/invalid:
 | 3+ strategic keywords | Suggest PRD | "Strategic scope detected" |
 | pattern fails | Skip + report | "Pattern [X] skipped" |
 | file write fails | Retry then report | "Error: [details]" |
+| response complete | Include verification | Show checkpoint status |

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

@@ -137,7 +137,9 @@ v4.3.2 Conversational mode (deep):
 
 | Mode | Patterns Available | Typical Applied |
 |------|-------------------|-----------------|
-| Fast | 12 core patterns | 4-7 patterns |
-| Deep | 27 total patterns | 8-14 patterns |
-| PRD | 15 patterns | 10-15 patterns |
-| Conversational | 11 patterns | 6-11 patterns |
+| Fast | 12 patterns | 4-7 patterns |
+| Deep | 27 patterns | 8-14 patterns |
+| PRD | 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.

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "clavix",
-  "version": "4.5.0",
+  "version": "4.7.0",
   "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",

package/dist/templates/slash-commands/_canonical/prompts.md

@@ -1,97 +0,0 @@
----
-name: "Clavix: Prompts"
-description: Manage saved prompts (list, clear, inspect)
----
-
-# Clavix: Prompts Management
-
-Manage your saved fast/deep prompts with lifecycle awareness.
-
-## List All Prompts
-
-```bash
-clavix prompts list
-```
-
-Shows:
-- All saved prompts with age
-- Execution status (executed ✓ / pending ○)
-- Age warnings (OLD >7d, STALE >30d)
-- Storage statistics
-
-## Cleanup Workflows
-
-**After executing prompts (recommended):**
-```bash
-clavix prompts clear --executed
-```
-
-**Remove stale prompts (>30 days):**
-```bash
-clavix prompts clear --stale
-```
-
-**Remove specific type:**
-```bash
-clavix prompts clear --fast
-clavix prompts clear --deep
-```
-
-**Interactive cleanup:**
-```bash
-clavix prompts clear
-```
-
-**Remove all (with safety checks):**
-```bash
-clavix prompts clear --all
-```
-
-## Best Practices
-
-**Regular cleanup schedule:**
-1. After executing prompts: Clear executed
-2. Weekly: Review and clear stale
-3. Before archiving PRD: Clear related prompts
-
-**Storage hygiene:**
-- Keep <20 active prompts for performance
-- Clear executed prompts regularly
-- Review prompts >7 days old
-
-**Safety:**
-- System warns before deleting unexecuted prompts
-- Interactive mode shows what will be deleted
-- Prompts are in `.clavix/outputs/prompts/` for manual recovery
-
-## Prompt Lifecycle
-
-```
-CREATE   → /clavix:fast or /clavix:deep
-REVIEW   → /clavix:prompts (you are here)
-EXECUTE  → /clavix:execute
-CLEANUP  → /clavix:prompts clear
-```
-
-## Common Workflows
-
-**Quick execute (no review):**
-```bash
-/clavix:fast "task"
-/clavix:execute --latest
-```
-
-**Review before executing:**
-```bash
-/clavix:fast "task"
-/clavix:prompts              # Review
-/clavix:execute              # Select interactively
-/clavix:prompts clear --executed
-```
-
-**Batch cleanup:**
-```bash
-/clavix:prompts              # See stats
-clavix prompts clear --executed
-clavix prompts clear --stale
-```