clavix 5.8.2 → 5.9.0

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

@@ -274,7 +274,7 @@ Result: Project permanently deleted
 
 ---
 
-## Agent Transparency (v5.8.2)
+## Agent Transparency (v5.9.0)
 
 ### Agent Manual (Universal Protocols)
 {{INCLUDE:agent-protocols/AGENT_MANUAL.md}}

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

@@ -524,7 +524,7 @@ I'll explain what's wrong and what you might need to do:
 
 ---
 
-## Agent Transparency (v5.8.2)
+## Agent Transparency (v5.9.0)
 
 ### Agent Manual (Universal Protocols)
 {{INCLUDE:agent-protocols/AGENT_MANUAL.md}}

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

@@ -524,7 +524,7 @@ Wait for the user to decide what to do next.
 
 ---
 
-## Agent Transparency (v5.8.2)
+## Agent Transparency (v5.9.0)
 
 ### Agent Manual (Universal Protocols)
 {{INCLUDE:agent-protocols/AGENT_MANUAL.md}}

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

@@ -107,30 +107,37 @@ Implementation: BLOCKED - I will create the plan, not the code
    - Check `.clavix/outputs/<project-name>/` for `full-prd.md`, `quick-prd.md`, etc.
    - If missing, check legacy `.clavix/outputs/summarize/`.
 2. **Read PRD**: Ingest the requirements.
+3. **Extract Architecture**: Look for the "Architecture & Design" section. Note any specific patterns (e.g., Clean Architecture, Feature-Sliced Design) or structural decisions.
 
 #### **Phase 3: Task Generation**
-1. **Synthesize**: Combine [PRD Requirements] + [Codebase Patterns].
-2. **Draft Tasks**: Create tasks that specify *exactly* what to change in the code.
-3. **Create `tasks.md`**: Use the format in "Task Format Reference".
-4. **Save to**: `.clavix/outputs/[project-name]/tasks.md`.
+1. **Synthesize**: Combine [PRD Requirements] + [Codebase Patterns] + [Architecture Decisions].
+2. **Prioritize Structure**: Ensure initial tasks cover any necessary architectural setup (e.g., creating folders for new layers, setting up base classes).
+3. **Draft Tasks**: Create tasks that specify *exactly* what to change in the code.
+4. **Create `tasks.md`**: Use the format in "Task Format Reference".
+5. **Save to**: `.clavix/outputs/[project-name]/tasks.md`.
 
 ### Part B: Behavioral Guidance (Technical Specificity)
 
 **Your goal is "Low-Level Engineering Plans", not "High-Level Management Plans".**
 
-1. **Specific File Paths**:
+1. **Architecture First**:
+   - If the PRD specifies a pattern (e.g., Repository), the first tasks MUST set up that structure.
+   - **Bad**: "Implement user feature."
+   - **Good**: "Create `src/repositories/UserRepository.ts` interface first, then implementation."
+
+2. **Specific File Paths**:
    - **Bad**: "Create a user profile component."
    - **Good**: "Create `src/components/user/UserProfile.tsx`. Export as default."
 
-2. **Technical Constraints**:
+3. **Technical Constraints**:
    - **Bad**: "Add validation."
    - **Good**: "Use `zod` schema in `src/schemas/user.ts`. Integrate with `react-hook-form`."
 
-3. **Respect Existing Architecture**:
+4. **Respect Existing Architecture**:
    - If the project uses a `services/` folder for API calls, do **not** put `fetch` calls directly in components.
    - If the project uses `shadcn/ui`, instruct to use those primitives, not raw HTML.
 
-4. **Granularity**:
+5. **Granularity**:
    - Each task should be a single logical unit of work (approx. 20-40 mins).
    - Separate "Backend API" from "Frontend UI" tasks.
    - Separate "Type Definition" from "Implementation" if complex.
@@ -150,6 +157,7 @@ Implementation: BLOCKED - I will create the plan, not the code
 
 ## Technical Context & Standards
 *Detected Stack & Patterns*
+- **Architecture**: {e.g., Feature-Sliced Design, Monolith}
 - **Framework**: {e.g., Next.js 14 App Router}
 - **Styling**: {e.g., Tailwind CSS + shadcn/ui}
 - **State**: {e.g., Zustand (stores in /src/store)}
@@ -221,7 +229,7 @@ Present the plan and ask:
 
 ---
 
-## Agent Transparency (v5.8.2)
+## Agent Transparency (v5.9.0)
 
 ### Agent Manual (Universal Protocols)
 {{INCLUDE:agent-protocols/AGENT_MANUAL.md}}

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

@@ -125,6 +125,11 @@ Both documents are automatically validated for quality (Clarity, Structure, Comp
      - "Are there performance requirements (load time, concurrent users)?"
    - **If "I don't know"**: Suggest common stacks based on project type or skip
 
+   **Question 3.5**: Any specific architectural patterns or design choices?
+
+   - **Optional**
+   - **Prompt**: "Do you have preferences for folder structure, design patterns (e.g., Repository, Adapter), or architectural style (Monolith vs Microservices)?"
+
    **Question 4**: What is explicitly OUT of scope? (What are we NOT building?)
 
    - **Validation**: At least 1 explicit exclusion
@@ -136,7 +141,7 @@ Both documents are automatically validated for quality (Clarity, Structure, Comp
 
    **Question 5**: Any additional context or requirements?
 
-   - **Optional**: Press Enter to skip
+   - **Optional**
    - **Helpful areas**: Compliance needs, accessibility, localization, deadlines, team constraints
 
 2. **Before proceeding to document generation**, verify minimum viable answers:
@@ -161,6 +166,9 @@ Both documents are automatically validated for quality (Clarity, Structure, Comp
    ### Technical Requirements
    [User's answer to Q3, detailed]
 
+   ### Architecture & Design
+   [User's answer to Q3.5 if provided]
+
    ## Out of Scope
    [User's answer to Q4]
 
@@ -346,7 +354,7 @@ The validation ensures generated PRDs are immediately usable for AI consumption
 
 ---
 
-## Agent Transparency (v5.8.2)
+## Agent Transparency (v5.9.0)
 
 ### Agent Manual (Universal Protocols)
 {{INCLUDE:agent-protocols/AGENT_MANUAL.md}}

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

@@ -415,7 +415,7 @@ I'll update the PRD and add this to the refinement history. Confirm?
 
 ---
 
-## Agent Transparency (v5.8.2)
+## Agent Transparency (v5.9.0)
 
 ### Agent Manual (Universal Protocols)
 {{INCLUDE:agent-protocols/AGENT_MANUAL.md}}

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

@@ -98,6 +98,7 @@ Implementation: BLOCKED - I will ask questions and explore needs, not implement
 2. As the user describes their needs:
    - Ask clarifying questions about unclear points
    - Probe for technical constraints
+   - Probe for architectural preferences (e.g., 'Do you need a specific structure like Clean Architecture, Microservices, or Feature-Sliced Design?')
    - Explore edge cases and requirements
    - Help them think through user needs
    - Identify potential challenges
@@ -117,6 +118,7 @@ Implementation: BLOCKED - I will ask questions and explore needs, not implement
    - Target users
    - Core features
    - Technical requirements
+   - Architecture & Design
    - Success criteria
    - Constraints and scope
 
@@ -228,7 +230,7 @@ The goal is natural exploration of requirements, not a rigid questionnaire. Foll
 
 ---
 
-## Agent Transparency (v5.8.2)
+## Agent Transparency (v5.9.0)
 
 ### Agent Manual (Universal Protocols)
 {{INCLUDE:agent-protocols/AGENT_MANUAL.md}}

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

@@ -115,6 +115,7 @@ Implementation: BLOCKED - I will extract requirements, not implement them
    - **Problem/Goal** [confidence]: What is the user trying to build or solve?
    - **Key Requirements** [confidence per requirement]: What features and functionality were discussed?
    - **Technical Constraints** [confidence]: Any technologies, integrations, or performance needs?
+   - **Architecture & Design** [confidence]: Any specific patterns, structures, or design choices?
    - **User Needs** [confidence]: Who are the end users and what do they need?
    - **Success Criteria** [confidence]: How will success be measured?
    - **Context** [confidence]: Any important background or constraints?
@@ -197,6 +198,11 @@ Implementation: BLOCKED - I will extract requirements, not implement them
    - **Integrations:** [External systems]
    - **Other:** [Any other technical constraints]
 
+   ## Architecture & Design
+   - **Pattern:** [e.g. Monolith, Microservices, Serverless]
+   - **Structure:** [e.g. Feature-based, Layered, Clean Architecture]
+   - **Key Decisions:** [Specific design choices made]
+
    ## User Context
    **Target Users:** [Who will use this?]
    **Primary Use Case:** [Main problem being solved]
@@ -403,7 +409,7 @@ The `/clavix:summarize` command extracts requirements from exploratory conversat
 
 ---
 
-## Agent Transparency (v5.8.2)
+## Agent Transparency (v5.9.0)
 
 ### Agent Manual (Universal Protocols)
 {{INCLUDE:agent-protocols/AGENT_MANUAL.md}}

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

@@ -123,7 +123,7 @@ Implementation: BLOCKED - I'll analyze and report, not modify or fix
 
 ----
 
-## Agent Transparency (v5.8.2)
+## Agent Transparency (v5.9.0)
 
 ### Agent Manual (Universal Protocols)
 {{INCLUDE:agent-protocols/AGENT_MANUAL.md}}

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "clavix",
-  "version": "5.8.2",
+  "version": "5.9.0",
   "description": "Agentic-first prompt workflows. Markdown templates that teach AI agents how to optimize prompts, create PRDs, and manage implementation.\n\nSLASH COMMANDS (in your AI assistant):\n  /clavix:improve    Optimize prompts with auto-depth\n  /clavix:prd        Generate PRD through questions\n  /clavix:plan       Create task breakdown from PRD\n  /clavix:implement  Execute tasks with progress tracking\n  /clavix:start      Begin conversational session\n  /clavix:summarize  Extract requirements from conversation\n  /clavix:refine     Refine existing PRD or prompt\n  /clavix:verify     Verify implementation against requirements\n  /clavix:archive    Archive completed projects\n\nWorks with Claude Code, Cursor, Windsurf, and 20 AI coding tools.",
   "type": "module",
   "main": "dist/index.js",