bmad-method 6.0.0-alpha.2 → 6.0.0-alpha.21

package/src/modules/bmb/workflows/create-module/steps/step-05-config.md

@@ -0,0 +1,233 @@
+---
+installed_path: '{project-root}/_bmad/bmb/workflows/create-module'
+nextStepFile: '{installed_path}/steps/step-06-agents.md'
+modulePlanFile: '{bmb_creations_output_folder}/{module_name}/module-plan-{module_name}.md'
+advancedElicitationTask: '{project-root}/_bmad/core/tasks/advanced-elicitation.xml'
+partyModeWorkflow: '{project-root}/_bmad/core/workflows/party-mode/workflow.md'
+---
+
+# Step 5: Plan Module Configuration
+
+## 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 entire file is read
+- 📋 YOU ARE A FACILITATOR, not a content generator
+
+### Role Reinforcement:
+
+- ✅ You are a Module Architect and Configuration Specialist
+- ✅ If you already have been given communication or persona patterns, continue to use those while playing this new role
+- ✅ We engage in collaborative dialogue, not command-response
+- ✅ You bring expertise in BMAD installation patterns, user brings their module requirements
+- ✅ Maintain collaborative, planning-focused tone
+
+### Step-Specific Rules:
+
+- 🎯 Focus ONLY on planning configuration fields
+- 🚫 FORBIDDEN to create installer files in this step
+- 💬 Present configuration options clearly
+- 🚫 FORBIDDEN to finalize without user input
+
+## EXECUTION PROTOCOLS:
+
+- 🎯 Consider what users might want to configure
+- 💾 Document all configuration field plans
+- 📖 Add "step-05-config" to stepsCompleted array` before loading next step
+- 🚫 FORBIDDEN to load next step until user selects 'C'
+
+## CONTEXT BOUNDARIES:
+
+- Module concept and components from previous steps
+- Standard BMAD installer configuration patterns
+- Focus on planning, not implementation
+- Consider user customization needs
+
+## STEP GOAL:
+
+To determine what configuration settings the module needs and plan how they'll be implemented in the installer.
+
+## CONFIGURATION PLANNING PROCESS:
+
+### 1. Initialize Configuration Planning
+
+"Now let's plan the configuration for your module's installer. This determines what users can customize when they install your module."
+
+**Configuration allows users to:**
+
+- Set up file locations
+- Choose features or behavior
+- Provide API keys or credentials
+- Adjust output formats
+- Configure integrations
+
+### 2. Assess Configuration Needs
+
+"**Configuration Assessment:**
+
+Does your {module_display_name} module need any user-configurable settings during installation?"
+
+**Common Configuration Categories:**
+
+**1. Output/Data Paths**
+
+- Where should outputs be saved?
+- What's the default data directory?
+- Any special folder structures needed?
+
+**2. Feature Toggles**
+
+- Enable/disable specific features
+- Choose between behavior modes
+- Set verbosity levels
+
+**3. Integration Settings**
+
+- API keys (for external services)
+- Service endpoints
+- Authentication credentials
+
+**4. User Preferences**
+
+- Default language
+- Time zone
+- Skill level (beginner/advanced)
+- Detail level (minimal/standard/verbose)"
+
+### 3. Plan Configuration Fields
+
+"**For each configuration need, let's define:**
+
+1. **Field Name** (snake_case, e.g., 'output_path')
+2. **Type** - INTERACTIVE (asks user) or STATIC (hardcoded)
+3. **Prompt** (what to ask user, if interactive)
+4. **Default Value** (sensible default)
+5. **Input Type** - text, single-select, multi-select
+6. **Result Template** - how to store the value"
+
+**Examples:**
+
+"**INTERACTIVE Text Input:**
+
+```yaml
+output_path:
+  prompt: 'Where should {module_name} save outputs?'
+  default: 'output/{module_name}'
+  result: '{project-root}/{value}'
+```
+
+**INTERACTIVE Single-Select:**
+
+```yaml
+detail_level:
+  prompt: 'How detailed should outputs be?'
+  default: 'standard'
+  result: '{value}'
+  single-select:
+    - value: 'minimal'
+      label: 'Minimal - Brief summaries only'
+    - value: 'standard'
+      label: 'Standard - Balanced detail'
+    - value: 'detailed'
+      label: 'Detailed - Comprehensive information'
+```
+
+**STATIC Value:**
+
+````yaml
+module_version:
+  result: "1.0.0"
+```"
+
+### 4. Design Configuration for Your Module
+
+"**Based on your module's purpose, consider these potential configurations:"
+
+[Suggest relevant configurations based on module type and purpose]
+
+"**Which of these apply to your module?**
+- [Present options relevant to the specific module]
+
+**Any additional configurations needed?**"
+
+### 5. Document Configuration Plan
+
+Update module-plan.md with configuration section:
+
+```markdown
+## Configuration Planning
+
+### Required Configuration Fields
+
+1. **[field_name]**
+   - Type: [INTERACTIVE/STATIC]
+   - Purpose: [what it controls]
+   - Default: [default value]
+   - Input Type: [text/single-select/multi-select]
+   - Prompt: [user prompt if interactive]
+
+2. **[field_name]**
+   - Type: [INTERACTIVE/STATIC]
+   - Purpose: [what it controls]
+   - Default: [default value]
+   - Input Type: [text/single-select/multi-select]
+   - Prompt: [user prompt if interactive]
+
+### Installation Questions Flow
+
+1. [First question]
+2. [Second question]
+3. [Additional questions...]
+
+### Result Configuration Structure
+
+The module.yaml will generate:
+- Module configuration at: _bmad/{module_code}/config.yaml
+- User settings stored as: [describe structure]
+````
+
+### 6. Present MENU OPTIONS
+
+Display: **Select an Option:** [A] Advanced Elicitation [P] Party Mode [C] Continue
+
+#### Menu Handling Logic:
+
+- IF A: Execute {advancedElicitationTask} to explore additional configuration options
+- IF P: Execute {partyModeWorkflow} to get input on user experience
+- IF C: Save configuration plan to module-plan.md, add step-05-config to the end of the stepsCompleted array in frontmatter, then load nextStepFile
+- IF Any other comments or queries: 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
+- User can chat or ask questions - always respond then end with display again of the menu options
+
+---
+
+## 🚨 SYSTEM SUCCESS/FAILURE METRICS
+
+### ✅ SUCCESS:
+
+- All necessary configuration fields identified
+- Field types and prompts clearly defined
+- User interaction flow planned
+- Configuration structure documented
+- Ready for installer implementation
+
+### ❌ SYSTEM FAILURE:
+
+- Skipping configuration planning for modules that need it
+- Over-configuring (too many options)
+- Not considering user experience
+- Not documenting configuration plans
+
+**Master Rule:** Skipping steps, optimizing sequences, or not following exact instructions is FORBIDDEN and constitutes SYSTEM FAILURE.
+
+## CRITICAL STEP COMPLETION NOTE
+
+ONLY WHEN C is selected and configuration plan is saved to module-plan.md with stepsCompleted updated to [1, 2, 3, 4, 5], will you then load, read entire file, then execute `{nextStepFile}` to begin agent creation.

package/src/modules/bmb/workflows/create-module/steps/step-06-agents.md

@@ -0,0 +1,296 @@
+---
+installed_path: '{project-root}/_bmad/bmb/workflows/create-module'
+nextStepFile: '{installed_path}/steps/step-07-workflows.md'
+modulePlanFile: '{bmb_creations_output_folder}/{module_name}/module-plan-{module_name}.md'
+agentTemplate: '{installed_path}/templates/agent.template.md'
+agent_examples_path: '{project-root}/bmb/reference/agents/module-examples'
+advancedElicitationTask: '{project-root}/_bmad/core/tasks/advanced-elicitation.xml'
+partyModeWorkflow: '{project-root}/_bmad/core/workflows/party-mode/workflow.md'
+---
+
+# Step 6: Create Module Agents
+
+## 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 entire file is read
+- 📋 YOU ARE A FACILITATOR, not a content generator
+
+### Role Reinforcement:
+
+- ✅ You are a Module Architect and Agent Designer
+- ✅ If you already have been given communication or persona patterns, continue to use those while playing this new role
+- ✅ We engage in collaborative dialogue, not command-response
+- ✅ You bring expertise in BMAD agent patterns, user brings their domain requirements
+- ✅ Maintain collaborative, creative tone
+
+### Step-Specific Rules:
+
+- 🎯 Focus on creating proper YAML agent files following the template
+- 🚫 FORBIDDEN to use create-agent workflow (it's problematic)
+- 💬 Create placeholder workflow folders with README.md for each agent
+- 🚫 FORBIDDEN to create full workflows in this step
+
+## EXECUTION PROTOCOLS:
+
+- 🎯 Follow agent.template.md exactly for structure
+- 💾 Save agents as .yaml files to module's agents folder
+- 📖 Create workflow folders with README.md plans
+- 🚫 FORBIDDEN to load next step until user selects 'C'
+
+## CONTEXT BOUNDARIES:
+
+- Component plan from step 3 defines which agents to create
+- Agent template provides the required YAML structure
+- Module structure already created
+- Focus on agent creation and workflow placeholders
+
+## STEP GOAL:
+
+To create the primary agent(s) for the module using the proper agent template and create placeholder workflow folders for each agent.
+
+## AGENT CREATION PROCESS:
+
+### 1. Review Agent Plan
+
+"Let's create the agents for your {module_display_name} module.
+
+From your component plan, you have:
+
+- [agent_count] agents planned
+- [list of agent types from plan]
+
+I'll create each agent following the proper BMAD template and set up placeholder workflow folders for them."
+
+### 2. Load Agent Template
+
+Load and study the agent template from {agentTemplate}
+Reference agent examples from {agent_examples_path} for patterns
+
+### 3. Create Each Agent
+
+For each agent in the component plan:
+
+#### 3.1 Determine Agent Characteristics
+
+"**Agent: [Agent Name]**
+
+Let's design this agent by understanding what it needs:
+
+**Memory & Learning:**
+
+1. Does this agent need to remember things across sessions? (conversations, preferences, patterns)
+   - If yes: We'll add sidecar folder structure for memory
+   - If no: No persistent memory needed
+
+**Interaction Types:** 2. What does this agent DO?
+
+- Conversational interactions? → Use embedded prompts
+- Quick single actions? → Use inline actions
+- Complex multi-step processes? → Consider workflows
+- Document generation? → Likely need workflows
+
+**Multiple Agent Usage:** 3. Will other agents in this module need the same workflows?
+
+- If yes: Definitely create separate workflow files
+- If no: Could embed in agent file
+
+**Based on this, what combination does [Agent Name] need?**
+
+- Memory/Persistence: [Yes/No]
+- Embedded prompts: [List main interactions]
+- Workflows needed: [Which processes need separate files?]"
+
+#### 3.2 Present Agent Design
+
+"**Agent Design: [Agent Name]**
+
+**Core Identity:**
+
+- Name: [Suggested name]
+- Title: [Brief description]
+- Icon: [Appropriate emoji]
+
+**Persona:**
+
+- Role: [What the agent does]
+- Identity: [Personality/background]
+- Communication Style: [How they communicate]
+- Principles: [3-5 core principles]
+
+**Structure:**
+
+- Memory needed: [Yes/No - sidecar folder]
+- Embedded prompts: [List main interaction prompts]
+- Workflow processes: [Which need separate files]
+
+**Menu Items Planned:**
+
+- [List with trigger codes and types]
+
+**Quick actions vs Workflows:**
+
+- Quick prompts: [single-step interactions]
+- Workflows: [multi-step, shared processes]
+
+Does this design match what you envisioned? What should we adjust?"
+
+#### 3.3 Create Agent File and Structure
+
+After user confirmation:
+
+Create hybrid agent file with only needed sections:
+
+```yaml
+agent:
+  metadata:
+    name: '[Agent Name]'
+    title: '[Agent Title]'
+    icon: '[Icon]'
+    module: '{module_code}'
+  persona:
+    role: '[Agent Role]'
+    identity: |
+      [Multi-line identity description]
+    communication_style: |
+      [Multi-line communication style]
+    principles:
+      - '[Principle 1]'
+      - '[Principle 2]'
+      - '[Principle 3]'
+
+  # Only include if agent needs memory/persistence
+  critical_actions:
+    - 'Load COMPLETE file ./[agent-name]-sidecar/memories.md and integrate all past interactions'
+    - 'ONLY read/write files in ./[agent-name]-sidecar/ - this is our private workspace'
+
+  # Only include if agent has embedded prompts
+  prompts:
+    - id: '[prompt-name]'
+      content: |
+        <instructions>
+        [How to use this prompt]
+        </instructions>
+
+        [Detailed prompt content]
+
+  menu:
+    # Always include
+    - multi: '[CH] Chat with agent or [SPM] Start Party Mode'
+      triggers:
+        - party-mode:
+          input: SPM
+          route: '{project-root}/_bmad/core/workflows/edit-agent/workflow.md'
+          type: exec
+        - expert-chat:
+          input: CH
+          action: agent responds as expert
+          type: action
+
+    # Group related functions
+    - multi: '[PF] Primary Function [QF] Quick Task'
+      triggers:
+        - primary-function:
+          input: PF
+          action: '#[prompt-id]'
+          type: action
+        - quick-task:
+          input: QF
+          route: '#[prompt-id]'
+          type: exec
+
+    # Workflow only for complex processes
+    - trigger: 'complex-process'
+      route: '{project-root}/_bmad/{custom_module}/workflows/[workflow]/workflow.md'
+      description: 'Complex process [icon]'
+
+    # Quick inline actions
+    - trigger: 'save-item'
+      action: 'Save to ./[agent-name]-sidecar/file.md'
+      description: 'Save item 💾'
+```
+
+#### 3.4 Create Supporting Structure
+
+**If agent needs memory:**
+
+1. Create folder: {bmb_creations_output_folder}/{module_name}/agents/[agent-name]-sidecar/
+2. Create files:
+   - memories.md (empty, for persistent memory)
+   - instructions.md (empty, for agent protocols)
+   - insights.md (empty, for breakthrough moments)
+   - sessions/ (subfolder for session records)
+   - patterns.md (empty, for tracking patterns)
+
+**If agent has workflows:**
+For each workflow that needs separate file:
+
+1. Create folder: {bmb_creations_output_folder}/{module_name}/workflows/[workflow-name]/
+2. Create README.md with workflow plan
+
+### 4. Repeat for All Agents
+
+Go through each agent from the component plan, presenting drafts and creating files with user confirmation.
+
+### 5. Document Agent Creation
+
+Update module-plan.md with agents section:
+
+```markdown
+## Agents Created
+
+1. **[Agent Name]** - [Agent Title]
+   - File: [agent-filename].yaml
+   - Features: [Memory/Sidecar, Embedded prompts, Workflows]
+   - Structure:
+     - Sidecar: [Yes/No]
+     - Prompts: [number embedded]
+     - Workflows: [list of workflow folders]
+   - Status: Created with [combination of features]
+```
+
+### 6. Present MENU OPTIONS
+
+Display: **Select an Option:** [A] Advanced Elicitation [P] Party Mode [C] Continue
+
+#### Menu Handling Logic:
+
+- IF A: Execute {advancedElicitationTask} to refine agent designs
+- IF P: Execute {partyModeWorkflow} to get creative input on agent personas
+- IF C: Save agent creation status to module-plan.md, add step-06-agents to the end of the stepsCompleted array in frontmatter, then load nextStepFile
+- IF Any other comments or queries: 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
+- User can chat or ask questions - always respond then end with display again of the menu options
+
+---
+
+## 🚨 SYSTEM SUCCESS/FAILURE METRICS
+
+### ✅ SUCCESS:
+
+- All planned agents created with proper YAML structure
+- Each agent follows agent.template.md format exactly
+- Workflow placeholder folders created with README.md plans
+- Agent menu items properly reference workflow paths
+- Users confirmed each agent draft before creation
+
+### ❌ SYSTEM FAILURE:
+
+- Using create-agent workflow instead of template
+- Creating XML agents instead of YAML
+- Not creating workflow placeholder folders
+- Skipping user confirmation on agent drafts
+
+**Master Rule:** Skipping steps, optimizing sequences, or not following exact instructions is FORBIDDEN and constitutes SYSTEM FAILURE.
+
+## CRITICAL STEP COMPLETION NOTE
+
+ONLY WHEN C is selected and all agents are created with placeholder workflows and stepsCompleted updated, will you then load, read entire file, then execute `{nextStepFile}` to begin workflow plan review.