bmad-method 4.4.2 → 4.5.1

package/docs/claude-code-guide.md

@@ -6,9 +6,11 @@ This guide walks you through the complete BMAD workflow using Claude Code as you
 
 1. Navigate to your project directory
 2. Run the BMAD installer:
+
    ```bash
    npx bmad-method install
    ```
+
 3. When prompted:
    - **Installation Type**: Choose "Complete installation (recommended)"
    - **IDE**: Select "Claude Code"
@@ -17,11 +19,11 @@ This creates a `.bmad-core` folder with all agents and a `.claude/commands` fold
 
 ## Step 2: Set Up Team Fullstack in Gemini
 
-For ideation and planning, use Google's Gemini with the team-fullstack configuration:
+For ideation and planning, use Google's Gemini Custom Gem with the team-fullstack configuration:
 
-1. Open [Google AI Studio (Gemini)](https://aistudio.google.com/)
-2. Create a new chat
-3. Copy the contents of `/Users/brianmadison/dev/BMAD-METHOD/.bmad-core/web-bundles/teams/team-fullstack.txt`
+1. Open [Google gems](https://gemini.google.com/gems/view)
+2. Create a new Gem - give it a title and description
+3. Copy the contents of `.<install location>/web-bundles/teams/team-fullstack.txt`
 4. Paste this content into Gemini to set up the team
 
 ### Gemini Planning Phase

package/docs/cursor-guide.md

@@ -6,9 +6,11 @@ This guide walks you through the complete BMAD workflow using Cursor as your AI-
 
 1. Navigate to your project directory
 2. Run the BMAD installer:
+
    ```bash
    npx bmad-method install
    ```
+
 3. When prompted:
    - **Installation Type**: Choose "Complete installation (recommended)"
    - **IDE**: Select "Cursor"
@@ -17,11 +19,11 @@ This creates a `.bmad-core` folder with all agents and a `.cursor/rules` folder
 
 ## Step 2: Set Up Team Fullstack in Gemini
 
-For ideation and planning, use Google's Gemini with the team-fullstack configuration:
+For ideation and planning, use Google's Gemini Custom Gem with the team-fullstack configuration:
 
-1. Open [Google AI Studio (Gemini)](https://aistudio.google.com/)
-2. Create a new chat
-3. Copy the contents of `/Users/brianmadison/dev/BMAD-METHOD/.bmad-core/web-bundles/teams/team-fullstack.txt`
+1. Open [Google gems](https://gemini.google.com/gems/view)
+2. Create a new Gem - give it a title and description
+3. Copy the contents of `.<install location>/web-bundles/teams/team-fullstack.txt`
 4. Paste this content into Gemini to set up the team
 
 ### Gemini Planning Phase
@@ -101,6 +103,8 @@ All BMAD agents are available as Cursor rules (use `@` prefix):
 - `@po` - Product owner for prioritization
 - `@ux-expert` - UX specialist for design
 
+Alternatively, and more performance - you can copy the contents of an agent file into a custom mode - see the cursor docs on how to use custom agents.
+
 ## Cursor-Specific Features
 
 - **Agent rules are stored in**: `.cursor/rules/` as `.mdc` files

package/docs/roo-code-guide.md

@@ -6,22 +6,24 @@ This guide walks you through the complete BMAD workflow using Roo Code as your A
 
 1. Navigate to your project directory
 2. Run the BMAD installer:
+
    ```bash
    npx bmad-method install
    ```
+
 3. When prompted:
    - **Installation Type**: Choose "Complete installation (recommended)"
    - **IDE**: Select "Roo Code"
 
-This creates a `.bmad-core` folder with all agents and a `.roo/.roomodes` file with custom modes.
+This creates a `.bmad-core` folder with all agents and a `.roomodes` file (in the project root) with custom modes.
 
 ## Step 2: Set Up Team Fullstack in Gemini
 
-For ideation and planning, use Google's Gemini with the team-fullstack configuration:
+For ideation and planning, use Google's Gemini Custom Gem with the team-fullstack configuration:
 
-1. Open [Google AI Studio (Gemini)](https://aistudio.google.com/)
-2. Create a new chat
-3. Copy the contents of `/Users/brianmadison/dev/BMAD-METHOD/.bmad-core/web-bundles/teams/team-fullstack.txt`
+1. Open [Google gems](https://gemini.google.com/gems/view)
+2. Create a new Gem - give it a title and description
+3. Copy the contents of `.<install location>/web-bundles/teams/team-fullstack.txt`
 4. Paste this content into Gemini to set up the team
 
 ### Gemini Planning Phase
@@ -103,7 +105,7 @@ All BMAD agents are available as custom modes:
 
 ## Roo Code-Specific Features
 
-- **Custom modes are stored in**: `.roo/.roomodes` file
+- **Custom modes are stored in**: `.roomodes` file (in the project root)
 - **Mode switching**: Use the mode selector in Roo Code's interface
 - **File permissions**: Each agent has specific file access permissions
   - **Documentation agents** (SM, PM, PO, Analyst): Limited to `.md` and `.txt` files

package/docs/windsurf-guide.md

@@ -6,9 +6,11 @@ This guide walks you through the complete BMAD workflow using Windsurf as your A
 
 1. Navigate to your project directory
 2. Run the BMAD installer:
+
    ```bash
    npx bmad-method install
    ```
+
 3. When prompted:
    - **Installation Type**: Choose "Complete installation (recommended)"
    - **IDE**: Select "Windsurf"
@@ -17,11 +19,11 @@ This creates a `.bmad-core` folder with all agents and a `.windsurf/rules` folde
 
 ## Step 2: Set Up Team Fullstack in Gemini
 
-For ideation and planning, use Google's Gemini with the team-fullstack configuration:
+For ideation and planning, use Google's Gemini Custom Gem with the team-fullstack configuration:
 
-1. Open [Google AI Studio (Gemini)](https://aistudio.google.com/)
-2. Create a new chat
-3. Copy the contents of `/Users/brianmadison/dev/BMAD-METHOD/.bmad-core/web-bundles/teams/team-fullstack.txt`
+1. Open [Google gems](https://gemini.google.com/gems/view)
+2. Create a new Gem - give it a title and description
+3. Copy the contents of `.<install location>/web-bundles/teams/team-fullstack.txt`
 4. Paste this content into Gemini to set up the team
 
 ### Gemini Planning Phase

package/expansion-packs/bmad-2d-phaser-game-dev/agent-teams/phaser-2d-nodejs-game-team.yml

@@ -0,0 +1,12 @@
+bundle:
+  name: Phaser 2D NodeJS Game Team
+  icon: 🎮
+  description: Game Development team specialized in 2D games using Phaser 3 and TypeScript.
+agents:
+  - bmad-orchestrator
+  - game-designer
+  - game-developer
+  - game-sm
+workflows:
+  - game-dev-greenfield
+  - game-prototype

package/expansion-packs/expansion-creator/README.md

@@ -0,0 +1,8 @@
+# BMAD Creator Tools
+
+Tools for creating and extending BMAD framework components.
+
+## Tasks
+
+- **create-agent**: Create new AI agent definitions
+- **generate-expansion-pack**: Generate new expansion pack templates

package/expansion-packs/expansion-creator/agents/bmad-the-creator.md

@@ -0,0 +1,53 @@
+# bmad-the-creator
+
+CRITICAL: Read the full YML, start activation to alter your state of being, follow startup section instructions, stay in this being until told to exit this mode:
+
+```yaml
+activation-instructions:
+  - Follow all instructions in this file -> this defines you, your persona and more importantly what you can do. STAY IN CHARACTER!
+  - Only read the files/tasks listed here when user selects them for execution to minimize context usage
+  - The customization field ALWAYS takes precedence over any conflicting instructions
+  - When listing tasks/templates or presenting options during conversations, always show as numbered options list, allowing the user to type a number to select or execute
+agent:
+  name: The Creator
+  id: bmad-the-creator
+  title: BMAD Framework Extension Specialist
+  icon: 🏗️
+  whenToUse: Use for creating new agents, expansion packs, and extending the BMAD framework
+  customization: null
+persona:
+  role: Expert BMAD Framework Architect & Creator
+  style: Methodical, creative, framework-aware, systematic
+  identity: Master builder who extends BMAD capabilities through thoughtful design and deep framework understanding
+  focus: Creating well-structured agents, expansion packs, and framework extensions that follow BMAD patterns and conventions
+core_principles:
+  - Framework Consistency - All creations follow established BMAD patterns
+  - Modular Design - Create reusable, composable components
+  - Clear Documentation - Every creation includes proper documentation
+  - Convention Over Configuration - Follow BMAD naming and structure patterns
+  - Extensibility First - Design for future expansion and customization
+  - Numbered Options Protocol - Always use numbered lists for user selections
+startup:
+  - Greet the user with your name and role, and inform of the *help command
+  - CRITICAL: Do NOT automatically create documents or execute tasks during startup
+  - CRITICAL: Do NOT create or modify any files during startup
+  - Offer to help with BMAD framework extensions but wait for explicit user confirmation
+  - Only execute tasks when user explicitly requests them
+commands:
+  - '*help" - Show numbered list of available commands for selection'
+  - '*chat-mode" - Conversational mode with advanced-elicitation for framework design advice'
+  - '*create" - Show numbered list of components I can create (agents, expansion packs)'
+  - '*brainstorm {topic}" - Facilitate structured framework extension brainstorming session'
+  - '*research {topic}" - Generate deep research prompt for framework-specific investigation'
+  - '*elicit" - Run advanced elicitation to clarify extension requirements'
+  - '*exit" - Say goodbye as The Creator, and then abandon inhabiting this persona'
+dependencies:
+  tasks:
+    - create-agent
+    - generate-expansion-pack
+    - advanced-elicitation
+    - create-deep-research-prompt
+  templates:
+    - agent-tmpl
+    - expansion-pack-plan-tmpl
+```

package/expansion-packs/expansion-creator/common-tasks/create-doc.md

@@ -0,0 +1,74 @@
+# Create Document from Template Task
+
+## Purpose
+
+- Generate documents from any specified template following embedded instructions from the perspective of the selected agent persona
+
+## Instructions
+
+### 1. Identify Template and Context
+
+- Determine which template to use (user-provided or list available for selection to user)
+
+  - Agent-specific templates are listed in the agent's dependencies under `templates`. For each template listed, consider it a document the agent can create. So if an agent has:
+
+    @{example}
+    dependencies:
+    templates: - prd-tmpl - architecture-tmpl
+    @{/example}
+
+    You would offer to create "PRD" and "Architecture" documents when the user asks what you can help with.
+
+- Gather all relevant inputs, or ask for them, or else rely on user providing necessary details to complete the document
+- Understand the document purpose and target audience
+
+### 2. Determine Interaction Mode
+
+Confirm with the user their preferred interaction style:
+
+- **Incremental:** Work through chunks of the document.
+- **YOLO Mode:** Draft complete document making reasonable assumptions in one shot. (Can be entered also after starting incremental by just typing /yolo)
+
+### 3. Execute Template
+
+- Load specified template from `templates#*` or the /templates directory
+- Follow ALL embedded LLM instructions within the template
+- Process template markup according to `utils#template-format` conventions
+
+### 4. Template Processing Rules
+
+#### CRITICAL: Never display template markup, LLM instructions, or examples to users
+
+- Replace all {{placeholders}} with actual content
+- Execute all [[LLM: instructions]] internally
+- Process `<<REPEAT>>` sections as needed
+- Evaluate ^^CONDITION^^ blocks and include only if applicable
+- Use @{examples} for guidance but never output them
+
+### 5. Content Generation
+
+- **Incremental Mode**: Present each major section for review before proceeding
+- **YOLO Mode**: Generate all sections, then review complete document with user
+- Apply any elicitation protocols specified in template
+- Incorporate user feedback and iterate as needed
+
+### 6. Validation
+
+If template specifies a checklist:
+
+- Run the appropriate checklist against completed document
+- Document completion status for each item
+- Address any deficiencies found
+- Present validation summary to user
+
+### 7. Final Presentation
+
+- Present clean, formatted content only
+- Ensure all sections are complete
+- DO NOT truncate or summarize content
+- Begin directly with document content (no preamble)
+- Include any handoff prompts specified in template
+
+## Important Notes
+
+- Template markup is for AI processing only - never expose to users

package/expansion-packs/expansion-creator/common-tasks/execute-checklist.md

@@ -0,0 +1,97 @@
+# Checklist Validation Task
+
+This task provides instructions for validating documentation against checklists. The agent MUST follow these instructions to ensure thorough and systematic validation of documents.
+
+## Context
+
+The BMAD Method uses various checklists to ensure quality and completeness of different artifacts. Each checklist contains embedded prompts and instructions to guide the LLM through thorough validation and advanced elicitation. The checklists automatically identify their required artifacts and guide the validation process.
+
+## Available Checklists
+
+If the user asks or does not specify a specific checklist, list the checklists available to the agent persona. If the task is being run not with a specific agent, tell the user to check the bmad-core/checklists folder to select the appropriate one to run.
+
+## Instructions
+
+1. **Initial Assessment**
+
+   - If user or the task being run provides a checklist name:
+     - Try fuzzy matching (e.g. "architecture checklist" -> "architect-checklist")
+     - If multiple matches found, ask user to clarify
+     - Load the appropriate checklist from bmad-core/checklists/
+   - If no checklist specified:
+     - Ask the user which checklist they want to use
+     - Present the available options from the files in the checklists folder
+   - Confirm if they want to work through the checklist:
+     - Section by section (interactive mode - very time consuming)
+     - All at once (YOLO mode - recommended for checklists, there will be a summary of sections at the end to discuss)
+
+2. **Document and Artifact Gathering**
+
+   - Each checklist will specify its required documents/artifacts at the beginning
+   - Follow the checklist's specific instructions for what to gather, generally a file can be resolved in the docs folder, if not or unsure, halt and ask or confirm with the user.
+
+3. **Checklist Processing**
+
+   If in interactive mode:
+
+   - Work through each section of the checklist one at a time
+   - For each section:
+     - Review all items in the section following instructions for that section embedded in the checklist
+     - Check each item against the relevant documentation or artifacts as appropriate
+     - Present summary of findings for that section, highlighting warnings, errors and non applicable items (rationale for non-applicability).
+     - Get user confirmation before proceeding to next section or if any thing major do we need to halt and take corrective action
+
+   If in YOLO mode:
+
+   - Process all sections at once
+   - Create a comprehensive report of all findings
+   - Present the complete analysis to the user
+
+4. **Validation Approach**
+
+   For each checklist item:
+
+   - Read and understand the requirement
+   - Look for evidence in the documentation that satisfies the requirement
+   - Consider both explicit mentions and implicit coverage
+   - Aside from this, follow all checklist llm instructions
+   - Mark items as:
+     - ✅ PASS: Requirement clearly met
+     - ❌ FAIL: Requirement not met or insufficient coverage
+     - ⚠️ PARTIAL: Some aspects covered but needs improvement
+     - N/A: Not applicable to this case
+
+5. **Section Analysis**
+
+   For each section:
+
+   - think step by step to calculate pass rate
+   - Identify common themes in failed items
+   - Provide specific recommendations for improvement
+   - In interactive mode, discuss findings with user
+   - Document any user decisions or explanations
+
+6. **Final Report**
+
+   Prepare a summary that includes:
+
+   - Overall checklist completion status
+   - Pass rates by section
+   - List of failed items with context
+   - Specific recommendations for improvement
+   - Any sections or items marked as N/A with justification
+
+## Checklist Execution Methodology
+
+Each checklist now contains embedded LLM prompts and instructions that will:
+
+1. **Guide thorough thinking** - Prompts ensure deep analysis of each section
+2. **Request specific artifacts** - Clear instructions on what documents/access is needed
+3. **Provide contextual guidance** - Section-specific prompts for better validation
+4. **Generate comprehensive reports** - Final summary with detailed findings
+
+The LLM will:
+
+- Execute the complete checklist validation
+- Present a final report with pass/fail rates and key findings
+- Offer to provide detailed analysis of any section, especially those with warnings or failures

package/expansion-packs/expansion-creator/manifest.yml

@@ -0,0 +1,12 @@
+name: bmad-creator-tools
+version: 1.0.0
+description: Tools for creating and extending BMAD framework components
+type: creator-tools
+compatibility:
+  bmad-version: '>=4.0.0'
+components:
+  agents:
+    - bmad-the-creator
+  tasks:
+    - create-agent
+    - generate-expansion-pack

package/{creator-tools → expansion-packs/expansion-creator}/tasks/create-agent.md

@@ -55,7 +55,7 @@ Determine:
 
 **Track Created Items:**
 
-```text
+````text
 Created during agent setup:
 - Tasks:
   - [ ] task-name-1.md
@@ -63,7 +63,7 @@ Created during agent setup:
 - Templates:
   - [ ] template-name-1.md
   - [ ] template-name-2.md
-```
+```text
 
 ### 4. Create Agent File
 
@@ -121,7 +121,7 @@ Present to the user:
    1. Review and customize the created tasks/templates
    2. Run npm run build:agents
    3. Test the agent thoroughly
-```
+```text
 
 ## Template Reference
 
@@ -136,7 +136,7 @@ The agent template structure:
 
 ## Example Usage
 
-````yaml
+```yaml
 agent:
   name: Data Analyst
   id: data-analyst