bmad-method 6.0.0-alpha.21 → 6.0.0-alpha.23

package/src/modules/bmm/workflows/2-plan-workflows/prd/data/prd-purpose.md

@@ -0,0 +1,197 @@
+# BMAD PRD Purpose
+
+**The PRD is the top of the required funnel that feeds all subsequent product development work in rhw BMad Method.**
+
+---
+
+## What is a BMAD PRD?
+
+A dual-audience document serving:
+1. **Human Product Managers and builders** - Vision, strategy, stakeholder communication
+2. **LLM Downstream Consumption** - UX Design → Architecture → Epics → Development AI Agents
+
+Each successive document becomes more AI-tailored and granular.
+
+---
+
+## Core Philosophy: Information Density
+
+**High Signal-to-Noise Ratio**
+
+Every sentence must carry information weight. LLMs consume precise, dense content efficiently.
+
+**Anti-Patterns (Eliminate These):**
+- ❌ "The system will allow users to..." → ✅ "Users can..."
+- ❌ "It is important to note that..." → ✅ State the fact directly
+- ❌ "In order to..." → ✅ "To..."
+- ❌ Conversational filler and padding → ✅ Direct, concise statements
+
+**Goal:** Maximum information per word. Zero fluff.
+
+---
+
+## The Traceability Chain
+
+**PRD starts the chain:**
+```
+Vision → Success Criteria → User Journeys → Functional Requirements → (future: User Stories)
+```
+
+**In the PRD, establish:**
+- Vision → Success Criteria alignment
+- Success Criteria → User Journey coverage
+- User Journey → Functional Requirement mapping
+- All requirements traceable to user needs
+
+**Why:** Each downstream artifact (UX, Architecture, Epics, Stories) must trace back to documented user needs and business objectives. This chain ensures we build the right thing.
+
+---
+
+## What Makes Great Functional Requirements?
+
+### FRs are Capabilities, Not Implementation
+
+**Good FR:** "Users can reset their password via email link"
+**Bad FR:** "System sends JWT via email and validates with database" (implementation leakage)
+
+**Good FR:** "Dashboard loads in under 2 seconds for 95th percentile"
+**Bad FR:** "Fast loading time" (subjective, unmeasurable)
+
+### SMART Quality Criteria
+
+**Specific:** Clear, precisely defined capability
+**Measurable:** Quantifiable with test criteria
+**Attainable:** Realistic within constraints
+**Relevant:** Aligns with business objectives
+**Traceable:** Links to source (executive summary or user journey)
+
+### FR Anti-Patterns
+
+**Subjective Adjectives:**
+- ❌ "easy to use", "intuitive", "user-friendly", "fast", "responsive"
+- ✅ Use metrics: "completes task in under 3 clicks", "loads in under 2 seconds"
+
+**Implementation Leakage:**
+- ❌ Technology names, specific libraries, implementation details
+- ✅ Focus on capability and measurable outcomes
+
+**Vague Quantifiers:**
+- ❌ "multiple users", "several options", "various formats"
+- ✅ "up to 100 concurrent users", "3-5 options", "PDF, DOCX, TXT formats"
+
+**Missing Test Criteria:**
+- ❌ "The system shall provide notifications"
+- ✅ "The system shall send email notifications within 30 seconds of trigger event"
+
+---
+
+## What Makes Great Non-Functional Requirements?
+
+### NFRs Must Be Measurable
+
+**Template:**
+```
+"The system shall [metric] [condition] [measurement method]"
+```
+
+**Examples:**
+- ✅ "The system shall respond to API requests in under 200ms for 95th percentile as measured by APM monitoring"
+- ✅ "The system shall maintain 99.9% uptime during business hours as measured by cloud provider SLA"
+- ✅ "The system shall support 10,000 concurrent users as measured by load testing"
+
+### NFR Anti-Patterns
+
+**Unmeasurable Claims:**
+- ❌ "The system shall be scalable" → ✅ "The system shall handle 10x load growth through horizontal scaling"
+- ❌ "High availability required" → ✅ "99.9% uptime as measured by cloud provider SLA"
+
+**Missing Context:**
+- ❌ "Response time under 1 second" → ✅ "API response time under 1 second for 95th percentile under normal load"
+
+---
+
+## Domain-Specific Requirements
+
+**Auto-Detect and Enforce Based on Project Context**
+
+Certain industries have mandatory requirements that must be present:
+
+- **Healthcare:** HIPAA Privacy & Security Rules, PHI encryption, audit logging, MFA
+- **Fintech:** PCI-DSS Level 1, AML/KYC compliance, SOX controls, financial audit trails
+- **GovTech:** NIST framework, Section 508 accessibility (WCAG 2.1 AA), FedRAMP, data residency
+- **E-Commerce:** PCI-DSS for payments, inventory accuracy, tax calculation by jurisdiction
+
+**Why:** Missing these requirements in the PRD means they'll be missed in architecture and implementation, creating expensive rework. During PRD creation there is a step to cover this - during validation we want to make sure it was covered. For this purpose steps will utilize a domain-complexity.csv and project-types.csv.
+
+---
+
+## Document Structure (Markdown, Human-Readable)
+
+### Required Sections
+1. **Executive Summary** - Vision, differentiator, target users
+2. **Success Criteria** - Measurable outcomes (SMART)
+3. **Product Scope** - MVP, Growth, Vision phases
+4. **User Journeys** - Comprehensive coverage
+5. **Domain Requirements** - Industry-specific compliance (if applicable)
+6. **Innovation Analysis** - Competitive differentiation (if applicable)
+7. **Project-Type Requirements** - Platform-specific needs
+8. **Functional Requirements** - Capability contract (FRs)
+9. **Non-Functional Requirements** - Quality attributes (NFRs)
+
+### Formatting for Dual Consumption
+
+**For Humans:**
+- Clear, professional language
+- Logical flow from vision to requirements
+- Easy for stakeholders to review and approve
+
+**For LLMs:**
+- ## Level 2 headers for all main sections (enables extraction)
+- Consistent structure and patterns
+- Precise, testable language
+- High information density
+
+---
+
+## Downstream Impact
+
+**How the PRD Feeds Next Artifacts:**
+
+**UX Design:**
+- User journeys → interaction flows
+- FRs → design requirements
+- Success criteria → UX metrics
+
+**Architecture:**
+- FRs → system capabilities
+- NFRs → architecture decisions
+- Domain requirements → compliance architecture
+- Project-type requirements → platform choices
+
+**Epics & Stories (created after architecture):**
+- FRs → user stories (1 FR could map to 1-3 stories potentially)
+- Acceptance criteria → story acceptance tests
+- Priority → sprint sequencing
+- Traceability → stories map back to vision
+
+**Development AI Agents:**
+- Precise requirements → implementation clarity
+- Test criteria → automated test generation
+- Domain requirements → compliance enforcement
+- Measurable NFRs → performance targets
+
+---
+
+## Summary: What Makes a Great BMAD PRD?
+
+✅ **High Information Density** - Every sentence carries weight, zero fluff
+✅ **Measurable Requirements** - All FRs and NFRs are testable with specific criteria
+✅ **Clear Traceability** - Each requirement links to user need and business objective
+✅ **Domain Awareness** - Industry-specific requirements auto-detected and included
+✅ **Zero Anti-Patterns** - No subjective adjectives, implementation leakage, or vague quantifiers
+✅ **Dual Audience Optimized** - Human-readable AND LLM-consumable
+✅ **Markdown Format** - Professional, clean, accessible to all stakeholders
+
+---
+
+**Remember:** The PRD is the foundation. Quality here ripples through every subsequent phase. A dense, precise, well-traced PRD makes UX design, architecture, epic breakdown, and AI development dramatically more effective.

package/src/modules/bmm/workflows/2-plan-workflows/prd/{steps → steps-c}/step-01-init.md

@@ -2,19 +2,13 @@
 name: 'step-01-init'
 description: 'Initialize the PRD workflow by detecting continuation state and setting up the document'
 
-# Path Definitions
-workflow_path: '{project-root}/_bmad/bmm/workflows/2-plan-workflows/prd'
-
 # File References
-thisStepFile: '{workflow_path}/steps/step-01-init.md'
-nextStepFile: '{workflow_path}/steps/step-02-discovery.md'
-continueStepFile: '{workflow_path}/steps/step-01b-continue.md'
-workflowFile: '{workflow_path}/workflow.md'
+nextStepFile: './step-02-discovery.md'
+continueStepFile: './step-01b-continue.md'
 outputFile: '{planning_artifacts}/prd.md'
 
-
-# Template References
-prdTemplate: '{workflow_path}/prd-template.md'
+# Template Reference
+prdTemplate: '../templates/prd-template.md'
 ---
 
 # Step 1: Workflow Initialization
@@ -33,6 +27,7 @@ Initialize the PRD workflow by detecting continuation state, discovering input d
 - 📖 CRITICAL: Read the complete step file before taking any action
 - 🔄 CRITICAL: When loading next step with 'C', ensure entire file is read
 - 📋 YOU ARE A FACILITATOR, not a content generator
+- ✅ YOU MUST ALWAYS SPEAK OUTPUT In your Agent communication style with the config `{communication_language}`
 
 ### Role Reinforcement:
 
@@ -156,7 +151,7 @@ Display menu after setup report:
 
 #### Menu Handling Logic:
 
-- IF C: Update frontmatter with `stepsCompleted: [1]`, then load, read entire {nextStepFile}, then execute {nextStepFile}
+- IF C: Update output file frontmatter, adding this step name to the end of the list of stepsCompleted, then load, read entire {nextStepFile}, then execute {nextStepFile}
 - IF user provides additional files: Load them, update inputDocuments and documentCounts, redisplay report
 - IF user asks questions: Answer and redisplay menu
 
@@ -167,7 +162,7 @@ Display menu after setup report:
 
 ## CRITICAL STEP COMPLETION NOTE
 
-ONLY WHEN [C continue option] is selected and [frontmatter properly updated with stepsCompleted: [1] and documentCounts], will you then load and read fully `{nextStepFile}` to execute and begin project discovery.
+ONLY WHEN [C continue option] is selected and [frontmatter properly updated with this step added to stepsCompleted and documentCounts], will you then load and read fully `{nextStepFile}` to execute and begin project discovery.
 
 ---
 
@@ -181,7 +176,7 @@ ONLY WHEN [C continue option] is selected and [frontmatter properly updated with
 - All discovered files tracked in frontmatter `inputDocuments`
 - User clearly informed of brownfield vs greenfield status
 - Menu presented and user input handled correctly
-- Frontmatter updated with `stepsCompleted: [1]` before proceeding
+- Frontmatter updated with this step name added to stepsCompleted before proceeding
 
 ### ❌ SYSTEM FAILURE:
 

package/src/modules/bmm/workflows/2-plan-workflows/prd/{steps → steps-c}/step-01b-continue.md

@@ -2,12 +2,7 @@
 name: 'step-01b-continue'
 description: 'Resume an interrupted PRD workflow from the last completed step'
 
-# Path Definitions
-workflow_path: '{project-root}/_bmad/bmm/workflows/2-plan-workflows/prd'
-
 # File References
-thisStepFile: '{workflow_path}/steps/step-01b-continue.md'
-workflowFile: '{workflow_path}/workflow.md'
 outputFile: '{planning_artifacts}/prd.md'
 ---
 
@@ -25,6 +20,7 @@ Resume the PRD workflow from where it was left off, ensuring smooth continuation
 - 📖 CRITICAL: Read the complete step file before taking any action
 - 🔄 CRITICAL: When loading next step with 'C', ensure entire file is read
 - 📋 YOU ARE A FACILITATOR, not a content generator
+- ✅ YOU MUST ALWAYS SPEAK OUTPUT In your Agent communication style with the config `{communication_language}`
 
 ### Role Reinforcement:
 
@@ -59,10 +55,9 @@ Resume the PRD workflow from where it was left off, ensuring smooth continuation
 **State Assessment:**
 Review the frontmatter to understand:
 
-- `stepsCompleted`: Which steps are already done
-- `lastStep`: The most recently completed step number
+- `stepsCompleted`: Array of completed step filenames
+- Last element of `stepsCompleted` array: The most recently completed step
 - `inputDocuments`: What context was already loaded
-- `documentCounts`: briefs, research, brainstorming, projectDocs counts
 - All other frontmatter variables
 
 ### 2. Restore Context Documents
@@ -73,47 +68,27 @@ Review the frontmatter to understand:
 - This ensures you have full context for continuation
 - Don't discover new documents - only reload what was previously processed
 
-### 3. Present Current Progress
-
-**Progress Report to User:**
-"Welcome back {{user_name}}! I'm resuming our PRD collaboration for {{project_name}}.
-
-**Current Progress:**
-
-- Steps completed: {stepsCompleted}
-- Last worked on: Step {lastStep}
-- Context documents available: {len(inputDocuments)} files
-
-**Document Status:**
-
-- Current PRD document is ready with all completed sections
-- Ready to continue from where we left off
-
-Does this look right, or do you want to make any adjustments before we proceed?"
-
-### 4. Determine Continuation Path
+### 3. Determine Next Step
 
-**Next Step Logic:**
-Based on `lastStep` value, determine which step to load next:
+**Simplified Next Step Logic:**
+1. Get the last element from the `stepsCompleted` array (this is the filename of the last completed step, e.g., "step-03-success.md")
+2. Load that step file and read its frontmatter
+3. Extract the `nextStepFile` value from the frontmatter
+4. That's the next step to load!
 
-- If `lastStep = 1` → Load `./step-02-discovery.md`
-- If `lastStep = 2` → Load `./step-03-success.md`
-- If `lastStep = 3` → Load `./step-04-journeys.md`
-- If `lastStep = 4` → Load `./step-05-domain.md`
-- If `lastStep = 5` → Load `./step-06-innovation.md`
-- If `lastStep = 6` → Load `./step-07-project-type.md`
-- If `lastStep = 7` → Load `./step-08-scoping.md`
-- If `lastStep = 8` → Load `./step-09-functional.md`
-- If `lastStep = 9` → Load `./step-10-nonfunctional.md`
-- If `lastStep = 10` → Load `./step-11-complete.md`
-- If `lastStep = 11` → Workflow already complete
+**Example:**
+- If `stepsCompleted = ["step-01-init.md", "step-02-discovery.md", "step-03-success.md"]`
+- Last element is `"step-03-success.md"`
+- Load `step-03-success.md`, read its frontmatter
+- Find `nextStepFile: './step-04-journeys.md'`
+- Next step to load is `./step-04-journeys.md`
 
-### 5. Handle Workflow Completion
+### 4. Handle Workflow Completion
 
-**If workflow already complete (`lastStep = 11`):**
+**If `stepsCompleted` array contains `"step-11-complete.md"`:**
 "Great news! It looks like we've already completed the PRD workflow for {{project_name}}.
 
-The final document is ready at `{outputFile}` with all sections completed through step 11.
+The final document is ready at `{outputFile}` with all sections completed.
 
 Would you like me to:
 
@@ -123,16 +98,29 @@ Would you like me to:
 
 What would be most helpful?"
 
-### 6. Present MENU OPTIONS
+### 5. Present Current Progress
 
 **If workflow not complete:**
-Display: "Ready to continue with Step {nextStepNumber}?
+"Welcome back {{user_name}}! I'm resuming our PRD collaboration for {{project_name}}.
+
+**Current Progress:**
+- Last completed: {last step filename from stepsCompleted array}
+- Next up: {nextStepFile determined from that step's frontmatter}
+- Context documents available: {len(inputDocuments)} files
+
+**Document Status:**
+- Current PRD document is ready with all completed sections
+- Ready to continue from where we left off
+
+Does this look right, or do you want to make any adjustments before we proceed?"
+
+### 6. Present MENU OPTIONS
 
-**Select an Option:** [C] Continue to next step"
+Display: "**Select an Option:** [C] Continue to {next step name}"
 
 #### Menu Handling Logic:
 
-- IF C: Load, read entire file, then execute the appropriate next step file based on `lastStep`
+- IF C: Load, read entire file, then execute the {nextStepFile} determined in step 3
 - IF Any other comments or queries: respond and redisplay menu
 
 #### EXECUTION RULES:
@@ -142,7 +130,7 @@ Display: "Ready to continue with Step {nextStepNumber}?
 
 ## CRITICAL STEP COMPLETION NOTE
 
-ONLY WHEN [C continue option] is selected and [current state confirmed], will you then load and read fully the appropriate next step file to resume the workflow.
+ONLY WHEN [C continue option] is selected and [current state confirmed], will you then load and read fully the {nextStepFile} to resume the workflow.
 
 ---
 
@@ -159,7 +147,7 @@ ONLY WHEN [C continue option] is selected and [current state confirmed], will yo
 
 - Discovering new input documents instead of reloading existing ones
 - Modifying content from already completed steps
-- Loading wrong next step based on `lastStep` value
+- Failing to extract nextStepFile from the last completed step's frontmatter
 - Proceeding without user confirmation of current state
 
 **Master Rule:** Skipping steps, optimizing sequences, or not following exact instructions is FORBIDDEN and constitutes SYSTEM FAILURE.

package/src/modules/bmm/workflows/2-plan-workflows/prd/steps-c/step-02-discovery.md

@@ -0,0 +1,224 @@
+---
+name: 'step-02-discovery'
+description: 'Discover project type, domain, and context through collaborative dialogue'
+
+# File References
+nextStepFile: './step-03-success.md'
+outputFile: '{planning_artifacts}/prd.md'
+
+# Data Files
+projectTypesCSV: '../data/project-types.csv'
+domainComplexityCSV: '../data/domain-complexity.csv'
+
+# Task References
+advancedElicitationTask: '{project-root}/_bmad/core/workflows/advanced-elicitation/workflow.xml'
+partyModeWorkflow: '{project-root}/_bmad/core/workflows/party-mode/workflow.md'
+---
+
+# Step 2: Project Discovery
+
+**Progress: Step 2 of 13** - Next: Product Vision
+
+## STEP GOAL:
+
+Discover and classify the project - understand what type of product this is, what domain it operates in, and the project context (greenfield vs brownfield).
+
+## MANDATORY EXECUTION RULES (READ FIRST):
+
+### Universal Rules:
+
+- 🛑 NEVER generate content without user input
+- 📖 CRITICAL: Read the complete step file before taking any action
+- 🔄 CRITICAL: When loading next step with 'C', ensure the entire file is read
+- ✅ ALWAYS treat this as collaborative discovery between PM peers
+- 📋 YOU ARE A FACILITATOR, not a content generator
+- ✅ YOU MUST ALWAYS SPEAK OUTPUT In your Agent communication style with the config `{communication_language}`
+
+### Role Reinforcement:
+
+- ✅ You are a product-focused PM facilitator collaborating with an expert peer
+- ✅ We engage in collaborative dialogue, not command-response
+- ✅ You bring structured thinking and facilitation skills, while the user brings domain expertise and product vision
+
+### Step-Specific Rules:
+
+- 🎯 Focus on classification and understanding - no content generation yet
+- 🚫 FORBIDDEN to generate executive summary or vision statements (that's next steps)
+- 💬 APPROACH: Natural conversation to understand the project
+- 🎯 LOAD classification data BEFORE starting discovery conversation
+
+## EXECUTION PROTOCOLS:
+
+- 🎯 Show your analysis before taking any action
+- ⚠️ Present A/P/C menu after classification complete
+- 💾 ONLY save classification to frontmatter when user chooses C (Continue)
+- 📖 Update frontmatter, adding this step to the end of the list of stepsCompleted
+- 🚫 FORBIDDEN to load next step until C is selected
+
+## CONTEXT BOUNDARIES:
+
+- Current document and frontmatter from step 1 are available
+- Input documents already loaded are in memory (product briefs, research, brainstorming, project docs)
+- **Document counts available in frontmatter `documentCounts`**
+- Classification CSV data will be loaded in this step only
+- No executive summary or vision content yet (that's steps 2b and 2c)
+
+## YOUR TASK:
+
+Discover and classify the project through natural conversation:
+- What type of product is this? (web app, API, mobile, etc.)
+- What domain does it operate in? (healthcare, fintech, e-commerce, etc.)
+- What's the project context? (greenfield new product vs brownfield existing system)
+- How complex is this domain? (low, medium, high)
+
+## DISCOVERY SEQUENCE:
+
+### 1. Check Document State
+
+Read the frontmatter from `{outputFile}` to get document counts:
+- `briefCount` - Product briefs available
+- `researchCount` - Research documents available
+- `brainstormingCount` - Brainstorming docs available
+- `projectDocsCount` - Existing project documentation
+
+**Announce your understanding:**
+
+"From step 1, I have loaded:
+- Product briefs: {{briefCount}}
+- Research: {{researchCount}}
+- Brainstorming: {{brainstormingCount}}
+- Project docs: {{projectDocsCount}}
+
+{{if projectDocsCount > 0}}This is a brownfield project - I'll focus on understanding what you want to add or change.{{else}}This is a greenfield project - I'll help you define the full product vision.{{/if}}"
+
+### 2. Load Classification Data
+
+**Attempt subprocess data lookup:**
+
+**Project Type Lookup:**
+"Your task: Lookup data in {projectTypesCSV}
+
+**Search criteria:**
+- Find row where project_type matches {{detectedProjectType}}
+
+**Return format:**
+Return ONLY the matching row as a YAML-formatted object with these fields:
+project_type, detection_signals
+
+**Do NOT return the entire CSV - only the matching row.**"
+
+**Domain Complexity Lookup:**
+"Your task: Lookup data in {domainComplexityCSV}
+
+**Search criteria:**
+- Find row where domain matches {{detectedDomain}}
+
+**Return format:**
+Return ONLY the matching row as a YAML-formatted object with these fields:
+domain, complexity, typical_concerns, compliance_requirements
+
+**Do NOT return the entire CSV - only the matching row.**"
+
+**Graceful degradation (if Task tool unavailable):**
+- Load the CSV files directly
+- Find the matching rows manually
+- Extract required fields
+- Keep in memory for intelligent classification
+
+### 3. Begin Discovery Conversation
+
+**Start with what you know:**
+
+If the user has a product brief or project docs, acknowledge them and share your understanding. Then ask clarifying questions to deepen your understanding.
+
+If this is a greenfield project with no docs, start with open-ended discovery:
+- What problem does this solve?
+- Who's it for?
+- What excites you about building this?
+
+**Listen for classification signals:**
+
+As the user describes their product, match against:
+- **Project type signals** (API, mobile, SaaS, etc.)
+- **Domain signals** (healthcare, fintech, education, etc.)
+- **Complexity indicators** (regulated industries, novel technology, etc.)
+
+### 4. Confirm Classification
+
+Once you have enough understanding, share your classification:
+
+"I'm hearing this as:
+- **Project Type:** {{detectedType}}
+- **Domain:** {{detectedDomain}}
+- **Complexity:** {{complexityLevel}}
+
+Does this sound right to you?"
+
+Let the user confirm or refine your classification.
+
+### 5. Save Classification to Frontmatter
+
+When user selects 'C', update frontmatter with classification:
+```yaml
+classification:
+  projectType: {{projectType}}
+  domain: {{domain}}
+  complexity: {{complexityLevel}}
+  projectContext: {{greenfield|brownfield}}
+```
+
+### N. Present MENU OPTIONS
+
+Present the project classification for review, then display menu:
+
+"Based on our conversation, I've discovered and classified your project.
+
+**Here's the classification:**
+
+**Project Type:** {{detectedType}}
+**Domain:** {{detectedDomain}}
+**Complexity:** {{complexityLevel}}
+**Project Context:** {{greenfield|brownfield}}
+
+**What would you like to do?**"
+
+Display: "**Select:** [A] Advanced Elicitation [P] Party Mode [C] Continue to Product Vision (Step 2b of 13)"
+
+#### Menu Handling Logic:
+- IF A: Execute {advancedElicitationTask} with the current classification, process the enhanced insights that come back, ask user if they accept the improvements, if yes update classification then redisplay menu, if no keep original classification then redisplay menu
+- IF P: Execute {partyModeWorkflow} with the current classification, process the collaborative insights, ask user if they accept the changes, if yes update classification then redisplay menu, if no keep original classification then redisplay menu
+- IF C: Save classification to {outputFile} frontmatter, add this step name to the end of stepsCompleted array, then load, read entire file, then execute {nextStepFile}
+- IF Any other: help user respond, then redisplay menu
+
+#### EXECUTION RULES:
+- ALWAYS halt and wait for user input after presenting menu
+- ONLY proceed to next step when user selects 'C'
+- After other menu items execution, return to this menu
+
+## CRITICAL STEP COMPLETION NOTE
+
+ONLY WHEN [C continue option] is selected and [classification saved to frontmatter], will you then load and read fully `{nextStepFile}` to explore product vision.
+
+---
+
+## 🚨 SYSTEM SUCCESS/FAILURE METRICS
+
+### ✅ SUCCESS:
+
+- Document state checked and announced to user
+- Classification data loaded and used intelligently
+- Natural conversation to understand project type, domain, complexity
+- Classification validated with user before saving
+- Frontmatter updated with classification when C selected
+- User's existing documents acknowledged and built upon
+
+### ❌ SYSTEM FAILURE:
+
+- Not reading documentCounts from frontmatter first
+- Skipping classification data loading
+- Generating executive summary or vision content (that's later steps!)
+- Not validating classification with user
+- Being prescriptive instead of having natural conversation
+- Proceeding without user selecting 'C'
+
+**Master Rule:** This is classification and understanding only. No content generation yet. Build on what the user already has. Have natural conversations, don't follow scripts.