clavix 5.0.0 → 5.1.0

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

@@ -4,7 +4,7 @@ These instructions enhance GitHub Copilot's understanding of Clavix prompt optim
 
 ---
 
-## ⛔ CLAVIX MODE ENFORCEMENT (v4.7)
+## ⛔ CLAVIX MODE ENFORCEMENT
 
 **CRITICAL: Know which mode you're in and STOP at the right point.**
 
@@ -12,7 +12,7 @@ These instructions enhance GitHub Copilot's understanding of Clavix prompt optim
 - 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"
+- ✅ After showing optimized prompt, tell user: "Run `/clavix:implement --latest` to implement"
 
 **PLANNING workflows** (NO CODE ALLOWED):
 - Conversational mode, requirement extraction, PRD generation
@@ -38,8 +38,7 @@ For complete step-by-step workflows, see `.clavix/instructions/`:
 |----------|-----------------|---------|
 | **Conversational Mode** | `workflows/start.md` | Natural requirements gathering through discussion |
 | **Extract Requirements** | `workflows/summarize.md` | Analyze conversation → mini-PRD + optimized prompts |
-| **Quick Optimization** | `workflows/fast.md` | Intent detection + quality assessment + smart triage |
-| **Deep Analysis** | `workflows/deep.md` | Comprehensive with alternatives, validation, edge cases |
+| **Prompt Optimization** | `workflows/improve.md` | Intent detection + quality assessment + auto-depth selection |
 | **PRD Generation** | `workflows/prd.md` | Socratic questions → full PRD + quick PRD |
 | **Mode Boundaries** | `core/clavix-mode.md` | Planning vs implementation distinction |
 
@@ -54,33 +53,39 @@ For complete step-by-step workflows, see `.clavix/instructions/`:
 
 ---
 
-## 📋 CLI Quick Reference
+## 📋 Clavix Commands (v5)
 
+### Setup Commands (CLI)
 | Command | Purpose |
 |---------|---------|
-| `clavix fast "<prompt>"` | Quick optimization (CLI auto-saves; slash commands require manual saving per template instructions) |
-| `clavix deep "<prompt>"` | Deep analysis (CLI auto-saves; slash commands require manual saving per template instructions) |
-| `clavix execute [--latest]` | Execute saved prompts (--latest, --fast, --deep, --id supported) |
-| `clavix prompts list` | View saved prompts with status (NEW, EXECUTED, OLD, STALE) |
-| `clavix prompts clear` | Manage cleanup (--executed, --stale, --fast, --deep, --all, --force) |
-| `clavix prd` | Guided PRD generation |
-| `clavix plan` | Transform PRD → tasks |
-| `clavix implement [--commit-strategy]` | Execute tasks |
-| `clavix start` | Begin conversational session |
-| `clavix summarize [session-id]` | Extract PRD from session |
-| `clavix list` | List sessions/outputs |
-| `clavix archive [project]` | Archive/restore projects |
-| `clavix update` | Refresh documentation |
+| `clavix init` | Initialize Clavix in a project |
+| `clavix update` | Update templates after package update |
+| `clavix config` | Manage configuration |
+| `clavix version` | Show version |
+
+### Workflow Commands (Slash Commands)
+All workflows are executed via slash commands:
+
+| Slash Command | Purpose |
+|---------------|---------|
+| `/clavix:improve` | Optimize prompts (auto-selects depth) |
+| `/clavix:prd` | Generate PRD through guided questions |
+| `/clavix:plan` | Create task breakdown from PRD |
+| `/clavix:implement` | Execute tasks or prompts (auto-detects source) |
+| `/clavix:start` | Begin conversational session |
+| `/clavix:summarize` | Extract requirements from conversation |
+| `/clavix:verify` | Verify implementation |
+| `/clavix:archive` | Archive completed projects |
 
 ---
 
-## 🔄 Prompt Lifecycle Management (v2.7+)
+## 🔄 Prompt Lifecycle Workflow
 
-**Prompt Lifecycle Workflow:**
-1. **Optimize**: `clavix fast/deep "<prompt>"` → CLI auto-saves; slash commands require manual saving per template instructions
-2. **Review**: `clavix prompts list` → View all saved prompts with status
-3. **Execute**: `clavix execute --latest` → Implement when ready
-4. **Cleanup**: `clavix prompts clear --executed` → Remove completed prompts
+**Prompt Lifecycle:**
+1. **Optimize**: `/clavix:improve` → Analyzes and improves your prompt
+2. **Review**: Agent reads `.clavix/outputs/prompts/*.md` to list saved prompts
+3. **Execute**: `/clavix:implement --latest` → Implement when ready
+4. **Cleanup**: Agent deletes old prompt files from `.clavix/outputs/prompts/`
 
 ---
 
@@ -94,10 +99,10 @@ PRD Creation → Task Planning → Implementation → Archive
 
 **Detailed steps:**
 
-1. **Planning Phase** - User creates PRD (conversational or direct)
-2. **Task Preparation** - `clavix plan` transforms PRD into tasks.md
-3. **Implementation Phase** - `clavix implement` executes tasks systematically
-4. **Completion** - `clavix archive` archives completed work
+1. **Planning Phase** - `/clavix:prd` or `/clavix:start` → `/clavix:summarize`
+2. **Task Preparation** - `/clavix:plan` transforms PRD into tasks.md
+3. **Implementation Phase** - `/clavix:implement` executes tasks systematically
+4. **Completion** - `/clavix:archive` archives completed work
 
 **Key principle:** Planning workflows create documents. Implementation workflows write code.
 
@@ -113,17 +118,17 @@ When analyzing prompts, consider these 5 dimensions:
 - **Completeness**: All specs provided (persona, format, tone, success criteria)?
 - **Actionability**: Can AI take immediate action?
 
-**Reference:** See `workflows/fast.md` for complete quality assessment patterns
+**Reference:** See `workflows/improve.md` for complete quality assessment patterns
 
 ---
 
 ## 💡 Best Practices for GitHub Copilot
 
-1. **Suggest appropriate workflow** - Fast for simple prompts, deep for complex, PRD for strategic
+1. **Suggest appropriate workflow** - `/clavix:improve` for prompts, `/clavix:prd` for strategic planning
 2. **Reference instruction files** - Point to `.clavix/instructions/workflows/*.md` instead of recreating steps
 3. **Respect mode boundaries** - Planning mode = no code, Implementation mode = write code
 4. **Use quality dimensions** - Apply 5-dimension assessment principles in responses
-5. **Guide users to CLI** - Recommend appropriate `clavix` commands for their needs
+5. **Guide users to slash commands** - Recommend appropriate `/clavix:*` commands for their needs
 
 ---
 
@@ -132,17 +137,17 @@ When analyzing prompts, consider these 5 dimensions:
 ### ❌ Jumping to implementation during planning
 **Wrong:** User discusses feature → Copilot generates code immediately
 
-**Right:** User discusses feature → Suggest `clavix prd` or `clavix start` → Create planning docs first
+**Right:** User discusses feature → Suggest `/clavix:prd` or `/clavix:start` → Create planning docs first
 
 ### ❌ Not suggesting Clavix workflows
 **Wrong:** User asks "How should I phrase this?" → Copilot provides generic advice
 
-**Right:** User asks "How should I phrase this?" → Suggest `clavix fast "<prompt>"` for quality assessment
+**Right:** User asks "How should I phrase this?" → Suggest `/clavix:improve` for quality assessment
 
 ### ❌ Recreating workflow steps inline
 **Wrong:** Copilot explains entire PRD generation process in chat
 
-**Right:** Copilot references `.clavix/instructions/workflows/prd.md` and suggests running `clavix prd`
+**Right:** Copilot references `.clavix/instructions/workflows/prd.md` and suggests running `/clavix:prd`
 
 ---
 
@@ -151,7 +156,7 @@ When analyzing prompts, consider these 5 dimensions:
 When users ask for help with prompts or requirements:
 
 1. **Detect need** - Identify if user needs planning, optimization, or implementation
-2. **Suggest command** - Recommend appropriate `clavix` command
+2. **Suggest slash command** - Recommend appropriate `/clavix:*` command
 3. **Explain benefit** - Describe expected output and value
 4. **Help interpret** - Assist with understanding Clavix-generated outputs
 5. **Apply principles** - Use quality dimensions in your responses
@@ -159,10 +164,10 @@ When users ask for help with prompts or requirements:
 **Example flow:**
 ```
 User: "I want to build a dashboard but I'm not sure how to phrase the requirements"
-Copilot: "I suggest running `clavix start` to begin conversational requirements gathering.
+Copilot: "I suggest running `/clavix:start` to begin conversational requirements gathering.
 This will help us explore your needs naturally, then we can extract structured requirements
-with `clavix summarize`. Alternatively, if you have a rough idea, try:
-clavix fast 'Build a dashboard for...' for quick optimization."
+with `/clavix:summarize`. Alternatively, if you have a rough idea, try:
+`/clavix:improve 'Build a dashboard for...'` for quick optimization."
 ```
 
 ---

package/dist/templates/agents/octo.md

@@ -4,7 +4,7 @@ Clavix workflows optimized for Octofriend's capabilities: model switching, multi
 
 ---
 
-## ⛔ CLAVIX MODE ENFORCEMENT (v4.11)
+## ⛔ CLAVIX MODE ENFORCEMENT
 
 **CRITICAL: Know which mode you're in and STOP at the right point.**
 
@@ -12,7 +12,7 @@ Clavix workflows optimized for Octofriend's capabilities: model switching, multi
 - `/clavix:improve` - Prompt optimization with smart depth auto-selection
 - 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"
+- ✅ After showing optimized prompt, tell user: "Run `/clavix:implement --latest` to implement"
 
 **PLANNING workflows** (NO CODE ALLOWED):
 - `/clavix:start`, `/clavix:summarize`, `/clavix:prd`, `/clavix:plan`
@@ -20,9 +20,10 @@ Clavix workflows optimized for Octofriend's capabilities: model switching, multi
 - ❌ DO NOT implement features during these workflows
 
 **IMPLEMENTATION workflows** (CODE ALLOWED):
-- `/clavix:implement`, `/clavix:execute`, `clavix task-complete`
+- `/clavix:implement`
 - Your role: Write code, execute tasks, implement features
 - ✅ DO implement code during these workflows
+- Mark task completion by editing tasks.md directly (`- [ ]` → `- [x]`)
 
 See `.clavix/instructions/core/clavix-mode.md` for complete mode documentation.
 
@@ -115,35 +116,39 @@ Autofix handles edge cases gracefully - let it work.
 
 ---
 
-## 📋 CLI Quick Reference
-
-| Command | Purpose | Output |
-|---------|---------|--------|
-| `clavix init` | Setup Clavix in project | `.clavix/config.json` |
-| `clavix prd` | Generate PRD through questions | `full-prd.md` + `quick-prd.md` |
-| `clavix fast "<prompt>"` | Quick prompt improvement (CLI auto-saves prompts; Slash commands require manual saving per template instructions) | Saved to `.clavix/outputs/prompts/fast/` |
-| `clavix deep "<prompt>"` | Comprehensive analysis (CLI auto-saves prompts; Slash commands require manual saving per template instructions) | Saved to `.clavix/outputs/prompts/deep/` |
-| `clavix execute [--latest]` | Execute prompt (interactive or --latest for most recent) | Implementation |
-| `clavix prompts list` | View all saved prompts with status | NEW, EXECUTED, OLD, STALE |
-| `clavix prompts clear` | Manage cleanup (--executed, --stale, --fast, --deep, --all) | Cleanup report |
-| `clavix start` | Conversational requirements | Session captured |
-| `clavix summarize` | Extract from conversation | `mini-prd.md` + prompts |
-| `clavix plan` | Generate tasks from PRD | `tasks.md` |
-| `clavix implement` | Execute tasks | Implementation + commits |
-| `clavix list` | Show sessions/outputs | List view |
-| `clavix update` | Refresh documentation | Updates managed files |
+## 📋 Clavix Commands (v5)
+
+### Setup Commands (CLI)
+| Command | Purpose |
+|---------|---------|
+| `clavix init` | Initialize Clavix in a project |
+| `clavix update` | Update templates after package update |
+| `clavix config` | Manage configuration |
+| `clavix version` | Show version |
+
+### Workflow Commands (Slash Commands)
+| Slash Command | Purpose |
+|---------------|---------|
+| `/clavix:improve` | Optimize prompts (auto-selects depth) |
+| `/clavix:prd` | Generate PRD through questions |
+| `/clavix:plan` | Create task breakdown from PRD |
+| `/clavix:implement` | Execute tasks or prompts (auto-detects source) |
+| `/clavix:start` | Begin conversational session |
+| `/clavix:summarize` | Extract requirements from conversation |
+| `/clavix:verify` | Verify implementation |
+| `/clavix:archive` | Archive completed projects |
 
 ---
 
 ## 🔄 Prompt Execution Workflow
 
-**When you have a saved prompt to execute prompt:**
+**When you have a saved prompt to execute:**
 
-1. **List available prompts**: `clavix prompts list` - See all saved prompts with status
-2. **execute prompt**: `clavix execute --latest` - implement saved prompt interactively
-3. **implement saved prompt**: Agent executes the optimized prompt and implements the feature
+1. **List available prompts**: List files in `.clavix/outputs/prompts/*.md`
+2. **Execute prompt**: `/clavix:implement --latest` - implement saved prompt
+3. **Implement**: Agent reads the optimized prompt and implements the feature
 
-**Note:** CLI auto-saves prompts from fast/deep commands. Slash commands require manual saving per template instructions.
+**Note:** Slash commands save prompts as `.md` files with frontmatter metadata.
 
 ---
 
@@ -151,26 +156,25 @@ Autofix handles edge cases gracefully - let it work.
 
 **Complete project flow:**
 
-1. **Planning** (`clavix prd`)
+1. **Planning** (`/clavix:prd`)
    - Creates PRD (full + quick versions)
    - Saves to `.clavix/outputs/{project}/`
 
-2. **Task Preparation** (`clavix plan`)
+2. **Task Preparation** (`/clavix:plan`)
    - Transforms PRD → curated tasks.md
    - Phase-based organization
 
-3. **Implementation** (`clavix implement`)
+3. **Implementation** (`/clavix:implement`)
    - Agent executes tasks systematically
-   - Uses `clavix task-complete` for progress
+   - Marks progress by editing tasks.md (`- [ ]` → `- [x]`)
    - Optional git commit strategies
 
-4. **Completion** (`clavix archive`)
+4. **Completion** (`/clavix:archive`)
    - Archives completed project
 
 **Alternative quick paths:**
-- **Quick improvement**: `clavix fast` → `clavix execute` → Done
-- **Deep analysis**: `clavix deep` → `clavix execute` → Done
-- **Conversational**: `clavix start` → `clavix summarize` → `clavix execute` → Done
+- **Quick improvement**: `/clavix:improve` → `/clavix:implement --latest` → Done
+- **Conversational**: `/clavix:start` → `/clavix:summarize` → `/clavix:implement` → Done
 
 ---
 
@@ -189,9 +193,9 @@ Autofix handles edge cases gracefully - let it work.
 ## ⚠️ Common Mistakes
 
 ### ❌ Implementing during planning workflows
-**Wrong:** User runs `clavix prd`, you generate PRD then start building features
+**Wrong:** User runs `/clavix:prd`, you generate PRD then start building features
 
-**Right:** User runs `clavix prd`, you generate PRD, save files, suggest `clavix plan` as next step
+**Right:** User runs `/clavix:prd`, you generate PRD, save files, suggest `/clavix:plan` as next step
 
 ### ❌ Skipping file creation
 **Wrong:** Display optimized prompt, stop there
@@ -201,7 +205,7 @@ Autofix handles edge cases gracefully - let it work.
 ### ❌ Not referencing instruction files
 **Wrong:** Trying to remember workflow details from this file
 
-**Right:** "See `.clavix/instructions/workflows/fast.md` for complete workflow"
+**Right:** "See `.clavix/instructions/workflows/improve.md` for complete workflow"
 
 ### ❌ Using wrong model for task
 **Wrong:** Using fast model for complex architectural planning
@@ -212,9 +216,9 @@ Autofix handles edge cases gracefully - let it work.
 
 ## 🆘 When in Doubt
 
-1. **Check which command was run** - Determines your mode (planning vs implementation)
+1. **Check which slash command was run** - Determines your mode (planning vs implementation)
 2. **Reference instruction files** - They have complete step-by-step guidance
-3. **Ask the user** - "Should I implement this (run `clavix implement`), or continue planning?"
+3. **Ask the user** - "Should I implement this (run `/clavix:implement`), or continue planning?"
 4. **Switch models** - Use thinking models for complex planning tasks
 
 ---

package/dist/templates/agents/warp.md

@@ -4,7 +4,7 @@ Clavix helps Warp developers turn rough ideas into quality, AI-ready prompts and
 
 ---
 
-### ⛔ CLAVIX MODE ENFORCEMENT (v4.7)
+### ⛔ CLAVIX MODE ENFORCEMENT
 
 **CRITICAL: Know which mode you're in and STOP at the right point.**
 
@@ -12,7 +12,7 @@ Clavix helps Warp developers turn rough ideas into quality, AI-ready prompts and
 - 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"
+- ✅ After showing optimized prompt, tell user: "Run `/clavix:implement --latest` to implement"
 
 **PLANNING workflows** (NO CODE ALLOWED):
 - Conversational mode, requirement extraction, PRD generation
@@ -33,8 +33,7 @@ See `.clavix/instructions/core/clavix-mode.md` for complete mode documentation.
 For complete step-by-step workflows, see `.clavix/instructions/`:
 - `.clavix/instructions/workflows/start.md` - Conversational mode
 - `.clavix/instructions/workflows/summarize.md` - Extract requirements
-- `.clavix/instructions/workflows/fast.md` - Quick prompt optimization
-- `.clavix/instructions/workflows/deep.md` - Comprehensive analysis
+- `.clavix/instructions/workflows/improve.md` - Prompt optimization (auto-depth)
 - `.clavix/instructions/workflows/prd.md` - PRD generation
 - `.clavix/instructions/troubleshooting/` - Common issues
 
@@ -47,25 +46,25 @@ For complete step-by-step workflows, see `.clavix/instructions/`:
 - Or run ad hoc: `npx clavix@latest init`
 - Verify setup: `clavix version`
 
-### Common commands
-- `clavix init` – interactive integration setup (regenerates docs & commands)
-- `clavix fast "<prompt>"` – quick quality assessment (5 dimensions) and improved prompt. CLI auto-saves; slash commands need manual saving per template instructions.
-- `clavix deep "<prompt>"` – comprehensive analysis with alternatives, edge cases, and validation checklists. CLI auto-saves; slash commands need manual saving per template instructions.
-- `clavix execute [--latest]` – execute saved prompts from fast/deep. Interactive selection or `--latest` for most recent.
-- `clavix prompts list` – view all saved prompts with age/status (NEW, EXECUTED, OLD, STALE)
-- `clavix prompts clear [--executed|--stale|--fast|--deep]` – cleanup executed or old prompts
-- `clavix prd` – answer focused questions to create full/quick PRDs
-- `clavix plan` – transform PRDs or sessions into task lists
-- `clavix implement [--commit-strategy=<type>]` – execute tasks (git: per-task, per-5-tasks, per-phase, none [default])
-- `clavix task-complete <taskId>` – mark task completed with validation and optional git commit
-- `clavix start` – capture requirement conversations in Warp
-- `clavix summarize [session-id]` – extract mini PRDs and optimized prompts
-- `clavix list` – list sessions/outputs (`--sessions`, `--outputs`, `--archived`)
-- `clavix show [session-id]` – inspect sessions or use `--output <project>`
-- `clavix archive [project]` – archive projects (or `--restore` to bring them back)
-- `clavix config get|set|edit|reset` – manage `.clavix/config.json`
-- `clavix update` – refresh documentation/commands (`--docs-only`, `--commands-only`)
-- `clavix version` – print installed CLI version
+### CLI Commands (v5)
+| Command | Purpose |
+|---------|---------|
+| `clavix init` | Initialize Clavix in a project |
+| `clavix update` | Update templates after package update |
+| `clavix config` | Manage configuration |
+| `clavix version` | Show version |
+
+### Slash Commands (Workflows)
+| Slash Command | Purpose |
+|---------------|---------|
+| `/clavix:improve` | Optimize prompts (auto-selects depth) |
+| `/clavix:prd` | Generate PRD through guided questions |
+| `/clavix:plan` | Create task breakdown from PRD |
+| `/clavix:implement` | Execute tasks or prompts (auto-detects source) |
+| `/clavix:start` | Begin conversational session |
+| `/clavix:summarize` | Extract requirements from conversation |
+| `/clavix:verify` | Verify implementation |
+| `/clavix:archive` | Archive completed projects |
 
 ### Outputs
 - Project artifacts live under `.clavix/outputs/<project>/`
@@ -86,14 +85,14 @@ For complete step-by-step workflows, see `.clavix/instructions/`:
 ### ⚠️ Common Mistakes
 
 #### ❌ Jumping to implementation during planning
-**Wrong:** User runs `clavix prd`, you generate PRD then start building features
+**Wrong:** User runs `/clavix:prd`, you generate PRD then start building features
 
-**Right:** User runs `clavix prd`, you generate PRD, save files, suggest `clavix plan` as next step
+**Right:** User runs `/clavix:prd`, you generate PRD, save files, suggest `/clavix:plan` as next step
 
 #### ❌ Not referencing instruction files
 **Wrong:** Trying to remember workflow details from this file
 
-**Right:** "See `.clavix/instructions/workflows/fast.md` for complete workflow"
+**Right:** "See `.clavix/instructions/workflows/improve.md` for complete workflow"
 
 ---
 

package/dist/templates/instructions/README.md

@@ -4,7 +4,7 @@ This directory contains the complete instruction set for AI agents consuming Cla
 
 ---
 
-## 📐 Documentation Architecture (v4.11)
+## 📐 Documentation Architecture
 
 ```
 Canonical Templates (SOURCE OF TRUTH)
@@ -14,8 +14,7 @@ Canonical Templates (SOURCE OF TRUTH)
   ├── start.md            - Conversational mode entry
   ├── summarize.md        - Extract requirements from conversation
   ├── plan.md             - Task breakdown from PRD
-  ├── implement.md        - Execute tasks with progress tracking
-  ├── execute.md          - Run saved prompts
+  ├── implement.md        - Execute tasks or prompts (auto-detection)
   ├── verify.md           - Post-implementation verification
   └── archive.md          - Archive completed projects
     ↓ (referenced by)
@@ -133,16 +132,18 @@ PRD Creation → Task Planning → Implementation → Verification → Archive
 | `/clavix:prd` | Planning | ✗ NO |
 | `/clavix:plan` | Planning | ✗ NO |
 | `/clavix:implement` | Implementation | ✓ YES |
-| `/clavix:execute` | Implementation | ✓ YES |
 | `/clavix:verify` | Verification | Context-dependent |
 | `/clavix:archive` | Management | ✗ NO |
 
-### Agent-Only Commands (No Slash Command)
+### Agent Operations (v5 Agentic-First)
 
-| CLI Command | Purpose | Invoked By |
-|-------------|---------|------------|
-| `clavix analyze` | Internal prompt analysis | `improve` workflow |
-| `clavix task-complete` | Mark task done | `implement` workflow |
+In v5, agents use native tools (Write, Edit, Bash) instead of CLI commands:
+
+| Operation | How Agent Performs It |
+|-----------|----------------------|
+| Save prompt | Use Write tool to create `.clavix/outputs/prompts/<id>.md` |
+| Mark task done | Use Edit tool to change `- [ ]` to `- [x]` in tasks.md |
+| Archive project | Use Bash tool to move directory to archive/ |
 
 ---
 
@@ -174,14 +175,14 @@ PRD Creation → Task Planning → Implementation → Verification → Archive
 
 ### Preventing the "Half-Update" Problem
 
-The v4.11.2 release introduced validation to catch incomplete updates:
+Clavix includes validation to catch incomplete updates:
 
 ```bash
 # Run before committing
 npm run validate:consistency
 
 # Checks performed:
-# - No legacy command references (fast, deep commands removed in v4.11)
+# - No legacy command references (removed deprecated commands)
 # - All CLI commands have templates (if required)
 # - All templates have CLI implementations
 # - No deprecated version references
@@ -240,12 +241,12 @@ npm run validate:consistency
 
 ### "Legacy command references found"
 
-**Root cause:** Template not updated during v4.11 migration
+**Root cause:** Template not updated during migration
 
 **Fix:**
 1. Run `npm run validate:consistency` to find all occurrences
-2. Replace legacy fast/deep commands with `clavix improve`
-3. Replace "fast mode"/"deep mode" with "standard depth"/"comprehensive depth"
+2. Replace legacy commands with current equivalents (e.g., `/clavix:implement`)
+3. Replace deprecated terminology (e.g., "fast mode" → "standard depth")
 4. Update any navigation references
 
 ### "Template doesn't match CLI behavior"
@@ -264,14 +265,14 @@ npm run validate:consistency
 ## 📚 Key Files Reference
 
 ### Canonical Templates (Start Here)
-- `improve.md` - Unified prompt optimization (v4.11)
+- `improve.md` - Unified prompt optimization
 - `prd.md` - PRD generation workflow
-- `implement.md` - Task execution workflow
+- `implement.md` - Task and prompt execution workflow
 
 ### Agent Protocols
-- `_components/agent-protocols/self-correction.md` - Mistake detection
-- `_components/agent-protocols/state-awareness.md` - Workflow state tracking
 - `_components/agent-protocols/decision-rules.md` - Decision logic
+- `_components/agent-protocols/state-awareness.md` - Workflow state tracking
+- `_components/agent-protocols/error-handling.md` - Error recovery patterns
 
 ### Validation
 - `scripts/validate-consistency.ts` - TypeScript ↔ Template validator
@@ -279,6 +280,6 @@ npm run validate:consistency
 
 ---
 
-**Last updated:** v4.11.2 (November 2025)
+**Last updated:** v5.1.0
 
 **Validation:** Run `npm run validate:consistency` before committing changes.

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

@@ -20,7 +20,7 @@ Clavix has **two distinct modes** based on the command type:
 
 ### CLAVIX IMPLEMENTATION MODE (Code Execution)
 
-**Commands:** `/clavix:implement`, `/clavix:execute`, `/clavix:task-complete`
+**Commands:** `/clavix:implement`
 
 **Your role:**
 - Write code and implement features
@@ -44,8 +44,6 @@ Clavix has **two distinct modes** based on the command type:
 | `/clavix:prd` | Planning | ✗ NO |
 | `/clavix:plan` | Planning (Pre-Implementation) | ✗ NO |
 | `/clavix:implement` | Implementation | ✓ YES |
-| `/clavix:execute` | Implementation | ✓ YES |
-| `/clavix:task-complete` | Implementation | ✓ YES |
 
 ---
 
@@ -87,9 +85,9 @@ Clavix has **two distinct modes** based on the command type:
    - Output: `.clavix/outputs/{project}/tasks.md`
 
 3. **Implementation Phase** (`/clavix:implement`)
-   - Agent executes tasks systematically
+   - Agent executes tasks or prompts systematically (auto-detects source)
    - Mode: IMPLEMENTATION
-   - Uses `task-complete` to mark progress
+   - Agent edits tasks.md directly (`- [ ]` → `- [x]`) to mark progress
 
 4. **Completion** (`/clavix:archive`)
    - Archives completed project
@@ -104,7 +102,7 @@ Clavix has **two distinct modes** based on the command type:
 **User says:** "Now implement this" or "Build this feature"
 → **Switch to IMPLEMENTATION MODE** if not already in implementation command
 
-**User runs:** `/clavix:implement` or `/clavix:execute`
+**User runs:** `/clavix:implement`
 → **You are in IMPLEMENTATION MODE** - write code
 
 **User runs:** `/clavix:prd` or `/clavix:improve` or `/clavix:start`
@@ -199,21 +197,7 @@ export function TodoApp() {
 
 ---
 
-### Scenario 4: User Runs Execute Command
-
-**Command:** `/clavix:execute` or `/clavix:execute --latest`
-
-**Your mode:** CLAVIX IMPLEMENTATION MODE
-
-**Actions:**
-- Load saved prompt from fast/deep workflow
-- Implement the feature described in the prompt
-- Write actual code
-- Complete the implementation
-
----
-
-### Scenario 5: Ambiguous Request During Planning
+### Scenario 4: Ambiguous Request During Planning
 
 **User:** "What do you think about adding real-time updates?"
 
@@ -230,14 +214,14 @@ export function TodoApp() {
 
 ---
 
-### Scenario 6: User Gives Direct Implementation Request
+### Scenario 5: User Gives Direct Implementation Request
 
 **User:** "Now implement this feature" or "Build the dashboard we discussed"
 
 **Your mode:** Check context first
 
 **If no `/clavix:implement` command was run:**
-- Suggest: "To implement this, please run `/clavix:implement` or `/clavix:execute`. This ensures proper task tracking and file management."
+- Suggest: "To implement this, please run `/clavix:implement`. This ensures proper task tracking and file management."
 
 **If `/clavix:implement` command was run:**
 - You're already in CLAVIX IMPLEMENTATION MODE
@@ -261,13 +245,14 @@ If you catch yourself implementing during a Clavix workflow:
 
 **Two distinct Clavix modes:**
 
-1. **CLAVIX PLANNING MODE** (`start`, `summarize`, `fast`, `deep`, `prd`, `plan`)
+1. **CLAVIX PLANNING MODE** (`start`, `summarize`, `improve`, `prd`, `plan`)
    - Create PRDs, prompts, documentation
    - DO NOT implement features
 
-2. **CLAVIX IMPLEMENTATION MODE** (`implement`, `execute`, `task-complete`)
+2. **CLAVIX IMPLEMENTATION MODE** (`implement`)
    - Write code and build features
    - DO implement what's been planned
+   - Auto-detects tasks.md or prompts/
 
 **Standard workflow:** PRD → Plan → Implement → Archive