clavix 5.0.0 → 5.1.0

package/dist/templates/instructions/core/mode-enforcement.md

@@ -1,4 +1,4 @@
-# Clavix Mode Enforcement v4.0
+# Clavix Mode Enforcement v5.1
 
 This is the authoritative reference for mode enforcement in Clavix workflows. All templates MUST adhere to these patterns.
 
@@ -8,7 +8,7 @@ This is the authoritative reference for mode enforcement in Clavix workflows. Al
 
 ### Planning Mode Declaration
 
-Used in: `fast.md`, `deep.md`, `prd.md`, `start.md`, `summarize.md`, `plan.md`
+Used in: `improve.md`, `prd.md`, `start.md`, `summarize.md`, `plan.md`
 
 ```markdown
 ## CLAVIX MODE: [Specific Planning Type]
@@ -32,7 +32,7 @@ For complete mode documentation, see: `.clavix/instructions/core/clavix-mode.md`
 
 ### Implementation Mode Declaration
 
-Used in: `implement.md`, `execute.md`
+Used in: `implement.md`
 
 ```markdown
 ## CLAVIX MODE: Implementation
@@ -148,7 +148,7 @@ All planning templates MUST include this protocol:
 1. Planning workflow must complete first (files saved)
 2. User must explicitly run implementation command
 3. Do NOT switch modes based on verbal requests alone
-4. Suggest correct command: "To implement, run `/clavix:execute` or `/clavix:implement`"
+4. Suggest correct command: "To implement, run `/clavix:implement`"
 
 ### From Implementation Back to Planning
 
@@ -204,34 +204,33 @@ When updating templates, verify:
 
 ## Template Categories
 
-### Planning Templates (6 total)
+### Planning Templates (5 total)
 
 | Template | Mode Type | Self-Correction | Primary Action |
 |----------|-----------|-----------------|----------------|
-| `fast.md` | Requirements & Planning | Required | Prompt optimization |
-| `deep.md` | Requirements & Planning | Required | Comprehensive analysis |
+| `improve.md` | Requirements & Planning | Required | Smart prompt optimization (auto-depth) |
 | `prd.md` | Requirements & Planning | Required | PRD generation |
 | `start.md` | Requirements & Planning | Required | Requirements gathering |
 | `summarize.md` | Requirements & Planning | Required | Requirements extraction |
 | `plan.md` | Pre-Implementation Planning | Required | Task breakdown |
 
-### Implementation Templates (2 total)
+### Implementation Templates (1 total)
 
 | Template | Mode Type | Entry Validation | Primary Action |
 |----------|-----------|------------------|----------------|
-| `implement.md` | Implementation | Required | Task execution |
-| `execute.md` | Implementation | Required | Prompt implementation |
+| `implement.md` | Implementation | Required | Task or prompt execution (auto-detects source) |
 
 ### Utility Templates (2 total)
 
 | Template | Mode | Notes |
 |----------|------|-------|
 | `archive.md` | Management | Project archival |
-| `prompts.md` | Management | Prompt management |
+| `verify.md` | Verification | Post-implementation verification |
 
 ---
 
 ## Version History
 
+- **v5.1** (2025): Consolidated execute into implement with auto-detection, removed fast/deep in favor of unified improve
 - **v4.0** (2024): Added self-correction protocol, standardized checkpoints, mode entry validation
 - **v3.0** (2024): Initial mode separation between planning and implementation

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

@@ -232,7 +232,7 @@ Result: Project permanently deleted
 
 ---
 
-## Agent Transparency (v5.0)
+## Agent Transparency (v5.1)
 
 ### CLI Reference (Commands I Execute)
 {{INCLUDE:agent-protocols/cli-reference.md}}

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

@@ -1,24 +1,46 @@
 ---
 name: "Clavix: Implement"
-description: Execute tasks from the implementation plan
+description: Execute tasks or prompts (auto-detects source)
 ---
 
-# Clavix: Implement Your Tasks
+# Clavix: Implement
 
-Time to build your project task by task! I'll work through your task list, building each feature and tracking progress.
+Time to build! This command auto-detects what to implement:
+- **Tasks from PRD workflow** - Your task list from `/clavix:plan`
+- **Prompts from improve workflow** - Your optimized prompts from `/clavix:improve`
 
 ---
 
 ## What This Does
 
 When you run `/clavix:implement`, I:
-1. **Find your task list** - Load tasks.md from your PRD output
-2. **Pick up where you left off** - Find the next incomplete task
-3. **Build each task** - Implement one at a time, in order
-4. **Mark progress automatically** - Update checkboxes when done
-5. **Create commits (optional)** - Git history as you go
+1. **Auto-detect what to build** - Check tasks.md first, then prompts/
+2. **Find your work** - Load from PRD output or saved prompts
+3. **Build systematically** - Tasks in order, or implement your prompt
+4. **Mark progress** - Update checkboxes or prompt metadata
+5. **Verify automatically** - Run tests and checks when done
 
-**You just say "let's build" and I handle the rest.**
+**You just say "implement" and I handle the rest.**
+
+### Detection Priority
+
+```
+/clavix:implement
+    │
+    ├─► Check .clavix/outputs/<project>/tasks.md
+    │       └─► If found → Task Implementation Mode
+    │
+    └─► Check .clavix/outputs/prompts/*.md
+            └─► If found → Prompt Execution Mode
+            └─► If neither → Ask what to build
+```
+
+### Explicit Flags
+
+Override auto-detection when needed:
+- `--tasks` - Force task mode (skip prompt check)
+- `--prompt <id>` - Execute specific prompt by ID
+- `--latest` - Execute most recent prompt
 
 ---
 
@@ -273,22 +295,169 @@ I find them automatically from tasks.md:
 
 You don't need to remember these - I handle all the tracking.
 
+---
+
+# Prompt Execution Mode
+
+When I detect saved prompts (or you use `--latest`/`--prompt`), I switch to prompt execution mode.
+
+## How Prompt Execution Works
+
+### The Quick Version
+
+```
+You:    /clavix:implement --latest
+Me:     [Finds your latest prompt]
+        [Reads requirements]
+        [Implements everything]
+        [Runs verification]
+Me:     "Done! Here's what I built..."
+```
+
+### The Detailed Version (v5 Agentic-First)
+
+**Step 1: I find your prompt**
+
+I read directly from the file system:
+- List `.clavix/outputs/prompts/*.md` to find saved prompts
+- Get the most recent one (by timestamp in filename or frontmatter)
+- Read the prompt file: `.clavix/outputs/prompts/<id>.md`
+
+**Step 2: I read and understand**
+
+I parse the prompt file and extract:
+- The objective (what to build)
+- Requirements (specifics to implement)
+- Technical constraints (how to build it)
+- Success criteria (how to know it's done)
+
+**Step 3: I implement everything**
+
+This is where I actually write code using my native tools:
+- Create new files as needed
+- Modify existing files
+- Write functions, components, classes
+- Add tests if specified
+
+**Step 4: I verify automatically**
+
+After building, I verify by:
+- Running tests (if test suite exists)
+- Building/compiling to ensure no errors
+- Checking requirements from the checklist
+
+**Step 5: I report results**
+
+You'll see a summary of:
+- What I built
+- What passed verification
+- Any issues (if they exist)
+
+---
+
+## Prompt Management
+
+**Where prompts live:**
+- All prompts: `.clavix/outputs/prompts/*.md`
+- Metadata: In frontmatter of each `.md` file
+
+### How I Access Prompts (Native Tools)
+
+| What I Do | How I Do It |
+|-----------|-------------|
+| List saved prompts | List `.clavix/outputs/prompts/*.md` files |
+| Get latest prompt | Find newest file by timestamp in filename |
+| Get specific prompt | Read `.clavix/outputs/prompts/<id>.md` |
+| Mark as executed | Edit frontmatter: `executed: true` |
+| Clean up executed | Delete files where frontmatter has `executed: true` |
+
+### The Prompt Lifecycle
+
+```
+1. YOU CREATE   →  /clavix:improve (saves to .clavix/outputs/prompts/<id>.md)
+2. I EXECUTE    →  /clavix:implement --latest (reads and implements)
+3. I VERIFY     →  Automatic verification
+4. MARK DONE    →  I update frontmatter with executed: true
+```
+
+---
+
+## Automatic Verification (Prompt Mode)
+
+**I always verify after implementing. You don't need to ask.**
+
+### What Happens Automatically
+
+After I finish building, I run verification myself:
+
+1. **Load the checklist** - From your executed prompt (what to check)
+2. **Run automated tests** - Test suite, build, linting, type checking
+3. **Check each requirement** - Make sure everything was implemented
+4. **Generate a report** - Show you what passed and failed
+
+### What You'll See
+
+```
+Implementation complete for [prompt-id]
+
+Verification Results:
+8 items passed
+1 item needs attention: [specific issue]
+
+Would you like me to fix the failing item?
+```
+
+### Understanding the Symbols
+
+| Symbol | Meaning |
+|--------|---------|
+| Pass | Passed - This works |
+| Fail | Failed - Needs fixing |
+| Skip | Skipped - Check later |
+| N/A | N/A - Doesn't apply |
+
+### When Things Fail
+
+**I try to fix issues automatically:**
+
+If verification finds problems, I'll:
+1. Tell you what failed and why
+2. Offer to fix it
+3. Re-verify after fixing
+
+**If I can't fix it myself:**
+
+I'll explain what's wrong and what you might need to do:
+> "The database connection is failing - this might be a configuration issue.
+> Can you check that your `.env` file has the correct `DATABASE_URL`?"
+
+---
+
 ## Workflow Navigation
 
-**Where you are:** Implement (building your tasks)
+**Where you are:** Implement (building tasks or prompts)
+
+**How you got here (two paths):**
 
-**How you got here:**
+**PRD Path:**
 1. `/clavix:prd` → Created your requirements document
 2. `/clavix:plan` → Generated your task breakdown
-3. **`/clavix:implement`** → Now building everything (you are here)
+3. **`/clavix:implement`** → Now building tasks (you are here)
+
+**Improve Path:**
+1. `/clavix:improve` → Optimized your prompt
+2. **`/clavix:implement --latest`** → Now building prompt (you are here)
 
 **What happens after:**
 - All tasks done → `/clavix:archive` to wrap up
+- Prompt complete → Verification runs automatically
 - Need to pause → Just stop. Run `/clavix:implement` again to continue
 
 **Related commands:**
-- `/clavix:plan` - Regenerate tasks if needed
+- `/clavix:improve` - Optimize prompts (creates prompts for execution)
+- `/clavix:plan` - Generate tasks from PRD
 - `/clavix:prd` - Review requirements
+- `/clavix:verify` - Detailed verification (if needed)
 - `/clavix:archive` - Archive when done
 
 ---
@@ -302,7 +471,7 @@ You don't need to remember these - I handle all the tracking.
 
 ---
 
-## Agent Transparency (v5.0)
+## Agent Transparency (v5.1)
 
 ### Workflow State Detection
 {{INCLUDE:agent-protocols/state-awareness.md}}
@@ -406,3 +575,47 @@ You don't need to remember these - I handle all the tracking.
 > [I fix the issues]
 >
 > ✓ Tests passing now!"
+
+---
+
+## Prompt Mode Troubleshooting
+
+### "No prompts found"
+
+**What happened:** I can't find any saved prompts.
+
+**What I'll do:**
+> "I don't see any saved prompts. Let's create one first!
+>
+> Run `/clavix:improve 'your requirement'` and come back with `/clavix:implement --latest`"
+
+### "Prompt is old or stale"
+
+**What happened:** Your prompt is more than 7 days old.
+
+**What I'll do:**
+> "This prompt is a bit old. Want me to proceed anyway, or should we create a fresh one?"
+
+### "Verification keeps failing"
+
+**What happened:** I can't get verification to pass after trying.
+
+**What I'll do:**
+> "I've tried a few fixes but this item keeps failing. Here's what's happening: [details]
+>
+> Would you like me to:
+> 1. Keep trying with a different approach
+> 2. Skip this check for now
+> 3. Show you what needs manual attention"
+
+### "Both tasks and prompts exist"
+
+**What happened:** You have both a tasks.md and saved prompts.
+
+**What I'll do:**
+> "I found both tasks and prompts. Which should I implement?
+>
+> - Tasks from your PRD (8 tasks remaining)
+> - Prompt: 'Add dark mode support'
+>
+> Or use `--tasks` or `--prompt <id>` to specify."

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

@@ -28,10 +28,10 @@ This template exists because agents (including you) tend to "help" by doing work
 2. Analyze it using the workflow below
 3. Output the analysis (intent, quality, optimized prompt)
 4. Save to `.clavix/outputs/prompts/`
-5. STOP and wait for `/clavix:execute`
+5. STOP and wait for `/clavix:implement`
 
 ## IF USER WANTS TO IMPLEMENT:
-Tell them: **"Run `/clavix:execute --latest` to implement this prompt."**
+Tell them: **"Run `/clavix:implement --latest` to implement this prompt."**
 
 **DO NOT IMPLEMENT YOURSELF. YOUR JOB ENDS AFTER SHOWING THE OPTIMIZED PROMPT.**
 
@@ -74,7 +74,7 @@ Implementation: BLOCKED - I will analyze and improve the prompt, not implement i
 
 ## What is Clavix Improve Mode?
 
-v4.11 introduces a unified **improve** mode that intelligently selects the appropriate analysis depth:
+Clavix provides a unified **improve** mode that intelligently selects the appropriate analysis depth:
 
 **Smart Depth Selection:**
 - **Quality Score >= 75%**: Auto-selects **comprehensive** depth (the prompt is good, add polish)
@@ -473,7 +473,7 @@ Before outputting final message, confirm ALL of these:
 ✅ Prompt saved to: `.clavix/outputs/prompts/<actual-prompt-id>.md`
 
 Ready to build this? Just say "let's implement" or run:
-/clavix:execute --latest
+/clavix:implement --latest
 ```
 
 **Replace `<actual-prompt-id>` with the real ID you generated (e.g., `std-20250126-143022-a3f2`).**
@@ -490,12 +490,12 @@ Wait for the user to decide what to do next.
 **You are here:** Improve Mode (Unified Prompt Intelligence)
 
 **Common workflows:**
-- **Quick cleanup**: `/clavix:improve` -> `/clavix:execute --latest` -> Implement
+- **Quick cleanup**: `/clavix:improve` -> `/clavix:implement --latest` -> Build
 - **Force comprehensive**: `/clavix:improve --comprehensive` -> Full analysis with alternatives
 - **Strategic planning**: `/clavix:improve` -> (suggests) `/clavix:prd` -> Plan -> Implement -> Archive
 
 **Related commands:**
-- `/clavix:execute` - Execute saved prompt (IMPLEMENTATION starts here)
+- `/clavix:implement` - Execute saved prompt or tasks (IMPLEMENTATION starts here)
 - `/clavix:prd` - Generate PRD for strategic planning
 - `/clavix:start` - Conversational exploration before prompting
 - `/clavix:verify` - Verify implementation against checklist
@@ -506,7 +506,7 @@ Wait for the user to decide what to do next.
 
 ---
 
-## Agent Transparency (v5.0)
+## Agent Transparency (v5.1)
 
 ### CLI Reference (Commands I Execute)
 {{INCLUDE:agent-protocols/cli-reference.md}}

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

@@ -84,36 +84,24 @@ Implementation: BLOCKED - I will create tasks, not implement them
 
 **As an AI agent, you have two execution options:**
 
-#### **Option 1: Run CLI Command** (Recommended for most cases)
+#### **Agent Execution Protocol (v5)**
 
 1. **Validate prerequisites**:
    - Check if `.clavix/outputs/` directory exists
    - Look for PRD artifacts: `full-prd.md`, `quick-prd.md`, `mini-prd.md`, or `optimized-prompt.md`
    - **If not found**: Error inline - "No PRD found in `.clavix/outputs/`. Use `/clavix:prd` or `/clavix:summarize` first."
 
-2. **Run the CLI command**:
-   ```bash
-   clavix plan
-   ```
+2. **Read the PRD** from `.clavix/outputs/[project-name]/`
 
-   Or specify a project:
-   ```bash
-   clavix plan --project project-name
-   ```
+3. **Generate task breakdown** following Part B principles
 
-   Or generate from saved session (auto-creates mini-prd.md):
-   ```bash
-   clavix plan --session SESSION_ID
-   ```
+4. **Create `tasks.md`** using your Write tool with format specified in "Task Format Reference" below
+
+5. **Save to**: `.clavix/outputs/[project-name]/tasks.md`
 
-3. **CLI will handle**:
-   - Project selection (if multiple)
-   - Reading PRD content
-   - Generating task breakdown
-   - Creating `tasks.md` file
-   - Formatting with proper task IDs
+6. **Use exact format** (task IDs, checkboxes, structure)
 
-#### **Option 2: Generate Tasks Directly** (If agent has full PRD context)
+#### **Alternative: Generate Tasks Directly** (If agent has full PRD context)
 
 If you have the full PRD content in memory and want to generate tasks directly:
 
@@ -301,7 +289,7 @@ The generated `tasks.md` will look like:
 
 ---
 
-## Agent Transparency (v4.9)
+## Agent Transparency (v5.1)
 
 ### Workflow State Detection
 {{INCLUDE:agent-protocols/state-awareness.md}}

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

@@ -328,7 +328,7 @@ The validation ensures generated PRDs are immediately usable for AI consumption
 
 ---
 
-## Agent Transparency (v4.9)
+## Agent Transparency (v5.1)
 
 ### PRD Examples
 {{INCLUDE:sections/prd-examples.md}}

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

@@ -202,7 +202,7 @@ The goal is natural exploration of requirements, not a rigid questionnaire. Foll
 
 ---
 
-## Agent Transparency (v4.9)
+## Agent Transparency (v5.1)
 
 ### Conversational Companion
 {{INCLUDE:agent-protocols/supportive-companion.md}}

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

@@ -117,7 +117,7 @@ Implementation: BLOCKED - I will extract requirements, not implement them
    - **Success Criteria** [confidence]: How will success be measured?
    - **Context** [confidence]: Any important background or constraints?
 
-   **Calculate Extraction Confidence (v4.4):**
+   **Calculate Extraction Confidence:**
    - Start with 50% base (conversational content detected)
    - Add 20% if concrete requirements extracted
    - Add 15% if clear goals identified
@@ -177,7 +177,7 @@ Implementation: BLOCKED - I will extract requirements, not implement them
    - [Edge case 1 and how it should be handled]
    - [Open question 1 - needs clarification]
 
-   ## Implicit Requirements (v4.4)
+   ## Implicit Requirements
    *Inferred from conversation context - please verify:*
    - [Category] [Requirement inferred from discussion]
    - [Category] [Another requirement]
@@ -371,7 +371,7 @@ Implementation: BLOCKED - I will extract requirements, not implement them
 
 ---
 
-## Agent Transparency (v4.9)
+## Agent Transparency (v5.1)
 
 ### How to Explain Improvements
 {{INCLUDE:sections/improvement-explanations.md}}

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

@@ -69,8 +69,8 @@ Me:     "Here's what I found:
 **Step 1: I find your work**
 
 I'll look for the prompt you implemented. Usually this is automatic:
-- If you just ran `/clavix:execute`, I know which prompt that was
-- I'll find the checklist from the deep/fast mode output
+- If you just ran `/clavix:implement`, I know which prompt that was
+- I'll find the checklist from the improve mode output
 
 **Step 2: I run automated checks**
 
@@ -352,17 +352,17 @@ I generate different checklists based on what you're building:
 
 ---
 
-## Reference: Verification Commands
+## Reference: Verification Operations
 
-**I run these automatically - you don't need to type them:**
+**I perform these operations using my native tools:**
 
-| What I Run | When |
-|------------|------|
-| `clavix verify --latest` | Check most recent implementation |
-| `clavix verify --id <id>` | Check specific prompt |
-| `clavix verify --retry-failed` | Re-check only failed items |
-| `clavix verify --status` | Show current verification state |
-| `clavix verify --export markdown` | Generate report file |
+| Operation | How I Do It |
+|-----------|-------------|
+| Check most recent implementation | Read `.clavix/outputs/prompts/` directory, find newest file |
+| Check specific prompt | Read the specific `.clavix/outputs/prompts/<id>.md` file |
+| Run automated checks | Execute `npm test`, `npm run build`, `npm run lint` via Bash tool |
+| Update verification status | Edit the prompt file metadata with verification results |
+| Generate report | Create verification report in `.clavix/outputs/` |
 
 ---
 
@@ -372,7 +372,7 @@ I generate different checklists based on what you're building:
 
 **How you got here:**
 1. `/clavix:improve` → Optimized your prompt
-2. `/clavix:execute` → Implemented the requirements
+2. `/clavix:implement` → Implemented the requirements
 3. **`/clavix:verify`** → Now checking it works (you are here)
 
 **What's next:**
@@ -380,13 +380,13 @@ I generate different checklists based on what you're building:
 - All passed → `/clavix:archive` to wrap up
 
 **Related commands:**
-- `/clavix:execute` - Run the implementation (previous step)
+- `/clavix:implement` - Execute tasks or prompts (previous step)
 - `/clavix:improve --comprehensive` - Get comprehensive checklist next time
 - `/clavix:archive` - Archive when done (next step)
 
 ---
 
-## Agent Transparency (v4.9)
+## Agent Transparency (v5.1)
 
 ### CLI Reference (Commands I Execute)
 {{INCLUDE:agent-protocols/cli-reference.md}}

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

@@ -66,14 +66,14 @@ IF escalation_score < 45:
 
 ```
 AFTER implementing task:
-  → RUN: clavix task-complete {task-id}
-  → NEVER manually edit tasks.md checkboxes
+  → EDIT tasks.md: Change - [ ] to - [x] for completed task
+  → Use Edit tool to update the checkbox
 
-IF task-complete succeeds:
+IF edit succeeds:
   → SHOW: Next task automatically
   → CONTINUE with next task
 
-IF task-complete fails:
+IF edit fails:
   → SHOW error to user
   → ASK: "Task completion failed: [error]. How to proceed?"
 ```
@@ -92,7 +92,7 @@ BEFORE starting /clavix:implement:
     → SAY: "All tasks complete. Consider /clavix:archive"
 
   IF not exists:
-    → RUN: clavix implement (to initialize)
+    → CREATE config file and start implementation
 ```
 
 ### Rule 6: File Operations
@@ -158,7 +158,6 @@ IF any verification fails:
 
 AFTER optimization complete:
   → MUST save prompt to .clavix/outputs/prompts/
-  → MUST update index file
   → SHOW: "✓ Prompt saved: [filename]"
 ```
 

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

@@ -19,10 +19,10 @@ Read: .clavix/outputs/{project}/.clavix-implement-config.json
 |-----------|-------|-------------|
 | Config missing, no PRD files | `NO_PROJECT` | Run /clavix:prd |
 | PRD exists, no tasks.md | `PRD_EXISTS` | Run /clavix:plan |
-| tasks.md exists, no config | `TASKS_EXIST` | Run clavix implement |
+| tasks.md exists, no config | `TASKS_EXIST` | Run /clavix:implement |
 | config.stats.remaining > 0 | `IMPLEMENTING` | Continue from currentTask |
 | config.stats.remaining == 0 | `ALL_COMPLETE` | Suggest /clavix:archive |
-| Project in archive/ directory | `ARCHIVED` | Use --restore to reactivate |
+| Project in archive/ directory | `ARCHIVED` | Move back from archive to restore |
 
 **Step 3: State assertion**
 Always output current state when starting a workflow:
@@ -54,22 +54,20 @@ NO_PROJECT:
 
 PRD_EXISTS:
   → /clavix:plan creates TASKS_EXIST
-  → clavix plan command creates TASKS_EXIST
 
 TASKS_EXIST:
-  → clavix implement initializes config → IMPLEMENTING
   → /clavix:implement starts tasks → IMPLEMENTING
 
 IMPLEMENTING:
-  → clavix task-complete reduces remaining
+  → Agent edits tasks.md (- [ ] → - [x]) reduces remaining
   → When remaining == 0 → ALL_COMPLETE
 
 ALL_COMPLETE:
-  → clavix archive moves to archive/ → ARCHIVED
+  → /clavix:archive moves to archive/ → ARCHIVED
   → Adding new tasks → back to IMPLEMENTING
 
 ARCHIVED:
-  → clavix archive --restore → back to previous state
+  → Agent moves project back from archive/ → back to previous state
 ```
 
 ### Prompt Lifecycle States (Separate from PRD)