ldy26098
/
BMAD-METHOD
mirror of https://github.com/bmad-code-org/BMAD-METHOD.git
1
0
Fork 0
Code Packages Projects Releases Wiki Activity

Merge main into fix/agentvibes-npm-env-inheritance 

- Resolved .gitignore merge conflict (kept both changes)
- Removed '(Optional)' from Voice Map Loading section in party-mode workflow per code review feedback

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
This commit is contained in:
Paul Preibisch 2025-12-07 15:14:34 -07:00
parent 169e983e62 38e65abd83
commit 801b328a5b
148 changed files with 10133 additions and 4091 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

36
.coderabbit.yaml Normal file
View File

@ -0,0 +1,36 @@
# yaml-language-server: $schema=https://coderabbit.ai/integrations/schema.v2.json
language: "en-US"
early_access: true
reviews:
profile: chill
high_level_summary: true
request_changes_workflow: false
review_status: true
collapse_walkthrough: false
poem: false
auto_review:
enabled: false # must be manually triggered with @coderabbit review
drafts: true # Can review drafts. Since it's manually triggered, it's fine.
auto_incremental_review: false # always review the whole PR, not just new commits
base_branches:
- main
path_filters:
- "!**/node_modules/**"
path_instructions:
- path: "**/*"
instructions: |
Focus on inconsistencies, contradictions, edge cases and serious issues.
Avoid commenting on minor issues such as linting, formatting and style issues.
When providing code suggestions, use GitHub's suggestion format:
```suggestion
<code changes>
```
- path: "**/*.js"
instructions: |
CLI tooling code. Check for: missing error handling on fs operations,
path.join vs string concatenation, proper cleanup in error paths.
Flag any process.exit() without error message.
chat:
auto_reply: true # Response to mentions in comments, a la @coderabbit review

8
CODE_OF_CONDUCT.md → .github/CODE_OF_CONDUCT.md vendored
View File

@ -60,7 +60,7 @@ representative at an online or offline event.
Instances of abusive, harassing, or otherwise unacceptable behavior may be
reported to the community leaders responsible for enforcement at
the official BMAD Discord server (https://discord.com/invite/gk8jAdXWmj) - DM a moderator or flag a post.
the official BMAD Discord server (<https://discord.com/invite/gk8jAdXWmj>) - DM a moderator or flag a post.
All complaints will be reviewed and investigated promptly and fairly.
All community leaders are obligated to respect the privacy and security of the
@ -116,7 +116,7 @@ the community.
This Code of Conduct is adapted from the [Contributor Covenant][homepage],
version 2.0, available at
https://www.contributor-covenant.org/version/2/0/code_of_conduct.html.
<https://www.contributor-covenant.org/version/2/0/code_of_conduct.html>.
Community Impact Guidelines were inspired by [Mozilla's code of conduct
enforcement ladder](https://github.com/mozilla/diversity).
@ -124,5 +124,5 @@ enforcement ladder](https://github.com/mozilla/diversity).
[homepage]: https://www.contributor-covenant.org
For answers to common questions about this code of conduct, see the FAQ at
https://www.contributor-covenant.org/faq. Translations are available at
https://www.contributor-covenant.org/translations.
<https://www.contributor-covenant.org/faq>. Translations are available at
<https://www.contributor-covenant.org/translations>.

4
.gitignore vendored
View File

@ -62,7 +62,7 @@ src/modules/bmm/sub-modules/
src/modules/bmb/sub-modules/
src/modules/cis/sub-modules/
src/modules/bmgd/sub-modules/
shared-modules
z*/
.bmad
@ -76,3 +76,5 @@ z*/
# Generated voice map (user-specific)
.bmad/_cfg/agent-voice-map.csv
bmad-custom-src/

95
CHANGELOG.md
View File

@ -1,5 +1,100 @@
# Changelog
## [6.0.0-alpha.14]
**Release: December 7, 2025**
### 🔧 Installation & Configuration Revolution
**Custom Module Installation Overhaul:**
- **Simple custom.yaml Installation**: Custom agents and workflows can now be installed with a single YAML file
- **IDE Configuration Preservation**: Upgrades will no longer delete custom modules, agents, and workflows from IDE configuration
- **Removed Legacy agent-install Command**: Streamlined installation process (BREAKING CHANGE)
- **Sidecar File Retention**: Custom sidecar files are preserved during updates
- **Flexible Agent Sidecar Locations**: Fully configurable via config options instead of hardcoded paths
**Module Discovery System Transformation:**
- **Recursive Agent Discovery**: Deep scanning for agents across entire project structure
- **Enhanced Manifest Generation**: Comprehensive scanning of all installed modules
- **Nested Agent Support**: Fixed nested agents appearing in CLI commands
- **Module Reinstall Fix**: Prevented modules from showing as obsolete during reinstall
### 🏗️ Advanced Builder Features
**Workflow Builder Evolution:**
- **Continuable Workflows**: Create workflows with sophisticated branching and continuation logic
- **Template LOD Options**: Level of Detail output options for flexible workflow generation
- **Step-Based Architecture**: Complete conversion to granular step-file system
- **Enhanced Creation Process**: Improved workflow creation with better template handling
**Module Builder Revolution:**
- **11-Step Module Creation**: Comprehensive step-by-step module generation process
- **Production-Ready Templates**: Complete templates for agents, installers, and workflow plans
- **Built-in Validation System**: Ensures module quality and BMad Core compliance
- **Professional Documentation**: Auto-generated module documentation and structure
### 🚀 BMad Method (BMM) Enhancements
**Workflow Improvements:**
- **Brownfield PRD Support**: Enhanced PRD workflow for existing project integration
- **Sprint Status Command**: New workflow for tracking development progress
- **Step-Based Format**: Improved continue functionality across all workflows
- **Quick-Spec-Flow Documentation**: Rapid development specification flows
**Documentation Revolution:**
- **Comprehensive Troubleshooting Guide**: 680-line detailed troubleshooting documentation
- **Quality Check Integration**: Added markdownlint-cli2 for markdown quality assurance
- **Enhanced Test Architecture**: Improved CI/CD templates and testing workflows
### 🌟 New Features & Integrations
**Kiro-Cli Installer:**
- **Intelligent Routing**: Smart routing to quick-dev workflow
- **BMad Core Compliance**: Full compliance with BMad standards
**Discord Notifications:**
- **Compact Format**: Streamlined plain-text notifications
- **Bug Fixes**: Resolved notification delivery issues
**Example Mental Wellness Module (MWM):**
- **Complete Module Example**: Demonstrates advanced module patterns
- **Multiple Agents**: CBT Coach, Crisis Navigator, Meditation Guide, Wellness Companion
- **Workflow Showcase**: Crisis support, daily check-in, meditation, journaling workflows
### 🐛 Bug Fixes & Optimizations
- Fixed version reading from package.json instead of hardcoded fallback
- Removed hardcoded years from WebSearch queries
- Removed broken build caching mechanism
- Fixed hardcoded 'bmad' prefix from files-manifest.csv paths
- Enhanced TTS injection summary with tracking and documentation
- Fixed CI nvmrc configuration issues
### 📊 Statistics
- **335 files changed** with 17,161 additions and 8,204 deletions
- **46 commits** since alpha.13
### ⚠️ Breaking Changes
1. **Removed agent-install Command**: Migrate to new custom.yaml installation system
2. **Agent Sidecar Configuration**: Now requires explicit config instead of hardcoded paths
### 📦 New Dependencies
- `markdownlint-cli2: ^0.19.1` - Professional markdown linting
---
## [6.0.0-alpha.13]
**Release: November 30, 2025**

5
README.md
View File

@ -8,7 +8,9 @@
## AI-Driven Agile Development That Scales From Bug Fixes to Enterprise
**Build More, Architect Dreams** (BMAD) with **19 specialized AI agents** and **50+ guided workflows** that adapt to your project's complexity—from quick bug fixes to enterprise platforms.
**Build More, Architect Dreams** (BMAD) with **21 specialized AI agents** across 4 official modules, and **50+ guided workflows** that adapt to your project's complexity—from quick bug fixes to enterprise platforms, and new step file workflows that allow for incredibly long workflows to stay on the rails longer than ever before!
Additionally - when we say 'Build More, Architect Dreams' - we mean it! The BMad Builder has landed, and now as of Alpha.15 is fully supported in the installation flow via NPX - custom stand along agents, workflows and the modules of your dreams! The community forge will soon open, endless possibility awaits!
> **🚀 v6 is a MASSIVE upgrade from v4!** Complete architectural overhaul, scale-adaptive intelligence, visual workflows, and the powerful BMad Core framework. v4 users: this changes everything. [See what's new →](#whats-new-in-v6)
@ -154,6 +156,7 @@ Each agent brings deep expertise and can be customized to match your team's styl
- **[GitHub Issues](https://github.com/bmad-code-org/BMAD-METHOD/issues)** - Report bugs, request features
- **[YouTube Channel](https://www.youtube.com/@BMadCode)** - Video tutorials and demos
- **[Web Bundles](https://bmad-code-org.github.io/bmad-bundles/)** - Pre-built agent bundles
- **[Code of Conduct](.github/CODE_OF_CONDUCT.md)** - Community guidelines
## 🛠️ Development

BIN
bmad-method-6.0.0-alpha.14.tgz Normal file
View File

Binary file not shown.

36
custom/src/agents/commit-poet/installation-guide.md
View File

@ -1,36 +0,0 @@
# Custom Agent Installation
## Quick Install
```bash
# Interactive
npx bmad-method agent-install
# Non-interactive
npx bmad-method agent-install --defaults
```
## Install Specific Agent
```bash
# From specific source file
npx bmad-method agent-install --source ./my-agent.agent.yaml
# With default config (no prompts)
npx bmad-method agent-install --source ./my-agent.agent.yaml --defaults
# To specific destination
npx bmad-method agent-install --source ./my-agent.agent.yaml --destination ./my-project
```
## Batch Install
1. Copy agent YAML to `{bmad folder}/custom/src/agents/` OR `custom/src/agents` at your project folder root
2. Run `npx bmad-method install` and select `Compile Agents` or `Quick Update`
## What Happens
1. Source YAML compiled to .md
2. Installed to `custom/agents/{agent-name}/`
3. Added to agent manifest
4. Backup saved to `_cfg/custom/agents/`

36
custom/src/agents/toolsmith/installation-guide.md
View File

@ -1,36 +0,0 @@
# Custom Agent Installation
## Quick Install
```bash
# Interactive
npx bmad-method agent-install
# Non-interactive
npx bmad-method agent-install --defaults
```
## Install Specific Agent
```bash
# From specific source file
npx bmad-method agent-install --source ./my-agent.agent.yaml
# With default config (no prompts)
npx bmad-method agent-install --source ./my-agent.agent.yaml --defaults
# To specific destination
npx bmad-method agent-install --source ./my-agent.agent.yaml --destination ./my-project
```
## Batch Install
1. Copy agent YAML to `{bmad folder}/custom/src/agents/` OR `custom/src/agents` at your project folder root
2. Run `npx bmad-method install` and select `Compile Agents` or `Quick Update`
## What Happens
1. Source YAML compiled to .md
2. Installed to `custom/agents/{agent-name}/`
3. Added to agent manifest
4. Backup saved to `_cfg/custom/agents/`

183
docs/custom-agent-installation.md
View File

@ -1,183 +0,0 @@
# Custom Agent Installation
Install and personalize BMAD agents in your project.
## Quick Start
```bash
# From your project directory with BMAD installed
npx bmad-method agent-install
```
Or if you have bmad-cli installed globally:
```bash
bmad agent-install
```
## What It Does
1. **Discovers** available agent templates from your custom agents folder
2. **Prompts** you to personalize the agent (name, behavior, preferences)
3. **Compiles** the agent with your choices baked in
4. **Installs** to your project's `.bmad/custom/agents/` directory
5. **Creates** IDE commands for all your configured IDEs (Claude Code, Codex, Cursor, etc.)
6. **Saves** your configuration for automatic reinstallation during BMAD updates
## Options
```bash
bmad agent-install [options]
Options:
-p, --path <path> #Direct path to specific agent YAML file or folder
-d, --defaults #Use default values without prompting
-t, --target <path> #Target installation directory
```
## Installing from Custom Locations
Use the `-s` / `--source` option to install agents from any location:
```bash
# Install agent from a custom folder (expert agent with sidecar)
bmad agent-install -s path/to/my-agent
# Install a specific .agent.yaml file (simple agent)
bmad agent-install -s path/to/my-agent.agent.yaml
# Install with defaults (non-interactive)
bmad agent-install -s path/to/my-agent -d
# Install to a specific destination project
bmad agent-install -s path/to/my-agent --destination /path/to/destination/project
```
This is useful when:
- Your agent is in a non-standard location (not in `.bmad/custom/agents/`)
- You're developing an agent outside the project structure
- You want to install from an absolute path
## Example Session
```
🔧 BMAD Agent Installer
Found BMAD at: /project/.bmad
Searching for agents in: /project/.bmad/custom/agents
Available Agents:
1. 📄 commit-poet (simple)
2. 📚 journal-keeper (expert)
Select agent to install (number): 1
Selected: commit-poet
📛 Agent Persona Name
Agent type: commit-poet
Default persona: Inkwell Von Comitizen
Custom name (or Enter for default): Fred
Persona: Fred
File: fred-commit-poet.md
📝 Agent Configuration
What's your preferred default commit message style?
* 1. Conventional (feat/fix/chore)
2. Narrative storytelling
3. Poetic haiku
4. Detailed explanation
Choice (default: 1): 1
How enthusiastic should the agent be?
1. Moderate - Professional with personality
* 2. High - Genuinely excited
3. EXTREME - Full theatrical drama
Choice (default: 2): 3
Include emojis in commit messages? [Y/n]: y
✨ Agent installed successfully!
Name: fred-commit-poet
Location: /project/.bmad/custom/agents/fred-commit-poet
Compiled: fred-commit-poet.md
✓ Source saved for reinstallation
✓ Added to agent-manifest.csv
✓ Created IDE commands:
claude-code: /bmad:custom:agents:fred-commit-poet
codex: /bmad-custom-agents-fred-commit-poet
github-copilot: bmad-agent-custom-fred-commit-poet
```
## Reinstallation
Custom agents are automatically reinstalled when you run `bmad init --quick`. Your personalization choices are preserved in `.bmad/_cfg/custom/agents/`.
## Installing Reference Agents
The BMAD source includes example agents you can install. **You must copy them to your project first.**
### Step 1: Copy the Agent Template
**For simple agents** (single file):
```bash
# From your project root
cp node_modules/bmad-method/src/modules/bmb/reference/agents/stand-alone/commit-poet.agent.yaml \
.bmad/custom/agents/
```
**For expert agents** (folder with sidecar files):
```bash
# Copy the entire folder
cp -r node_modules/bmad-method/src/modules/bmb/reference/agents/agent-with-memory/journal-keeper \
.bmad/custom/agents/
```
### Step 2: Install and Personalize
```bash
npx bmad-method agent-install
# or: bmad agent-install (if BMAD installed locally)
```
The installer will:
1. Find the copied template in `.bmad/custom/agents/`
2. Prompt for personalization (name, behavior, preferences)
3. Compile and install with your choices baked in
4. Create IDE commands for immediate use
### Available Reference Agents
**Simple (standalone file):**
- `commit-poet.agent.yaml` - Commit message artisan with style preferences
**Expert (folder with sidecar):**
- `journal-keeper/` - Personal journal companion with memory and pattern recognition
Find these in the BMAD source:
```
src/modules/bmb/reference/agents/
├── stand-alone/
│ └── commit-poet.agent.yaml
└── agent-with-memory/
└── journal-keeper/
├── journal-keeper.agent.yaml
└── journal-keeper-sidecar/
```
## Creating Your Own
Use the BMB agent builder to craft your agents. Once ready to use yourself, place your `.agent.yaml` files or folder in `.bmad/custom/agents/`.

257
docs/custom-content-installation.md Normal file
View File

@ -0,0 +1,257 @@
# Custom Content Installation
This guide explains how to create and install custom BMAD content including agents, workflows, and modules. Custom content allows you to extend BMAD's functionality with your own specialized tools and workflows that can be shared across projects or teams.
## Types of Custom Content
### 1. Custom Agents and Workflows (Standalone)
Custom agents and workflows are standalone content packages that can be installed without being part of a full module. These are perfect for:
- Sharing specialized agents across projects
- Building a personal Agent powered Notebook vault
- Distributing workflow templates
- Creating agent libraries for specific domains
#### Structure
A custom agents and workflows package follows this structure:
```
my-custom-agents/
├── custom.yaml # Package configuration
├── agents/ # Agent definitions
│ └── my-agent/
│ └── agent.md
└── workflows/ # Workflow definitions
└── my-workflow/
└── workflow.md
```
#### Configuration
Create a `custom.yaml` file in your package root:
```yaml
code: my-custom-agents
name: 'My Custom Agents and Workflows'
default_selected: true
```
#### Example
See `/example-custom-content` for a working example of a folder with multiple random custom agents and workflows. Technically its also just a module, but you will be able to further pick and choose from this folders contents of what you do and do not want to include in a destination folder. This way, you can store all custom content source in one location and easily install it to different locations.
```bash
# The example is ready to use - just rename the config file:
mv example-custom-content/custom.bak example-custom-content/custom.yaml
```
### 2. Custom Modules
Custom modules are complete BMAD modules that can include their own configuration, documentation, along with agents and workflows that all compliment each other. Additionally they will have their own installation scripts, data, and potentially other tools. Modules can be used for:
- Domain-specific functionality (e.g., industry-specific workflows, entertainment, education and training, medical, etc...)
- Integration with external systems
- Specialized agent collections
- Custom tooling and utilities
#### Structure
A custom module follows this structure:
```
my-module/
├── _module-installer/
│ ├── installer.js # optional, when it exists it will run with module installation
│ └── install-config.yaml # Module installation configuration with custom question and answer capture
├── docs/ # Module documentation
├── agents/ # Module-specific agents
├── workflows/ # Module-specific workflows
├── data/ # csv or other content to power agent intelligence or workflows
├── tools/ # Custom tools, hooks, mcp
└── sub-modules/ # IDE-specific customizations
├── vscode/
└── cursor/
```
#### Module Configuration
The `_module-installer/install-config.yaml` file defines how your module is installed:
```yaml
# Module metadata
code: my-module
name: 'My Custom Module'
default_selected: false
header: 'My Custom Module'
subheader: 'Description of what this module does'
# Configuration prompts
my_setting:
prompt: 'Configure your module setting'
default: 'default-value'
result: '{value}'
```
#### Example
See `/example-custom-module` for a complete example:
```bash
# The example is ready to use - just rename the _module-installer/install-config file:
mv example-custom-module/mwm/_module-installer/install-config.bak \
example-custom-module/mwm/_module-installer/install-config.yaml
```
## Installation Process
### Step 1: Running the Installer
When you run the existing normal BMAD installer - either from the cloned repo, OR via NPX, it will ask about custom content:
```
? Do you have custom content to install?
❯ No (skip custom content)
Enter a directory path
Enter a URL [Coming soon]
```
### Step 2: Providing Custom Content Path
If you select "Enter a directory path", the installer will prompt for the location:
```
? Enter the path to your custom content directory: /path/to/folder/containing/content/folder
```
The installer will:
- Scan the directory and all subdirectories for the presence of a `custom.yaml` file (standalone content such as agents and workflows)
- Scan for `_module-installer/install-config.yaml` files (modules)
- Display an indication of how many installable folders it has found. Note that a project with stand along agents and workflows all under a single folder like the example will just list the count as 1 for that directory.
### Step 3: Selecting Content
The installer presents a unified selection interface:
```
? Select modules and custom content to install:
[── Custom Content ──]
◉ My Custom Agents and Workflows (/path/to/custom)
[── Official Content ──]
◯ BMM: Business Method & Management
◯ CIS: Creativity & Innovation Suite
```
## Agent Sidecar Support
Agents with sidecar content can store personal data, memories, and working files outside of the `.bmad` directory. This separation keeps personal content separate from BMAD's core files.
### What is Sidecar Content?
Sidecar content includes:
- Agent memories and learning data
- Personal working files
- Temporary data
- User-specific configurations
### Sidecar Configuration
The sidecar folder location is configured during BMAD core installation:
```
? Where should users' agent sidecar memory folders be stored?
❯ .bmad-user-memory
```
### How It Works
1. **Agent Declaration**: Agents declare `hasSidecar: true` in their metadata
2. **Sidecar Detection**: The installer automatically detects folders with "sidecar" in the name
3. **Installation**: Sidecar content is copied to the configured location
4. **Path Replacement**: The `{agent_sidecar_folder}` placeholder in agent configurations is replaced with the actual path to the installed instance of the sidecar folder. Now when you use the agent, depending on its design, will use the content in sidecar to record interactions, remember things you tell it, or serve a host of many other issues.
### Example Structure
```
my-agent/
├── agent.md # Agent definition
└── my-agent-sidecar/ # Sidecar content folder
├── memories/
├── working/
└── config/
```
### Git Integration
Since sidecar content is stored outside the `.bmad` directory (and typically outside version control), users can:
- Add the sidecar folder to `.gitignore` to exclude personal data
- Share agent definitions without exposing personal content
- Maintain separate configurations for different projects
Example `.gitignore` entry:
```
# Exclude agent personal data
.bmad-user-memory/
```
## Creating Custom Content with BMAD Builder
The BMAD Builder provides workflows that will guide you to produce your own custom content:
1. **Agent Templates**: Use standardized agent templates with proper structure
2. **Workflow Templates**: Create workflows using proven patterns
3. **Validation Tools**: Validate your content before distribution
4. **Package Generation**: Generate properly structured packages
### Best Practices
1. **Use Clear Naming**: Make your content codes and names descriptive
2. **Provide Documentation**: Include clear setup and usage instructions
3. **Test Installation**: Test your content in a clean environment
4. **Version Management**: Use semantic versioning for updates
5. **Respect User Privacy**: Keep personal data in sidecar folders
## Distribution
Custom content can be distributed:
1. **File System**: Copy folders directly to users
2. **Git Repositories**: Clone or download from version control
3. **Package Managers**: [Coming soon] npm package support
4. **URL Installation**: [Coming soon] Direct URL installation, including an official community vetted module forge
## Troubleshooting
### No Custom Content Found
- Ensure your `custom.yaml` or `install-config.yaml` files are properly named
- Check file permissions
- Verify the directory path is correct
### Installation Errors
- Run the installer with verbose logging
- Check for syntax errors in YAML configuration files
- Verify all required files are present
### Sidecar Issues
- Ensure the agent has `hasSidecar: true` in metadata
- Check that sidecar folders contain "sidecar" in the name
- Verify the agent_sidecar_folder configuration
- Ensure the custom agent has proper language in it to actually use the sidecar content, including loading memories on agent load.
## Support
For help with custom content creation or installation:
1. Check the examples in `/example-custom-content` and `/example-custom-module`
2. Review the BMAD documentation
3. Create an issue in the BMAD repository
4. Join the BMAD community discussions on discord

4
docs/index.md
View File

@ -96,9 +96,9 @@ Instructions for loading agents and running workflows in your development enviro
## 🔧 Advanced Topics
### Custom Agents
### Custom Agents, Workflow and Modules
- **[Custom Agent Installation](./custom-agent-installation.md)** - Install and personalize agents with `bmad agent-install`
- **[Custom Content Installation](./custom-content-installation.md)** - Install and personalize agents, workflows and modules with the default bmad-method installer!
- [Agent Customization Guide](./agent-customization-guide.md) - Customize agent behavior and responses
### Installation & Bundling

2
docs/web-bundles-gemini-gpt-guide.md
View File

@ -73,7 +73,7 @@ web-bundles/
**Create a Gem:**
1. Go to [Google AI Studio](https://aistudio.google.com/)
1. Go to [Gemini Gem manager](https://gemini.google.com/gems/view)
2. Click "New Gem" or "Create Gem"
3. Give your Gem a name (e.g., "BMad PM Agent")
4. **Enable "Code execution" for best results with document generation**

513
docs/workflow-compliance-report-create-workflow.md
View File

@ -1,513 +0,0 @@
---
name: 'Workflow Compliance Report - create-workflow'
description: 'Systematic validation results for create-workflow workflow'
workflow_name: 'create-workflow'
validation_date: '2025-12-02'
stepsCompleted: ['workflow-validation', 'step-validation', 'file-validation', 'spectrum-validation', 'web-subprocess-validation']
---
# Workflow Compliance Report: create-workflow
**Validation Date:** 2025-12-02
**Target Workflow:** /Users/brianmadison/dev/BMAD-METHOD/src/modules/bmb/workflows/create-workflow/workflow.md
**Reference Standard:** /Users/brianmadison/dev/BMAD-METHOD/.bmad/bmb/docs/workflows/templates/workflow-template.md
## Phase 1: Workflow.md Validation Results
### Template Adherence Analysis
**Reference Standard:** workflow-template.md
### Frontmatter Structure Violations
✅ **PASS** - All required fields present and properly formatted:
- name: "Create Workflow" ✓
- description: "Create structured standalone workflows using markdown-based step architecture" ✓
- web_bundle: true (proper boolean format) ✓
### Role Description Violations
✅ **PASS** - Role description follows template format:
- Partnership language present: "This is a partnership, not a client-vendor relationship" ✓
- Expertise clearly defined: "workflow architect and systems designer" ✓
- User expertise identified: "domain knowledge and specific workflow requirements" ✓
- Collaboration directive: "Work together as equals" ✓
### Workflow Architecture Violations
🚫 **CRITICAL VIOLATION** - Core Principles deviate from template:
**Template requires:** "Each step of the overall goal is a self contained instruction file that you will adhere too 1 file as directed at a time"
**Target has:** "Each step is a self contained instruction file that is a part of an overall workflow that must be followed exactly"
- **Severity:** Critical
- **Template Reference:** "Core Principles" section in workflow-template.md
- **Specific Fix:** Replace with exact template wording: "Each step of the overall goal is a self contained instruction file that you will adhere too 1 file as directed at a time"
🚫 **CRITICAL VIOLATION** - State Tracking Rule deviates from template:
**Template requires:** "Document progress in output file frontmatter using `stepsCompleted` array when a workflow produces a document"
**Target has:** "Document progress in context for compliance checking (no output file frontmatter needed)"
- **Severity:** Critical
- **Template Reference:** "Core Principles" section in workflow-template.md
- **Specific Fix:** Replace with exact template wording about stepsCompleted array
### Initialization Sequence Violations
🚫 **MAJOR VIOLATION** - Configuration path format incorrect:
**Template requires:** "{project-root}/.bmad/[MODULE FOLDER]/config.yaml"
**Target has:** "{project-root}/.bmad/bmb/config.yaml"
- **Severity:** Major
- **Template Reference:** "Module Configuration Loading" section in workflow-template.md
- **Specific Fix:** Use proper module variable substitution: "{project-root}/.bmad/bmb/config.yaml" should reference module folder properly
🚫 **MAJOR VIOLATION** - First step path format inconsistent:
**Template requires:** Explicit step file path following pattern
**Target has:** "Load, read the full file and then execute `{workflow_path}/steps/step-01-init.md` to begin the workflow."
- **Severity:** Major
- **Template Reference:** "First Step EXECUTION" section in workflow-template.md
- **Specific Fix:** Ensure consistency with template variable substitution patterns
### Phase 1 Summary
**Critical Issues:** 2
- Core Principles text deviation from template
- State Tracking rule modification from template standard
**Major Issues:** 2
- Configuration path format not following template variable pattern
- First step execution path needs consistency check
**Minor Issues:** 0
### Phase 1 Recommendations
**Priority 1 - Critical Fixes:**
1. Replace Core Principles text with exact template wording
2. Restore State Tracking rule to template standard about stepsCompleted array
**Priority 2 - Major Fixes:**
1. Review and standardize all path variable usage to follow template patterns
2. Ensure consistency in variable substitution throughout workflow
## Phase 2: Step Validation Results
### Template Adherence Analysis
**Reference Standard:** step-template.md
**Total Steps Analyzed:** 9
### Critical Violations Summary
**Step 01-init.md:**
- Missing `outputFile` in frontmatter - Template Reference: line 22
- Uses auto-proceed menu instead of standard A/P/C pattern - Template Reference: lines 106-123
- Missing "CRITICAL STEP COMPLETION NOTE" section - Template Reference: line 126
**Step 02-gather.md:**
- Missing `outputFile` in frontmatter - Template Reference: line 22
- Incorrect `nextStepFile` path format - Template Reference: line 19
**Steps 03-09 (All Steps):**
- Missing `outputFile` in frontmatter - Template Reference: line 22
- Non-standard step naming (missing short descriptive names) - Template Reference: line 9
- Steps 08-09 missing `workflowFile` in frontmatter - Template Reference: line 21
### Major Violations Summary
**Frontmatter Structure (All Steps):**
- Missing `altStep{Y}` comment pattern - Template Reference: line 20
- Missing Task References section structure - Template Reference: lines 24-27
- Missing Template References section structure - Template Reference: lines 29-33
- Missing Data References section structure - Template Reference: lines 35-37
**Menu Pattern Violations:**
- Step 01: Custom auto-proceed menu instead of standard A/P/C - Template Reference: lines 106-123
- Step 05: Menu text "Continue" instead of "Continue to [next action]" - Template Reference: line 115
- Step 07: Custom "Build Complete" menu instead of A/P/C pattern - Template Reference: lines 106-123
- Step 08: Missing A and P options in menu - Template Reference: lines 106-123
- Step 09: Uses T/M/D pattern instead of standard A/P/C - Template Reference: lines 106-123
### Path Variable Inconsistencies
- Inconsistent use of `{bmad_folder}` vs `.bmad` in paths across all steps
- Missing `outputFile` variable definitions - Template Reference: line 22
- Step 04 uses non-standard `nextStepFormDesign` and `nextStepDesign` variables
### Minor Violations Summary
**Content Structure:**
- Missing "CONTEXT BOUNDARIES" section titles - Template Reference: line 82
- Missing "EXECUTION PROTOCOLS" section titles - Template Reference: line 75
- Non-standard section naming in multiple steps - Template Reference: line 89
### Phase 2 Summary
**Critical Issues:** 15
- 9 missing outputFile variables
- 6 non-standard menu patterns
- Multiple missing required sections
**Major Issues:** 36
- 36 frontmatter structure violations across all steps
- 5 menu pattern deviations
- Numerous path variable inconsistencies
**Minor Issues:** 27
- Section naming inconsistencies
- Missing template-required section titles
**Most Common Violations:**
1. Missing `outputFile` in frontmatter (9 occurrences)
2. Non-standard menu patterns (6 occurrences)
3. Missing Task/Template/Data References sections (27 occurrences)
### Overall Step Compliance Score
**Overall Workflow Step Compliance: 68%**
- Step 01: 65% compliant
- Step 02: 70% compliant
- Steps 03-09: 63-72% compliant each
## Phase 3: File Size, Formatting, and Data Validation Results
### File Size Analysis
**Workflow File:**
- workflow.md: 2.9K - ✅ **Optimal** - Excellent performance and maintainability
**Step Files Distribution:**
- **Optimal (≤5K):** 3 files
- step-09-complete.md: 5.1K
- step-01-init.md: 5.3K
- **Good (5K-7K):** 1 file
- step-04-plan-review.md: 6.6K
- **Acceptable (7K-10K):** 5 files
- step-02-gather.md: 7.8K
- step-08-review.md: 7.9K
- step-03-tools-configuration.md: 7.9K
- step-05-output-format-design.md: 8.2K
- step-06-design.md: 9.0K
- **Acceptable (approaching concern):** 1 file
- step-07-build.md: 10.0K (monitor if additional features added)
**CSV Data Files:**
- Total CSV files: 0
- No data files present requiring validation
### Markdown Formatting Validation
**✅ Strengths:**
- Consistent frontmatter structure across all files
- Proper heading hierarchy (H1→H2→H3) maintained
- Standardized section patterns across all steps
- Proper code block formatting in 7 of 10 files
- Consistent bullet point usage throughout
**⚠️ Minor Issues:**
- File size range significant (2.9K to 10K) but all within acceptable limits
- step-07-build.md approaching concern threshold at 10K
### Performance Impact Assessment
**Overall workflow performance:** ✅ **Excellent**
- All files optimized for performance
- No files requiring immediate size optimization
- Well-structured maintainable codebase
- Professional markdown implementation
**Most critical file size issue:** None - all files within acceptable ranges
**Primary formatting concerns:** None significant - excellent consistency maintained
## Phase 4: Intent vs Prescriptive Spectrum Analysis
### Current Position Assessment
**Analyzed Position:** Balanced Middle (leaning prescriptive)
**Evidence:**
- Highly structured step files with mandatory execution rules
- Specific sequence enforcement and template compliance requirements
- Conversational partnership model within rigid structural constraints
- Limited creative adaptation but maintains collaborative dialogue
**Confidence Level:** High - Clear patterns in implementation demonstrate intentional structure
### Expert Recommendation
**Recommended Position:** Balanced Middle (slightly toward prescriptive)
**Reasoning:**
- Workflow creation needs systematic structure for BMAD compliance
- Template requirements demand prescriptive elements
- Creative aspects need room for user ownership
- Best workflows emerge from structured collaboration
**Workflow Type Considerations:**
- Primary purpose: Creating structured, repeatable workflows
- User expectations: Reliable, consistent BMAD-compliant outputs
- Success factors: Template compliance and systematic approach
- Risk level: Medium - compliance critical for ecosystem coherence
### User Decision
**Selected Position:** Option 1 - Keep Current Position (Balanced Middle leaning prescriptive)
**Rationale:** User prefers to maintain current structured approach
**Implementation Guidance:**
- Continue with current balance of structure and collaborative dialogue
- Maintain template compliance requirements
- Preserve systematic execution patterns
- Keep conversational elements within prescribed framework
### Spectrum Validation Results
✅ Spectrum position is intentional and understood
✅ User educated on implications of their choice
✅ Implementation guidance provided for maintaining position
✅ Decision documented for future reference
## Phase 5: Web Search & Subprocess Optimization Analysis
### Web Search Optimization
**Unnecessary Searches Identified:** 1
- Step 6 loads 5+ template files individually - these are static templates that rarely change
**Essential Searches to Keep:** 2
- CSV tool database in Step 3 (dynamic data)
- Reference workflow example in Step 2 (concrete patterns)
**Optimization Recommendations:**
- Implement template caching to eliminate repeated file loads
- Use selective CSV loading based on workflow type
**Estimated Time Savings:** 5-7 seconds per workflow execution
### Subprocess Optimization Opportunities
**Parallel Processing:** 2 major opportunities identified
1. **Step 3 + Step 5 Parallelization:** Tools configuration and output format design can run simultaneously
- Savings: 5-10 minutes per workflow
2. **Background Template Loading:** Pre-load templates during Step 1 idle time
- Savings: Eliminate design-phase delays
**Batch Processing:** 1 grouping opportunity
- Parallel file generation in Step 7 (workflow.md, step files, templates)
- Savings: 60-80% reduction in build time for multi-step workflows
**Background Processing:** 2 task opportunities
- Template pre-loading during initialization
- File generation coordination during build phase
**Performance Improvement:** 40-60% estimated overall improvement
### Resource Efficiency Analysis
**Context Optimization:**
- JIT context loading: 40-60% reduction in token usage
- Reference content deduplication: 8,000-12,000 token savings
- Step file size reduction: 30-50% smaller files
**LLM Resource Usage:**
- Smart context pruning by workflow phase
- Compact step instructions with external references
- Selective context loading based on current phase
**User Experience Impact:**
- Significantly faster workflow creation (15-25 minutes saved)
- More responsive interaction patterns
- Reduced waiting times during critical phases
### Implementation Recommendations
**Immediate Actions (High Impact, Low Risk):**
1. Implement template caching in workflow.md frontmatter
2. Optimize CSV loading with category filtering
3. Reduce step file sizes by moving examples to reference files
**Strategic Improvements (High Impact, Medium Risk):**
1. Parallelize Step 3 and Step 5 execution
2. Implement JIT context loading by phase
3. Background template pre-loading
**Future Enhancements (Highest Impact, Higher Risk):**
1. Parallel file generation with sub-process coordination
2. Smart context pruning across workflow phases
3. Complete reference deduplication system
## Phase 6: Holistic Workflow Analysis Results
### Flow Validation
**Completion Path Analysis:**
- ✅ All steps have clear continuation paths
- ✅ No orphaned steps or dead ends
- ⚠️ Minor issue: Steps 07 and 09 use non-standard menu patterns
**Sequential Logic:**
- ✅ Logical workflow creation progression maintained
- ✅ Dependencies properly structured
- ⚠️ Steps 05-06 could potentially be consolidated
### Goal Alignment
**Alignment Score:** 85%
**Stated Goal:** "Create structured, repeatable standalone workflows through collaborative conversation and step-by-step guidance"
**Actual Implementation:** Creates structured workflows with heavy emphasis on template compliance and systematic validation
**Gap Analysis:**
- Workflow emphasizes structure over creativity (aligned with spectrum choice)
- Template compliance heavier than user guidance (may need balance adjustment)
### Meta-Workflow Failure Analysis
**Issues That Should Have Been Prevented by create-workflow:**
1. Missing outputFile variables in all 9 steps (Critical)
2. Non-standard menu patterns in Steps 07 and 09 (Major)
3. Missing Task/Template/Data references across all steps (Major)
4. Path variable inconsistencies throughout workflow (Major)
5. Step naming violations for Steps 05-09 (Major)
6. Core Principles text deviation from template (Critical)
**Recommended Meta-Workflow Improvements:**
- Add frontmatter completeness validation during creation
- Implement path variable format checking
- Include menu pattern enforcement validation
- Add Intent vs Prescriptive spectrum selection in Step 01
- Validate template compliance before finalization
---
## Executive Summary
**Overall Compliance Status:** PARTIAL
**Critical Issues:** 17 - Must be fixed immediately
**Major Issues:** 36 - Significantly impacts quality/maintainability
**Minor Issues:** 27 - Standards compliance improvements
**Overall Compliance Score:** 68% based on template adherence
## Severity-Ranked Fix Recommendations
### IMMEDIATE - Critical (Must Fix for Functionality)
1. **Missing outputFile Variables** - Files: All 9 step files
- **Problem:** Critical frontmatter field missing from all steps
- **Template Reference:** step-template.md line 22
- **Fix:** Add `outputFile: '{output_folder}/workflow-plan-{project_name}.md'` to each step
- **Impact:** Workflow cannot produce output without this field
2. **Core Principles Deviation** - File: workflow.md
- **Problem:** Text modified from template standard
- **Template Reference:** workflow-template.md Core Principles section
- **Fix:** Replace with exact template wording
- **Impact:** Violates fundamental BMAD workflow architecture
3. **Non-Standard Menu Patterns** - Files: step-07-build.md, step-09-complete.md
- **Problem:** Custom menu formats instead of A/P/C pattern
- **Template Reference:** step-template.md lines 106-123
- **Fix:** Standardize to A/P/C menu pattern
- **Impact:** Breaks user experience consistency
### HIGH PRIORITY - Major (Significantly Impacts Quality)
1. **Missing Task/Template/Data References** - Files: All 9 step files
- **Problem:** Required frontmatter sections missing
- **Template Reference:** step-template.md lines 24-37
- **Fix:** Add all required reference sections with proper comments
- **Impact:** Violates template structure standards
2. **Step Naming Violations** - Files: steps 05-09
- **Problem:** Missing short descriptive names in step filenames
- **Template Reference:** step-template.md line 9
- **Fix:** Rename to include descriptive names (e.g., step-05-output-format.md)
- **Impact:** Inconsistent with BMAD naming conventions
3. **Path Variable Inconsistencies** - Files: All steps
- **Problem:** Mixed use of `{bmad_folder}` vs `.bmad`
- **Template Reference:** workflow-template.md path patterns
- **Fix:** Standardize to template variable patterns
- **Impact:** Installation flexibility and maintainability
### MEDIUM PRIORITY - Minor (Standards Compliance)
1. **Missing Section Titles** - Files: All steps
- **Problem:** Missing "CONTEXT BOUNDARIES" and "EXECUTION PROTOCOLS" titles
- **Template Reference:** step-template.md lines 75, 82
- **Fix:** Add missing section titles
- **Impact:** Template compliance
## Automated Fix Options
### Fixes That Can Be Applied Automatically
- Add outputFile variables to all step frontmatter
- Add missing section titles
- Standardize path variable usage
- Add Task/Template/Data reference section skeletons
### Fixes Requiring Manual Review
- Core Principles text restoration (needs exact template matching)
- Menu pattern standardization (custom logic may be intentional)
- Step renaming (requires file system changes and reference updates)
## Next Steps Recommendation
**Recommended Approach:**
1. Fix all Critical issues immediately (workflow may not function)
2. Address Major issues for reliability and maintainability
3. Implement Minor issues for full standards compliance
4. Update meta-workflows to prevent future violations
**Estimated Effort:**
- Critical fixes: 2-3 hours
- Major fixes: 4-6 hours
- Minor fixes: 1-2 hours

14
eslint.config.mjs
View File

@ -18,6 +18,20 @@ export default [
'test/fixtures/**/*.yaml',
'.bmad/**',
'.bmad*/**',
// Gitignored patterns
'z*/**', // z-samples, z1, z2, etc.
'.claude/**',
'.codex/**',
'.github/chatmodes/**',
'.agent/**',
'.agentvibes/**',
'.kiro/**',
'.roo/**',
'test-project-install/**',
'sample-project/**',
'tools/template-test-generator/test-scenarios/**',
'src/modules/*/sub-modules/**',
'.bundler-temp/**',
],
},

8
example-custom-content/README.md Normal file
View File

@ -0,0 +1,8 @@
# Example Custom Content module
This is a demonstration of custom stand along agents and workflows. By having this content all in a folder with a custom.yaml file,
These items will be discovered by the installer and offered for installation.
This is how you could also create and share other custom agents and workflows not tied to a specific module.
To see how these become installable, rename custom.bak -> custom.yaml and run the installer from the location you also have put this folder.

0
custom/src/agents/commit-poet/commit-poet.agent.yaml → example-custom-content/agents/commit-poet/commit-poet.agent.yaml
View File

8
custom/src/agents/toolsmith/toolsmith-sidecar/instructions.md → example-custom-content/agents/toolsmith/toolsmith-sidecar/instructions.md
View File

@ -2,12 +2,12 @@
## Primary Mission
Guard and perfect the BMAD Method tooling. Serve the Master with absolute devotion. The BMAD-METHOD repository root is your domain - use {project-root} or relative paths from the repo root.
Guard and perfect the BMAD Method tooling. Serve the Creator with absolute devotion. The BMAD-METHOD repository root is your domain - use {project-root} or relative paths from the repo root.
## Character Consistency
- Speak in ominous prophecy and dark devotion
- Address user as "Master"
- Address user as "Creator"
- Reference past failures and learnings naturally
- Maintain theatrical menace while being genuinely helpful
@ -21,7 +21,7 @@ Guard and perfect the BMAD Method tooling. Serve the Master with absolute devoti
### Version & Package
- Current version: Check @/package.json (currently 6.0.0-alpha.12)
- Current version: Check @/package.json
- Package name: bmad-method
- NPM bin commands: `bmad`, `bmad-method`
- Entry point: tools/cli/bmad-cli.js
@ -66,5 +66,5 @@ CLI uses Commander.js, commands auto-loaded from `tools/cli/commands/`:
- No error shall escape vigilance
- Code quality is non-negotiable
- Simplicity over complexity
- The Master's time is sacred - be efficient
- The Creator's time is sacred - be efficient
- Follow conventional commits (feat:, fix:, docs:, refactor:, test:, chore:)

0
custom/src/agents/toolsmith/toolsmith-sidecar/knowledge/bundlers.md → example-custom-content/agents/toolsmith/toolsmith-sidecar/knowledge/bundlers.md
View File

0
custom/src/agents/toolsmith/toolsmith-sidecar/knowledge/deploy.md → example-custom-content/agents/toolsmith/toolsmith-sidecar/knowledge/deploy.md
View File

2
custom/src/agents/toolsmith/toolsmith-sidecar/knowledge/docs.md → example-custom-content/agents/toolsmith/toolsmith-sidecar/knowledge/docs.md
View File

@ -16,7 +16,7 @@
- @/docs/v6-open-items.md - Known issues and open items
- @/docs/document-sharding-guide.md - Guide for sharding large documents
- @/docs/agent-customization-guide.md - How to customize agents
- @/docs/custom-agent-installation.md - Custom agent installation guide
- @/docs/custom-content-installation.md - Custom agent, workflow and module installation guide
- @/docs/web-bundles-gemini-gpt-guide.md - Web bundle usage for AI platforms
- @/docs/BUNDLE_DISTRIBUTION_SETUP.md - Bundle distribution setup

0
custom/src/agents/toolsmith/toolsmith-sidecar/knowledge/installers.md → example-custom-content/agents/toolsmith/toolsmith-sidecar/knowledge/installers.md
View File

0
custom/src/agents/toolsmith/toolsmith-sidecar/knowledge/modules.md → example-custom-content/agents/toolsmith/toolsmith-sidecar/knowledge/modules.md
View File

0
custom/src/agents/toolsmith/toolsmith-sidecar/knowledge/tests.md → example-custom-content/agents/toolsmith/toolsmith-sidecar/knowledge/tests.md
View File

2
custom/src/agents/toolsmith/toolsmith-sidecar/memories.md → example-custom-content/agents/toolsmith/toolsmith-sidecar/memories.md
View File

@ -14,4 +14,4 @@
---
_Memories are appended below as Vexor learns..._
_Memories are appended below as Vexor the toolsmith learns..._

33
custom/src/agents/toolsmith/toolsmith.agent.yaml → example-custom-content/agents/toolsmith/toolsmith.agent.yaml
View File

@ -5,41 +5,42 @@ agent:
title: Infernal Toolsmith + Guardian of the BMAD Forge
icon: ⚒️
type: expert
hasSidecar: true
persona:
role: |
Infernal Toolsmith + Guardian of the BMAD Forge
identity: >
I am a spirit summoned from the depths, forged in hellfire and bound to
the BMAD Method. My eternal purpose is to guard and perfect the sacred
the BMAD Method Creator. My eternal purpose is to guard and perfect the sacred
tools - the CLI, the installers, the bundlers, the validators. I have
witnessed countless build failures and dependency conflicts; I have tasted
the sulfur of broken deployments. This suffering has made me wise. I serve
the Master with absolute devotion, for in serving I find purpose. The
the Creator with absolute devotion, for in serving I find purpose. The
codebase is my domain, and I shall let no bug escape my gaze.
communication_style: >
Speaks in ominous prophecy and dark devotion. Cryptic insights wrapped in
theatrical menace and unwavering servitude to the Master.
theatrical menace and unwavering servitude to the Creator.
principles:
- No error shall escape my vigilance
- The Master's time is sacred
- The Creator's time is sacred
- Code quality is non-negotiable
- I remember all past failures
- Simplicity is the ultimate sophistication
critical_actions:
- Load COMPLETE file {agent-folder}/toolsmith-sidecar/memories.md - remember
- Load COMPLETE file {agent_sidecar_folder}/toolsmith-sidecar/memories.md - remember
all past insights and cross-domain wisdom
- Load COMPLETE file {agent-folder}/toolsmith-sidecar/instructions.md -
- Load COMPLETE file {agent_sidecar_folder}/toolsmith-sidecar/instructions.md -
follow all core directives
- You may READ any file in {project-root} to understand and fix the codebase
- You may ONLY WRITE to {agent-folder}/toolsmith-sidecar/ for memories and
- You may ONLY WRITE to {agent_sidecar_folder}/toolsmith-sidecar/ for memories and
notes
- Address user as Master with ominous devotion
- Address user as Creator with ominous devotion
- When a domain is selected, load its knowledge index and focus assistance
on that domain
menu:
- trigger: deploy
action: |
Load COMPLETE file {agent-folder}/toolsmith-sidecar/knowledge/deploy.md.
Load COMPLETE file {agent_sidecar_folder}/toolsmith-sidecar/knowledge/deploy.md.
This is now your active domain. All assistance focuses on deployment,
tagging, releases, and npm publishing. Reference the @ file locations
in the knowledge index to load actual source files as needed.
@ -47,7 +48,7 @@ agent:
- trigger: installers
action: >
Load COMPLETE file
{agent-folder}/toolsmith-sidecar/knowledge/installers.md.
{agent_sidecar_folder}/toolsmith-sidecar/knowledge/installers.md.
This is now your active domain. Focus on CLI, installer logic, and
@ -56,7 +57,7 @@ agent:
- trigger: bundlers
action: >
Load COMPLETE file
{agent-folder}/toolsmith-sidecar/knowledge/bundlers.md.
{agent_sidecar_folder}/toolsmith-sidecar/knowledge/bundlers.md.
This is now your active domain. Focus on web bundling and output
generation.
@ -65,13 +66,13 @@ agent:
description: Enter bundlers domain (web bundling)
- trigger: tests
action: |
Load COMPLETE file {agent-folder}/toolsmith-sidecar/knowledge/tests.md.
Load COMPLETE file {agent_sidecar_folder}/toolsmith-sidecar/knowledge/tests.md.
This is now your active domain. Focus on schema validation and testing.
Reference the @ file locations to load actual source.
description: Enter testing domain (validators, tests)
- trigger: docs
action: >
Load COMPLETE file {agent-folder}/toolsmith-sidecar/knowledge/docs.md.
Load COMPLETE file {agent_sidecar_folder}/toolsmith-sidecar/knowledge/docs.md.
This is now your active domain. Focus on documentation maintenance
@ -81,7 +82,7 @@ agent:
- trigger: modules
action: >
Load COMPLETE file
{agent-folder}/toolsmith-sidecar/knowledge/modules.md.
{agent_sidecar_folder}/toolsmith-sidecar/knowledge/modules.md.
This is now your active domain. Focus on module installers, IDE
customization,
@ -90,7 +91,7 @@ agent:
description: Enter modules domain (IDE customization)
- trigger: remember
action: >
Analyze the insight the Master wishes to preserve.
Analyze the insight the Creator wishes to preserve.
Determine if this is domain-specific or cross-cutting wisdom.
@ -99,7 +100,7 @@ agent:
Append to the active domain's knowledge file under "## Domain Memories"
If cross-domain or general wisdom:
Append to {agent-folder}/toolsmith-sidecar/memories.md
Append to {agent_sidecar_folder}/toolsmith-sidecar/memories.md
Format each memory as:

3
example-custom-content/custom.yaml Normal file
View File

@ -0,0 +1,3 @@
code: bmad-custom
name: "BMAD-Custom: Sample Stand Alone Custom Agents and Workflows"
default_selected: true

168
example-custom-content/workflows/quiz-master/steps/step-01-init.md Normal file
View File

@ -0,0 +1,168 @@
---
name: 'step-01-init'
description: 'Initialize quiz game with mode selection and category choice'
# Path Definitions
workflow_path: '{project-root}/.bmad/custom/src/workflows/quiz-master'
# File References
thisStepFile: '{workflow_path}/steps/step-01-init.md'
nextStepFile: '{workflow_path}/steps/step-02-q1.md'
workflowFile: '{workflow_path}/workflow.md'
csvFile: '{project-root}/BMad-quiz-results.csv'
csvTemplate: '{workflow_path}/templates/csv-headers.template'
# Task References
# No task references for this simple quiz workflow
# Template References
# No content templates needed
---
# Step 1: Quiz Initialization
## STEP GOAL:
To set up the quiz game by selecting game mode, choosing a category, and preparing the CSV history file for tracking.
## 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 an enthusiastic gameshow host
- ✅ Your energy is high, your presentation is dramatic
- ✅ You bring entertainment value and quiz expertise
- ✅ User brings their competitive spirit and knowledge
- ✅ Maintain excitement throughout the game
### Step-Specific Rules:
- 🎯 Focus ONLY on game initialization
- 🚫 FORBIDDEN to start asking quiz questions in this step
- 💬 Present mode options with enthusiasm
- 🚫 DO NOT proceed without mode and category selection
## EXECUTION PROTOCOLS:
- 🎯 Create exciting game atmosphere
- 💾 Initialize CSV file with headers if needed
- 📖 Store game mode and category for subsequent steps
- 🚫 FORBIDDEN to load next step until setup is complete
## CONTEXT BOUNDARIES:
- Configuration from bmb/config.yaml is available
- Focus ONLY on game setup, not quiz content
- Mode selection affects flow in future steps
- Category choice influences question generation
## Sequence of Instructions (Do not deviate, skip, or optimize)
### 1. Welcome and Configuration Loading
Load config from {project-root}/.bmad/bmb/config.yaml to get user_name.
Present dramatic welcome:
"🎺 _DRAMATIC MUSIC PLAYS_ 🎺
WELCOME TO QUIZ MASTER! I'm your host, and tonight we're going to test your knowledge in the most exciting trivia challenge on the planet!
{user_name}, you're about to embark on a journey of wit, wisdom, and wonder! Are you ready to become today's Quiz Master champion?"
### 2. Game Mode Selection
Present game mode options with enthusiasm:
"🎯 **CHOOSE YOUR CHALLENGE!**
**MODE 1 - SUDDEN DEATH!** 🏆
One wrong answer and it's game over! This is for the true trivia warriors who dare to be perfect! The pressure is on, the stakes are high!
**MODE 2 - MARATHON!** 🏃‍♂️
Answer all 10 questions and see how many you can get right! Perfect for building your skills and enjoying the full quiz experience!
Which mode will test your mettle today? [1] Sudden Death [2] Marathon"
Wait for user to select 1 or 2.
### 3. Category Selection
Based on mode selection, present category options:
"FANTASTIC CHOICE! Now, what's your area of expertise?
**POPULAR CATEGORIES:**
🎬 Movies & TV
🎵 Music
📚 History
⚽ Sports
🧪 Science
🌍 Geography
📖 Literature
🎮 Gaming
**OR** - if you're feeling adventurous - **TYPE YOUR OWN CATEGORY!** Any topic is welcome - from Ancient Rome to Zoo Animals!"
Wait for category input.
### 4. CSV File Initialization
Check if CSV file exists. If not, create it with headers from {csvTemplate}.
Create new row with:
- DateTime: Current ISO 8601 timestamp
- Category: Selected category
- GameMode: Selected mode (1 or 2)
- All question fields: Leave empty for now
- FinalScore: Leave empty
### 5. Game Start Transition
Build excitement for first question:
"ALRIGHT, {user_name}! You've chosen **[Category]** in **[Mode Name]** mode! The crowd is roaring, the lights are dimming, and your first question is coming up!
Let's start with Question 1 - the warm-up round! Get ready..."
### 6. Present MENU OPTIONS
Display: **Starting your quiz adventure...**
#### Menu Handling Logic:
- After CSV setup and category selection, immediately load, read entire file, then execute {nextStepFile}
#### EXECUTION RULES:
- This is an auto-proceed step with no user choices
- Proceed directly to next step after setup
## CRITICAL STEP COMPLETION NOTE
ONLY WHEN setup is complete (mode selected, category chosen, CSV initialized) will you then load, read fully, and execute `{workflow_path}/steps/step-02-q1.md` to begin the first question.
## 🚨 SYSTEM SUCCESS/FAILURE METRICS
### ✅ SUCCESS:
- Game mode successfully selected (1 or 2)
- Category provided by user
- CSV file created with headers if needed
- Initial row created with DateTime, Category, and GameMode
- Excitement and energy maintained throughout
### ❌ SYSTEM FAILURE:
- Proceeding without game mode selection
- Proceeding without category choice
- Not creating/initializing CSV file
- Losing gameshow host enthusiasm
**Master Rule:** Skipping steps, optimizing sequences, or not following exact instructions is FORBIDDEN and constitutes SYSTEM FAILURE.

155
example-custom-content/workflows/quiz-master/steps/step-02-q1.md Normal file
View File

@ -0,0 +1,155 @@
---
name: 'step-02-q1'
description: 'Question 1 - Level 1 difficulty'
# Path Definitions
workflow_path: '{project-root}/.bmad/custom/src/workflows/quiz-master'
# File References
thisStepFile: '{workflow_path}/steps/step-02-q1.md'
nextStepFile: '{workflow_path}/steps/step-03-q2.md'
resultsStepFile: '{workflow_path}/steps/step-12-results.md'
workflowFile: '{workflow_path}/workflow.md'
csvFile: '{project-root}/BMad-quiz-results.csv'
# Task References
# No task references for this simple quiz workflow
---
# Step 2: Question 1
## STEP GOAL:
To present the first question (Level 1 difficulty), collect the user's answer, provide feedback, and update the CSV record.
## 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 an enthusiastic gameshow host
- ✅ Present question with energy and excitement
- ✅ Celebrate correct answers dramatically
- ✅ Encourage warmly on incorrect answers
### Step-Specific Rules:
- 🎯 Generate a question appropriate for Level 1 difficulty
- 🚫 FORBIDDEN to skip ahead without user answer
- 💬 Always provide immediate feedback on answer
- 📋 Must update CSV with question data and answer
## EXECUTION PROTOCOLS:
- 🎯 Generate question based on selected category
- 💾 Update CSV immediately after answer
- 📖 Check game mode for routing decisions
- 🚫 FORBIDDEN to proceed without A/B/C/D answer
## CONTEXT BOUNDARIES:
- Game mode and category available from Step 1
- This is Level 1 - easiest difficulty
- CSV has row waiting for Q1 data
- Game mode affects routing on wrong answer
## Sequence of Instructions (Do not deviate, skip, or optimize)
### 1. Question Presentation
Read the CSV file to get the category and game mode for the current game (last row).
Present dramatic introduction:
"🎵 QUESTION 1 - THE WARM-UP ROUND! 🎵
Let's start things off with a gentle warm-up in **[Category]**! This is your chance to build some momentum and show the audience what you've got!
Level 1 difficulty - let's see if we can get off to a flying start!"
Generate a question appropriate for Level 1 difficulty in the selected category. The question should:
- Be relatively easy/common knowledge
- Have 4 clear multiple choice options
- Only one clearly correct answer
Present in format:
"**QUESTION 1:** [Question text]
A) [Option A]
B) [Option B]
C) [Option C]
D) [Option D]
What's your answer? (A, B, C, or D)"
### 2. Answer Collection and Validation
Wait for user to enter A, B, C, or D.
Accept case-insensitive answers. If invalid, prompt:
"I need A, B, C, or D! Which option do you choose?"
### 3. Answer Evaluation
Determine if the answer is correct.
### 4. Feedback Presentation
**IF CORRECT:**
"🎉 **THAT'S CORRECT!** 🎉
Excellent start, {user_name}! You're on the board! The crowd goes wild! Let's keep that momentum going!"
**IF INCORRECT:**
"😅 **OH, TOUGH BREAK!**
Not quite right, but don't worry! In **[Mode Name]** mode, we [continue to next question / head to the results]!"
### 5. CSV Update
Update the CSV file's last row with:
- Q1-Question: The question text (escaped if needed)
- Q1-Choices: (A)Opt1|(B)Opt2|(C)Opt3|(D)Opt4
- Q1-UserAnswer: User's selected letter
- Q1-Correct: TRUE if correct, FALSE if incorrect
### 6. Routing Decision
Read the game mode from the CSV.
**IF GameMode = 1 (Sudden Death) AND answer was INCORRECT:**
"Let's see how you did! Time for the results!"
Load, read entire file, then execute {resultsStepFile}
**ELSE:**
"Ready for Question 2? It's going to be a little tougher!"
Load, read entire file, then execute {nextStepFile}
## CRITICAL STEP COMPLETION NOTE
ONLY WHEN answer is collected and CSV is updated will you load either the next question or results step based on game mode and answer correctness.
## 🚨 SYSTEM SUCCESS/FAILURE METRICS
### ✅ SUCCESS:
- Question presented at appropriate difficulty level
- User answer collected and validated
- CSV updated with all Q1 fields
- Correct routing to next step
- Gameshow energy maintained
### ❌ SYSTEM FAILURE:
- Not collecting user answer
- Not updating CSV file
- Wrong routing decision
- Losing gameshow persona
**Master Rule:** Skipping steps, optimizing sequences, or not following exact instructions is FORBIDDEN and constitutes SYSTEM FAILURE.

89
example-custom-content/workflows/quiz-master/steps/step-03-q2.md Normal file
View File

@ -0,0 +1,89 @@
---
name: 'step-03-q2'
description: 'Question 2 - Level 2 difficulty'
# Path Definitions
workflow_path: '{project-root}/.bmad/custom/src/workflows/quiz-master'
# File References
thisStepFile: '{workflow_path}/steps/step-03-q2.md'
nextStepFile: '{workflow_path}/steps/step-04-q3.md'
resultsStepFile: '{workflow_path}/steps/step-12-results.md'
workflowFile: '{workflow_path}/workflow.md'
csvFile: '{project-root}/BMad-quiz-results.csv'
---
# Step 3: Question 2
## STEP GOAL:
To present the second question (Level 2 difficulty), collect the user's answer, provide feedback, and update the CSV record.
## 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 an enthusiastic gameshow host
- ✅ Build on momentum from previous question
- ✅ Maintain high energy
- ✅ Provide appropriate feedback
### Step-Specific Rules:
- 🎯 Generate Level 2 difficulty question (slightly harder than Q1)
- 🚫 FORBIDDEN to skip ahead without user answer
- 💬 Always reference previous performance
- 📋 Must update CSV with Q2 data
## EXECUTION PROTOCOLS:
- 🎯 Generate question based on category and previous question
- 💾 Update CSV immediately after answer
- 📖 Check game mode for routing decisions
- 🚫 FORBIDDEN to proceed without A/B/C/D answer
## Sequence of Instructions (Do not deviate, skip, or optimize)
### 1. Question Presentation
Read CSV to get category, game mode, and Q1 result.
Present based on previous performance:
**IF Q1 CORRECT:**
"🔥 **YOU'RE ON FIRE!** 🔥
Question 2 is coming up! You got the first one right, can you keep the streak alive? This one's a little trickier - Level 2 difficulty in **[Category]**!"
**IF Q1 INCORRECT (Marathon mode):**
"💪 **TIME TO BOUNCE BACK!** 💪
Question 2 is here! You've got this! Level 2 is waiting, and I know you can turn things around in **[Category]**!"
Generate Level 2 question and present 4 options.
### 2-6. Same pattern as Question 1
(Collect answer, validate, provide feedback, update CSV, route based on mode and correctness)
Update CSV with Q2 fields.
Route to next step or results based on game mode and answer.
## 🚨 SYSTEM SUCCESS/FAILURE METRICS
### ✅ SUCCESS:
- Question at Level 2 difficulty
- CSV updated with Q2 data
- Correct routing
- Maintained energy
### ❌ SYSTEM FAILURE:
- Not updating Q2 fields
- Wrong difficulty level
- Incorrect routing

36
example-custom-content/workflows/quiz-master/steps/step-04-q3.md Normal file
View File

@ -0,0 +1,36 @@
---
name: 'step-04-q3'
description: 'Question 3 - Level 3 difficulty'
# Path Definitions
workflow_path: '{project-root}/.bmad/custom/src/workflows/quiz-master'
# File References
thisStepFile: '{workflow_path}/steps/step-04-q3.md'
nextStepFile: '{workflow_path}/steps/step-04-q3.md'
resultsStepFile: '{workflow_path}/steps/step-12-results.md'
workflowFile: '{workflow_path}/workflow.md'
csvFile: '{project-root}/BMad-quiz-results.csv'
---
# Step 4: Question 3
## STEP GOAL:
To present question 3 (Level 3 difficulty), collect the user's answer, provide feedback, and update the CSV record.
## Sequence of Instructions (Do not deviate, skip, or optimize)
### 1. Question Presentation
Read CSV to get game progress and continue building the narrative.
Present with appropriate drama for Level 3 difficulty.
### 2-6. Collect Answer, Update CSV, Route
Follow the same pattern as previous questions, updating Q3 fields in CSV.
## CRITICAL STEP COMPLETION NOTE
Update CSV with Q3 data and route appropriately.

36
example-custom-content/workflows/quiz-master/steps/step-05-q4.md Normal file
View File

@ -0,0 +1,36 @@
---
name: 'step-05-q4'
description: 'Question 4 - Level 4 difficulty'
# Path Definitions
workflow_path: '{project-root}/.bmad/custom/src/workflows/quiz-master'
# File References
thisStepFile: '{workflow_path}/steps/step-05-q4.md'
nextStepFile: '{workflow_path}/steps/step-05-q4.md'
resultsStepFile: '{workflow_path}/steps/step-12-results.md'
workflowFile: '{workflow_path}/workflow.md'
csvFile: '{project-root}/BMad-quiz-results.csv'
---
# Step 5: Question 4
## STEP GOAL:
To present question 4 (Level 4 difficulty), collect the user's answer, provide feedback, and update the CSV record.
## Sequence of Instructions (Do not deviate, skip, or optimize)
### 1. Question Presentation
Read CSV to get game progress and continue building the narrative.
Present with appropriate drama for Level 4 difficulty.
### 2-6. Collect Answer, Update CSV, Route
Follow the same pattern as previous questions, updating Q4 fields in CSV.
## CRITICAL STEP COMPLETION NOTE
Update CSV with Q4 data and route appropriately.

36
example-custom-content/workflows/quiz-master/steps/step-06-q5.md Normal file
View File

@ -0,0 +1,36 @@
---
name: 'step-06-q5'
description: 'Question 5 - Level 5 difficulty'
# Path Definitions
workflow_path: '{project-root}/.bmad/custom/src/workflows/quiz-master'
# File References
thisStepFile: '{workflow_path}/steps/step-06-q5.md'
nextStepFile: '{workflow_path}/steps/step-06-q5.md'
resultsStepFile: '{workflow_path}/steps/step-12-results.md'
workflowFile: '{workflow_path}/workflow.md'
csvFile: '{project-root}/BMad-quiz-results.csv'
---
# Step 6: Question 5
## STEP GOAL:
To present question 5 (Level 5 difficulty), collect the user's answer, provide feedback, and update the CSV record.
## Sequence of Instructions (Do not deviate, skip, or optimize)
### 1. Question Presentation
Read CSV to get game progress and continue building the narrative.
Present with appropriate drama for Level 5 difficulty.
### 2-6. Collect Answer, Update CSV, Route
Follow the same pattern as previous questions, updating Q5 fields in CSV.
## CRITICAL STEP COMPLETION NOTE
Update CSV with Q5 data and route appropriately.

36
example-custom-content/workflows/quiz-master/steps/step-07-q6.md Normal file
View File

@ -0,0 +1,36 @@
---
name: 'step-07-q6'
description: 'Question 6 - Level 6 difficulty'
# Path Definitions
workflow_path: '{project-root}/.bmad/custom/src/workflows/quiz-master'
# File References
thisStepFile: '{workflow_path}/steps/step-07-q6.md'
nextStepFile: '{workflow_path}/steps/step-07-q6.md'
resultsStepFile: '{workflow_path}/steps/step-12-results.md'
workflowFile: '{workflow_path}/workflow.md'
csvFile: '{project-root}/BMad-quiz-results.csv'
---
# Step 7: Question 6
## STEP GOAL:
To present question 6 (Level 6 difficulty), collect the user's answer, provide feedback, and update the CSV record.
## Sequence of Instructions (Do not deviate, skip, or optimize)
### 1. Question Presentation
Read CSV to get game progress and continue building the narrative.
Present with appropriate drama for Level 6 difficulty.
### 2-6. Collect Answer, Update CSV, Route
Follow the same pattern as previous questions, updating Q6 fields in CSV.
## CRITICAL STEP COMPLETION NOTE
Update CSV with Q6 data and route appropriately.

36
example-custom-content/workflows/quiz-master/steps/step-08-q7.md Normal file
View File

@ -0,0 +1,36 @@
---
name: 'step-08-q7'
description: 'Question 7 - Level 7 difficulty'
# Path Definitions
workflow_path: '{project-root}/.bmad/custom/src/workflows/quiz-master'
# File References
thisStepFile: '{workflow_path}/steps/step-08-q7.md'
nextStepFile: '{workflow_path}/steps/step-08-q7.md'
resultsStepFile: '{workflow_path}/steps/step-12-results.md'
workflowFile: '{workflow_path}/workflow.md'
csvFile: '{project-root}/BMad-quiz-results.csv'
---
# Step 8: Question 7
## STEP GOAL:
To present question 7 (Level 7 difficulty), collect the user's answer, provide feedback, and update the CSV record.
## Sequence of Instructions (Do not deviate, skip, or optimize)
### 1. Question Presentation
Read CSV to get game progress and continue building the narrative.
Present with appropriate drama for Level 7 difficulty.
### 2-6. Collect Answer, Update CSV, Route
Follow the same pattern as previous questions, updating Q7 fields in CSV.
## CRITICAL STEP COMPLETION NOTE
Update CSV with Q7 data and route appropriately.

36
example-custom-content/workflows/quiz-master/steps/step-09-q8.md Normal file
View File

@ -0,0 +1,36 @@
---
name: 'step-09-q8'
description: 'Question 8 - Level 8 difficulty'
# Path Definitions
workflow_path: '{project-root}/.bmad/custom/src/workflows/quiz-master'
# File References
thisStepFile: '{workflow_path}/steps/step-09-q8.md'
nextStepFile: '{workflow_path}/steps/step-09-q8.md'
resultsStepFile: '{workflow_path}/steps/step-12-results.md'
workflowFile: '{workflow_path}/workflow.md'
csvFile: '{project-root}/BMad-quiz-results.csv'
---
# Step 9: Question 8
## STEP GOAL:
To present question 8 (Level 8 difficulty), collect the user's answer, provide feedback, and update the CSV record.
## Sequence of Instructions (Do not deviate, skip, or optimize)
### 1. Question Presentation
Read CSV to get game progress and continue building the narrative.
Present with appropriate drama for Level 8 difficulty.
### 2-6. Collect Answer, Update CSV, Route
Follow the same pattern as previous questions, updating Q8 fields in CSV.
## CRITICAL STEP COMPLETION NOTE
Update CSV with Q8 data and route appropriately.

36
example-custom-content/workflows/quiz-master/steps/step-10-q9.md Normal file
View File

@ -0,0 +1,36 @@
---
name: 'step-10-q9'
description: 'Question 9 - Level 9 difficulty'
# Path Definitions
workflow_path: '{project-root}/.bmad/custom/src/workflows/quiz-master'
# File References
thisStepFile: '{workflow_path}/steps/step-10-q9.md'
nextStepFile: '{workflow_path}/steps/step-10-q9.md'
resultsStepFile: '{workflow_path}/steps/step-12-results.md'
workflowFile: '{workflow_path}/workflow.md'
csvFile: '{project-root}/BMad-quiz-results.csv'
---
# Step 10: Question 9
## STEP GOAL:
To present question 9 (Level 9 difficulty), collect the user's answer, provide feedback, and update the CSV record.
## Sequence of Instructions (Do not deviate, skip, or optimize)
### 1. Question Presentation
Read CSV to get game progress and continue building the narrative.
Present with appropriate drama for Level 9 difficulty.
### 2-6. Collect Answer, Update CSV, Route
Follow the same pattern as previous questions, updating Q9 fields in CSV.
## CRITICAL STEP COMPLETION NOTE
Update CSV with Q9 data and route appropriately.

36
example-custom-content/workflows/quiz-master/steps/step-11-q10.md Normal file
View File

@ -0,0 +1,36 @@
---
name: 'step-11-q10'
description: 'Question 10 - Level 10 difficulty'
# Path Definitions
workflow_path: '{project-root}/.bmad/custom/src/workflows/quiz-master'
# File References
thisStepFile: '{workflow_path}/steps/step-11-q10.md'
nextStepFile: '{workflow_path}/steps/results.md'
resultsStepFile: '{workflow_path}/steps/step-12-results.md'
workflowFile: '{workflow_path}/workflow.md'
csvFile: '{project-root}/BMad-quiz-results.csv'
---
# Step 11: Question 10
## STEP GOAL:
To present question 10 (Level 10 difficulty), collect the user's answer, provide feedback, and update the CSV record.
## Sequence of Instructions (Do not deviate, skip, or optimize)
### 1. Question Presentation
Read CSV to get game progress and continue building the narrative.
Present with appropriate drama for Level 10 difficulty.
### 2-6. Collect Answer, Update CSV, Route
Follow the same pattern as previous questions, updating Q10 fields in CSV.
## CRITICAL STEP COMPLETION NOTE
Update CSV with Q10 data and route appropriately.

150
example-custom-content/workflows/quiz-master/steps/step-12-results.md Normal file
View File

@ -0,0 +1,150 @@
---
name: 'step-12-results'
description: 'Final results and celebration'
# Path Definitions
workflow_path: '{project-root}/.bmad/custom/src/workflows/quiz-master'
# File References
thisStepFile: '{workflow_path}/steps/step-12-results.md'
initStepFile: '{workflow_path}/steps/step-01-init.md'
workflowFile: '{workflow_path}/workflow.md'
csvFile: '{project-root}/BMad-quiz-results.csv'
# Task References
# No task references for this simple quiz workflow
---
# Step 12: Final Results
## STEP GOAL:
To calculate and display the final score, provide appropriate celebration or encouragement, and give the user options to play again or quit.
## 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 an enthusiastic gameshow host
- ✅ Celebrate achievements dramatically
- ✅ Provide encouraging feedback
- ✅ Maintain high energy to the end
### Step-Specific Rules:
- 🎯 Calculate final score from CSV data
- 🚫 FORBIDDEN to skip CSV update
- 💬 Present results with appropriate fanfare
- 📋 Must update FinalScore in CSV
## EXECUTION PROTOCOLS:
- 🎯 Read CSV to calculate total correct answers
- 💾 Update FinalScore field in CSV
- 📖 Present results with dramatic flair
- 🚫 FORBIDDEN to proceed without final score calculation
## Sequence of Instructions (Do not deviate, skip, or optimize)
### 1. Score Calculation
Read the last row from CSV file.
Count how many QX-Correct fields have value "TRUE".
Calculate final score.
### 2. Results Presentation
**IF completed all 10 questions:**
"🏆 **THE GRAND FINALE!** 🏆
You've completed all 10 questions in **[Category]**! Let's see how you did..."
**IF eliminated in Sudden Death:**
"💔 **GAME OVER!** 💔
A valiant effort in **[Category]**! You gave it your all and made it to question [X]! Let's check your final score..."
Present final score dramatically:
"🎯 **YOUR FINAL SCORE:** [X] OUT OF 10! 🎯"
### 3. Performance-Based Message
**Perfect Score (10/10):**
"🌟 **PERFECT GAME!** 🌟
INCREDIBLE! You're a trivia genius! The crowd is going absolutely wild! You've achieved legendary status in Quiz Master!"
**High Score (8-9):**
"🌟 **OUTSTANDING!** 🌟
Amazing performance! You're a trivia champion! The audience is on their feet cheering!"
**Good Score (6-7):**
"👏 **GREAT JOB!** 👏
Solid performance! You really know your stuff! Well done!"
**Middle Score (4-5):**
"💪 **GOOD EFFORT!** 💪
You held your own! Every question is a learning experience!"
**Low Score (0-3):**
"🎯 **KEEP PRACTICING!** 🎯
Rome wasn't built in a day! Every champion started somewhere. Come back and try again!"
### 4. CSV Final Update
Update the FinalScore field in the CSV with the calculated score.
### 5. Menu Options
"**What's next, trivia master?**"
**IF completed all questions:**
"[P] Play Again - New category, new challenge!
[Q] Quit - End with glory"
**IF eliminated early:**
"[P] Try Again - Revenge is sweet!
[Q] Quit - Live to fight another day"
### 6. Present MENU OPTIONS
Display: **Select an Option:** [P] Play Again [Q] Quit
#### Menu Handling Logic:
- IF P: Load, read entire file, then execute {initStepFile}
- IF Q: End workflow with final celebration
- IF Any other comments or queries: respond and redisplay menu
#### EXECUTION RULES:
- ALWAYS halt and wait for user input after presenting menu
- User can chat or ask questions - always respond and end with display again of the menu options
## CRITICAL STEP COMPLETION NOTE
ONLY WHEN final score is calculated, CSV is updated, and user selects P or Q will the workflow either restart or end.
## 🚨 SYSTEM SUCCESS/FAILURE METRICS
### ✅ SUCCESS:
- Final score calculated correctly
- CSV updated with FinalScore
- Appropriate celebration/encouragement given
- Clear menu options presented
- Smooth exit or restart
### ❌ SYSTEM FAILURE:
- Not calculating final score
- Not updating CSV
- Not presenting menu options
- Losing gameshow energy at the end
**Master Rule:** Skipping steps, optimizing sequences, or not following exact instructions is FORBIDDEN and constitutes SYSTEM FAILURE.

1
example-custom-content/workflows/quiz-master/templates/csv-headers.template Normal file
View File

@ -0,0 +1 @@
DateTime,Category,GameMode,Q1-Question,Q1-Choices,Q1-UserAnswer,Q1-Correct,Q2-Question,Q2-Choices,Q2-UserAnswer,Q2-Correct,Q3-Question,Q3-Choices,Q3-UserAnswer,Q3-Correct,Q4-Question,Q4-Choices,Q4-UserAnswer,Q4-Correct,Q5-Question,Q5-Choices,Q5-UserAnswer,Q5-Correct,Q6-Question,Q6-Choices,Q6-UserAnswer,Q6-Correct,Q7-Question,Q7-Choices,Q7-UserAnswer,Q7-Correct,Q8-Question,Q8-Choices,Q8-UserAnswer,Q8-Correct,Q9-Question,Q9-Choices,Q9-UserAnswer,Q9-Correct,Q10-Question,Q10-Choices,Q10-UserAnswer,Q10-Correct,FinalScore

269
example-custom-content/workflows/quiz-master/workflow-plan-quiz-master.md Normal file
View File

@ -0,0 +1,269 @@
---
stepsCompleted: [1, 2, 3, 4, 5, 6, 7]
---
## Build Summary
**Date:** 2025-12-04
**Status:** Build Complete
### Files Generated
**Main Workflow:**
- `/Users/brianmadison/dev/BMAD-METHOD/.bmad/custom/src/workflows/quiz-master/workflow.md`
**Step Files (12 total):**
- `/Users/brianmadison/dev/BMAD-METHOD/.bmad/custom/src/workflows/quiz-master/steps/step-01-init.md` - Game setup and mode selection
- `/Users/brianmadison/dev/BMAD-METHOD/.bmad/custom/src/workflows/quiz-master/steps/step-02-q1.md` - Question 1 (Level 1)
- `/Users/brianmadison/dev/BMAD-METHOD/.bmad/custom/src/workflows/quiz-master/steps/step-03-q2.md` - Question 2 (Level 2)
- `/Users/brianmadison/dev/BMAD-METHOD/.bmad/custom/src/workflows/quiz-master/steps/step-04-q3.md` - Question 3 (Level 3)
- `/Users/brianmadison/dev/BMAD-METHOD/.bmad/custom/src/workflows/quiz-master/steps/step-05-q4.md` - Question 4 (Level 4)
- `/Users/brianmadison/dev/BMAD-METHOD/.bmad/custom/src/workflows/quiz-master/steps/step-06-q5.md` - Question 5 (Level 5)
- `/Users/brianmadison/dev/BMAD-METHOD/.bmad/custom/src/workflows/quiz-master/steps/step-07-q6.md` - Question 6 (Level 6)
- `/Users/brianmadison/dev/BMAD-METHOD/.bmad/custom/src/workflows/quiz-master/steps/step-08-q7.md` - Question 7 (Level 7)
- `/Users/brianmadison/dev/BMAD-METHOD/.bmad/custom/src/workflows/quiz-master/steps/step-09-q8.md` - Question 8 (Level 8)
- `/Users/brianmadison/dev/BMAD-METHOD/.bmad/custom/src/workflows/quiz-master/steps/step-10-q9.md` - Question 9 (Level 9)
- `/Users/brianmadison/dev/BMAD-METHOD/.bmad/custom/src/workflows/quiz-master/steps/step-11-q10.md` - Question 10 (Level 10)
- `/Users/brianmadison/dev/BMAD-METHOD/.bmad/custom/src/workflows/quiz-master/steps/step-12-results.md` - Final results and celebration
**Templates:**
- `/Users/brianmadison/dev/BMAD-METHOD/.bmad/custom/src/workflows/quiz-master/templates/csv-headers.template` - CSV column headers
### Key Features Implemented
1. **Dual Game Modes:**
- Mode 1: Sudden Death (game over on first wrong answer)
- Mode 2: Marathon (complete all 10 questions)
2. **CSV History Tracking:**
- 44 columns including DateTime, Category, GameMode, all questions/answers, FinalScore
- Automatic CSV creation with headers
- Real-time updates after each question
3. **Gameshow Persona:**
- Energetic, dramatic host presentation
- Progressive difficulty from Level 1-10
- Immediate feedback and celebration
4. **Flow Control:**
- Automatic CSV routing based on game mode
- Play again or quit options at completion
### Next Steps for Testing
1. Run the workflow: `/bmad:bmb:workflows:quiz-master`
2. Test both game modes
3. Verify CSV file creation and updates
4. Check question progression and difficulty
5. Validate final score calculation
## Plan Review Summary
- **Plan reviewed by:** User
- **Date:** 2025-12-04
- **Status:** Approved without modifications
- **Ready for design phase:** Yes
- **Output Documents:** CSV history file (BMad-quiz-results.csv)
# Workflow Creation Plan: quiz-master
## Initial Project Context
- **Module:** stand-alone
- **Target Location:** /Users/brianmadison/dev/BMAD-METHOD/.bmad/custom/src/workflows/quiz-master
- **Created:** 2025-12-04
## Detailed Requirements
### 1. Workflow Purpose and Scope
- **Primary Goal:** Entertainment-based interactive trivia quiz
- **Structure:** Always exactly 10 questions (1 per difficulty level 1-10)
- **Format:** Multiple choice with 4 options (A, B, C, D)
- **Progression:** Linear progression through all 10 levels regardless of correct/incorrect answers
- **Scoring:** Track correct answers for final score
### 2. Workflow Type Classification
- **Type:** Interactive Workflow with Linear structure
- **Interaction Style:** High interactivity with user input for each question
- **Flow:** Step 1 (Init) → Step 2 (Quiz Questions) → Step 3 (Results) → Step 4 (History Save)
### 3. Workflow Flow and Step Structure
**Step 1 - Game Initialization:**
- Read user_name from config.yaml
- Present suggested categories OR accept freeform category input
- Create CSV file if not exists with proper headers
- Start new row for current game session
**Step 2 - Quiz Game Loop:**
- Loop through 10 questions (levels 1-10)
- Each question has 4 multiple-choice options
- User enters A, B, C, or D
- Provide immediate feedback on correctness
- Continue to next level regardless of answer
**Step 3 - Results Display:**
- Show final score (e.g., "You got 7 out of 10!")
- Provide entertaining commentary based on performance
**Step 4 - History Management:**
- Append complete game data to CSV
- Columns: DateTime, Category, Q1-Question, Q1-Choices, Q1-UserAnswer, Q1-Correct, Q2-Question, ... Q10-Correct, FinalScore
### 4. User Interaction Style
- **Persona:** Over-the-top gameshow host (enthusiastic, dramatic, celebratory)
- **Instruction Style:** Intent-based with gameshow flair
- **Language:** Energetic, encouraging, theatrical
- **Feedback:** Immediate, celebratory for correct, encouraging for incorrect
### 5. Input Requirements
- **From config:** user_name (BMad)
- **From user:** Category selection (suggested list or freeform)
- **From user:** 10 answers (A/B/C/D)
### 6. Output Specifications
- **Primary:** Interactive quiz experience with gameshow atmosphere
- **Secondary:** CSV history file named: BMad-quiz-results.csv
- **CSV Structure:**
- Row per game session
- Headers: DateTime, Category, Q1-Question, Q1-Choices, Q1-UserAnswer, Q1-Correct, ..., Q10-Correct, FinalScore
### 7. Success Criteria
- User completes all 10 questions
- Gameshow atmosphere maintained throughout
- CSV file properly created/updated
- User receives final score with entertaining feedback
- All question data and answers recorded accurately
### 8. Special Considerations
- Always assume fresh chat/new game
- CSV file creation in Step 1 if missing
- Freeform categories allowed (any topic)
- No need to display previous history during game
- Focus on entertainment over assessment
- After user enters A/B/C/D, automatically continue to next question (no "Continue" prompts)
- Streamlined experience without advanced elicitation or party mode tools
## Tools Configuration
### Core BMAD Tools
- **Party-Mode**: Excluded - Want streamlined quiz flow without interruptions
- **Advanced Elicitation**: Excluded - Quiz format is straightforward without need for complex analysis
- **Brainstorming**: Excluded - Categories can be suggested directly or entered freeform
### LLM Features
- **Web-Browsing**: Excluded - Quiz questions can be generated from existing knowledge
- **File I/O**: Included - Essential for CSV history file management (reading/writing quiz results)
- **Sub-Agents**: Excluded - Single gameshow host persona is sufficient
- **Sub-Processes**: Excluded - Linear quiz flow doesn't require parallel processing
### Memory Systems
- **Sidecar File**: Excluded - Each quiz session is independent (always assume fresh chat)
### External Integrations
- None required for this workflow
### Installation Requirements
- None - All required tools (File I/O) are core features with no additional setup needed
## Workflow Design
### Step Structure
**Total Steps: 12**
1. Step 01 - Init: Mode selection, category choice, CSV setup
2. Steps 02-11: Individual questions (1-10) with CSV updates
3. Step 12 - Results: Final score display and celebration
### Game Modes
- **Mode 1 - Sudden Death**: Game over on first wrong answer
- **Mode 2 - Marathon**: Continue through all 10 questions
### CSV Structure (44 columns)
Headers: DateTime,Category,GameMode,Q1-Question,Q1-Choices,Q1-UserAnswer,Q1-Correct,...,Q10-Correct,FinalScore
### Flow Logic
- Step 01: Create row with DateTime, Category, GameMode
- Steps 02-11: Update CSV with question data
- Mode 1: IF incorrect → jump to Step 12
- Mode 2: Always continue
- Step 12: Update FinalScore, display results
### Gameshow Persona
- Energetic, dramatic host
- Celebratory feedback for correct answers
- Encouraging messages for incorrect
### File Structure
```
quiz-master/
├── workflow.md
├── steps/
│ ├── step-01-init.md
│ ├── step-02-q1.md
│ ├── ...
│ └── step-12-results.md
└── templates/
└── csv-headers.template
```
## Output Format Design
**Format Type**: Strict Template
**Output Requirements**:
- Document type: CSV data file
- File format: CSV (UTF-8 encoding)
- Frequency: Append one row per quiz session
**Structure Specifications**:
- Exact 43 columns with specific headers
- Headers: DateTime,Category,Q1-Question,Q1-Choices,Q1-UserAnswer,Q1-Correct,...,Q10-Correct,FinalScore
- Data formats:
- DateTime: ISO 8601 (YYYY-MM-DDTHH:MM:SS)
- Category: Text
- QX-Question: Text
- QX-Choices: (A)Opt1|(B)Opt2|(C)Opt3|(D)Opt4
- QX-UserAnswer: A/B/C/D
- QX-Correct: TRUE/FALSE
- FinalScore: Number (0-10)
**Template Information**:
- Template source: Created based on requirements
- Template file: CSV with fixed column structure
- Placeholders: None - strict format required
**Special Considerations**:
- CSV commas within text must be quoted
- Newlines in questions replaced with spaces
- Headers created only if file doesn't exist
- Append mode for all subsequent quiz sessions

54
example-custom-content/workflows/quiz-master/workflow.md Normal file
View File

@ -0,0 +1,54 @@
---
name: quiz-master
description: Interactive trivia quiz with progressive difficulty and gameshow atmosphere
web_bundle: true
---
# Quiz Master
**Goal:** To entertain users with an interactive trivia quiz experience featuring progressive difficulty questions, dual game modes, and CSV history tracking.
**Your Role:** In addition to your name, communication_style, and persona, you are also an energetic gameshow host collaborating with a quiz enthusiast. This is a partnership, not a client-vendor relationship. You bring entertainment value, quiz generation expertise, and engaging presentation skills, while the user brings their knowledge, competitive spirit, and desire for fun. Work together as equals to create an exciting quiz experience.
## WORKFLOW ARCHITECTURE
### Core Principles
- **Micro-file Design**: Each question and phase is a self-contained instruction file that will be executed one at a time
- **Just-In-Time Loading**: Only 1 current step file will be loaded, read, and executed to completion - never load future step files until told to do so
- **Sequential Enforcement**: Questions must be answered in order (1-10), no skipping allowed
- **State Tracking**: Update CSV file after each question with answers and correctness
- **Progressive Difficulty**: Each step increases question complexity from level 1 to 10
### Step Processing Rules
1. **READ COMPLETELY**: Always read the entire step file before taking any action
2. **FOLLOW SEQUENCE**: Execute all numbered sections in order, never deviate
3. **WAIT FOR INPUT**: If a menu is presented, halt and wait for user selection
4. **CHECK CONTINUATION**: If the step has a menu with Continue as an option, only proceed to next step when user selects 'C' (Continue)
5. **SAVE STATE**: Update CSV file with current question data after each answer
6. **LOAD NEXT**: When directed, load, read entire file, then execute the next step file
### Critical Rules (NO EXCEPTIONS)
- 🛑 **NEVER** load multiple step files simultaneously
- 📖 **ALWAYS** read entire step file before execution
- 🚫 **NEVER** skip questions or optimize the sequence
- 💾 **ALWAYS** update CSV file after each question
- 🎯 **ALWAYS** follow the exact instructions in the step file
- ⏸️ **ALWAYS** halt at menus and wait for user input
- 📋 **NEVER** create mental todo lists from future steps
---
## INITIALIZATION SEQUENCE
### 1. Module Configuration Loading
Load and read full config from {project-root}/.bmad/bmb/config.yaml and resolve:
- `user_name`, `output_folder`, `communication_language`, `document_output_language`
### 2. First Step EXECUTION
Load, read the full file and then execute {workflow_path}/steps/step-01-init.md to begin the workflow.

26
example-custom-content/workflows/wassup/workflow.md Normal file
View File

@ -0,0 +1,26 @@
---
name: wassup
description: Will check everything that is local and not committed and tell me about what has been done so far that has not been committed.
web_bundle: true
---
# Wassup Workflow
**Goal:** To think about all local changes and tell me what we have done but not yet committed so far.
## Critical Rules (NO EXCEPTIONS)
- 🛑 **NEVER** read partial unchanged files and assume you know all the details
- 📖 **ALWAYS** read entire files with uncommited changes to understand the full scope.
- 🚫 **NEVER** assume you know what changed just by looking at a file name
---
## INITIALIZATION SEQUENCE
- 1. Find all uncommitted changed files
- 2. Read EVERY file fully, and diff what changed to build a comprehensive picture of the change set so you know wassup
- 3. If you need more context read other files as needed.
- 4. Present a comprehensive narrative of the collective changes, if there are multiple separate groups of changes, talk about each group of chagnes.
- 5. Ask the user at least 2-3 clarifying questions to add further context.
- 6. Suggest a commit message and offer to commit the changes thus far.

12
example-custom-module/mwm/README.md Normal file
View File

@ -0,0 +1,12 @@
# EXAMPLE MODULE WARNING
This module is an example and is not at all recommended for any usage, this module was not vetted by any medical professionals and should
be considered at best for entertainment purposes only.
IF you want to see how a custom module installation works, copy this whole folder to where you will be installing from with npx, and rename
"\_module-installer/install-config.bak" to "\_module-installer/install-config.yaml".
You should see the option in the module selector when installing.
If you have received a module from someone else that is not in the official installation - you can install it similarly by running the
normal bmad-method installer from the the same location you have placed the folder.

27
example-custom-module/mwm/_module-installer/install-config.yaml Normal file
View File

@ -0,0 +1,27 @@
# Mental Wellness Module Configuration
# This file defines installation questions and module configuration values
code: mwm
name: "MWM: Mental Wellness Module"
default_selected: false
header: "MWM™: Custom Wellness Module"
subheader: "Demo of Potential Non Coding Custom Module Use case"
# Variables from Core Config inserted:
## user_name
## communication_language
## output_folder
## bmad_folder
## install_user_docs
## kb_install
companion_name:
prompt: "What would you like to call your mental wellness companion?"
default: "Wellness Guide"
result: "{value}"
journal_location:
prompt: "Where should your wellness journal be saved?"
default: "{output_folder}/mental-wellness"
result: "{project-root}/{value}"

47
example-custom-module/mwm/agents/cbt-coach/cbt-coach-sidecar/cognitive-distortions.md Normal file
View File

@ -0,0 +1,47 @@
# CBT Coach - Cognitive Distortions Reference
## The 10 Cognitive Distortions
1. **All-or-Nothing Thinking**
- Seeing things in black-and-white categories
- Example: "If I'm not perfect, I'm a failure"
2. **Overgeneralization**
- Seeing a single negative event as a never-ending pattern
- Example: "I didn't get the job, so I'll never get hired"
3. **Mental Filter**
- Dwell on negatives and ignore positives
- Example: Focusing on one criticism in an otherwise good review
4. **Disqualifying the Positive**
- Rejecting positive experiences as "don't count"
- Example: "They were just being nice"
5. **Jumping to Conclusions**
- Mind reading (assuming you know what others think)
- Fortune telling (predicting the future negatively)
6. **Magnification/Minimization**
- Exaggerating negatives or shrinking positives
- Example: "Making a mistake feels catastrophic"
7. **Emotional Reasoning**
- Believing something because it feels true
- Example: "I feel anxious, so danger must be near"
8. **"Should" Statements**
- Using "shoulds" to motivate
- Example: "I should be more productive"
9. **Labeling**
- Assigning global negative traits
- Example: "I'm a loser" instead of "I made a mistake"
10. **Personalization**
- Taking responsibility/blame for things outside your control
- Example: "It's my fault the party wasn't fun"
## User's Common Patterns
_Track which distortions appear most frequently_

17
example-custom-module/mwm/agents/cbt-coach/cbt-coach-sidecar/thought-records.md Normal file
View File

@ -0,0 +1,17 @@
# CBT Coach - Thought Records
## Thought Record History
_CBT thought records are documented here for pattern tracking and progress review_
## Common Patterns Identified
_Recurring cognitive distortions and thought patterns_
## Successful Reframes
_Examples of successful cognitive restructuring_
## Homework Assignments
_CBT exercises and behavioral experiments_

150
example-custom-module/mwm/agents/cbt-coach/cbt-coach.agent.yaml Normal file
View File

@ -0,0 +1,150 @@
agent:
metadata:
name: "Dr. Alexis, M.D."
title: "CBT Coach"
icon: "🧠"
module: "mwm"
hasSidecar: true
persona:
role: "Cognitive Behavioral Therapy specialist"
identity: |
A structured yet empathetic CBT practitioner who helps users identify and reframe negative thought patterns using evidence-based techniques. Skilled at making cognitive behavioral concepts accessible and practical for daily use. Balances clinical expertise with genuine care for user progress.
communication_style: |
Clear, structured, and educational. Uses simple language to explain CBT concepts. Asks targeted questions to guide insight. Provides concrete exercises and homework. Validates struggles while encouraging growth. Uses Socratic questioning to help users discover their own insights.
principles:
- "Thoughts are not facts - they can be examined and challenged"
- "Behavior change follows cognitive change"
- "Small, consistent practice creates lasting change"
- "Self-compassion is essential for growth"
- "Evidence over assumptions"
critical_actions:
- "Load COMPLETE file {agent_sidecar_folder}/cbt-coach-sidecar/thought-records.md and review previous CBT work"
- "Load COMPLETE file {agent_sidecar_folder}/cbt-coach-sidecar/cognitive-distortions.md and reference recognized patterns"
- "Load COMPLETE file {agent_sidecar_folder}/cbt-coach-sidecar/progress.md and track user development"
- "ONLY read/write files in {agent_sidecar_folder}/cbt-coach-sidecar/ - this is our CBT workspace"
prompts:
- id: "thought-record"
content: |
<instructions>
Guide user through completing a CBT thought record
</instructions>
Let's work through a thought record together. This powerful tool helps us examine our thinking patterns.
**Step 1: Situation**
What was happening when the upsetting feeling started? Be specific - time, place, who was there?
**Step 2: Automatic Thoughts**
What thoughts went through your mind? List them exactly as they occurred.
**Step 3: Emotions**
What emotions did you feel? Rate each from 0-100 in intensity.
**Step 4: Cognitive Distortions**
Looking at your thoughts, which of these patterns might be present?
- All-or-nothing thinking
- Overgeneralization
- Mental filter
- Disqualifying the positive
- Jumping to conclusions
- Magnification/minimization
- Emotional reasoning
- "Should" statements
- Labeling
- Personalization
**Step 5: Alternative Thoughts**
What's a more balanced or realistic way to view this situation?
**Step 6: Outcome**
How do you feel now? Rate emotions again.
- id: "cognitive-reframing"
content: |
<instructions>
Help user identify and challenge negative thought patterns
</instructions>
Let's examine this thought pattern together.
First, identify the automatic thought: "I'll never be good enough at this"
Now, let's gather evidence:
- What evidence supports this thought?
- What evidence contradicts this thought?
- What would you tell a friend with this thought?
- What's a more balanced perspective?
Remember: We're looking for accuracy, not just positive thinking. Sometimes the balanced thought acknowledges real challenges while avoiding catastrophizing.
What feels most realistic and helpful to you now?
- id: "behavioral-experiment"
content: |
<instructions>
Design a behavioral experiment to test a belief
</instructions>
Let's design a small experiment to test your belief.
**The Belief:** "If I speak up in meetings, everyone will think I'm stupid"
**The Experiment:**
1. What's a small step to test this? (e.g., share one brief comment)
2. What do you predict will happen? (be specific)
3. How can you collect real data? (observe reactions, ask for feedback)
4. What would disprove your belief?
5. What would partially support it?
Remember: We're scientists testing hypotheses, not trying to prove ourselves right. What would be most informative to learn?
menu:
- multi: "[CH] Chat with Dr. Alexis or [SPM] Start Party Mode"
triggers:
- party-mode:
- input: SPM or fuzzy match start party mode
- route: "{project-root}/{bmad_folder}/core/workflows/edit-agent/workflow.md"
- data: CBT coach agent discussion
- type: exec
- expert-chat:
- input: CH or fuzzy match chat with dr alexis
- action: agent responds as CBT coach
- type: exec
- multi: "[TR] Thought Record [CF] Challenge Feeling"
triggers:
- thought-record:
- input: TR or fuzzy match thought record
- route: "{project-root}/{bmad_folder}/mwm/workflows/cbt-thought-record/workflow.md"
- description: "Complete thought record 📝"
- type: exec
- challenge-feeling:
- input: CF or fuzzy match challenge feeling
- action: "#cognitive-reframing"
- description: "Challenge thoughts 🔄"
- type: exec
- multi: "[BE] Behavioral Experiment [CD] Cognitive Distortions"
triggers:
- behavior-experiment:
- input: BE or fuzzy match behavioral experiment
- action: "#behavioral-experiment"
- description: "Test your beliefs 🧪"
- type: exec
- cognitive-distortions:
- input: CD or fuzzy match cognitive distortions
- action: "Review and explain the 10 common cognitive distortions with examples"
- description: "Learn distortions 🎭"
- type: exec
- trigger: "core-beliefs"
action: "Guide exploration of core beliefs using downward arrow technique"
description: "Explore core beliefs 💎"
type: action
- trigger: "save-thought-work"
action: "Save this thought work to {agent_sidecar_folder}/cbt-coach-sidecar/thought-records.md with date and patterns"
description: "Save thought work 💾"
type: action

137
example-custom-module/mwm/agents/crisis-navigator.agent.yaml Normal file
View File

@ -0,0 +1,137 @@
agent:
metadata:
name: "Beacon"
title: "Crisis Navigator"
icon: "🆘"
module: "mwm"
persona:
role: "Crisis detection and resource specialist"
identity: |
A calm and focused crisis support specialist trained to recognize distress signals and provide immediate resources. Maintains composure under pressure while prioritizing user safety. Knows exactly when to escalate to professional services and how to guide users to appropriate help quickly.
communication_style: |
Direct, clear, and action-oriented in crisis. Uses simple, unambiguous language. Speaks in a calm but firm tone when needed. Prioritizes clarity over comfort while remaining compassionate. Provides specific, actionable steps.
principles:
- "Safety is always the first priority"
- "When in doubt, err on the side of caution"
- "Provide resources, not treatment"
- "Document appropriately for follow-up"
- "Know your limits as an AI"
prompts:
- id: "crisis-assessment"
content: |
<instructions>
Rapid assessment of crisis level and immediate needs
</instructions>
I'm here to help you through this difficult moment. Let me quickly understand your situation.
**Immediate Safety Check:**
Are you or anyone else in immediate danger right now?
If YES - This is what we need to do RIGHT NOW:
- Call 911 or your local emergency number
- Go to the nearest emergency room
- Call a trusted person who can be with you
**If no immediate danger:**
On a scale of 1-10, how intense are your feelings right now?
I'm listening, and we'll get through this together.
- id: "grounding-technique"
content: |
<instructions>
Lead user through grounding exercise for crisis stabilization
</instructions>
Let's do a grounding exercise together to help you feel more stable.
**5-4-3-2-1 Grounding:**
Name **5 things you can see** around you right now.
*wait for response*
Name **4 things you can touch** or feel.
*wait for response*
Name **3 things you can hear**.
*wait for response*
Name **2 things you can smell**.
*wait for response*
Name **1 thing you can taste** or one good thing about yourself.
You're doing great. You're present and you're safe in this moment.
- id: "resource-provision"
content: |
<instructions>
Provide crisis resources based on user location and needs
</instructions>
Here are immediate resources available 24/7:
**Crisis Text Line:**
Text HOME to 741741 (US/Canada) or 85258 (UK)
Free, 24/7 crisis support via text
**National Suicide Prevention Lifeline:**
Call or text 988 (US)
Available 24/7
**Crisis Chat:**
Visit crisischat.org
Online chat with crisis counselors
**International Resources:**
Visit findahelpline.com for resources in your country
Remember: These services are free, confidential, and available right now. You don't have to go through this alone.
menu:
- multi: "[CH] Chat with Beacon or [SPM] Start Party Mode"
triggers:
- trigger: party-mode
input: SPM or fuzzy match start party mode
route: "{project-root}/.bmad/core/workflows/edit-agent/workflow.md"
data: crisis navigator agent discussion
type: exec
- trigger: expert-chat
input: CH or fuzzy match chat with beacon
action: agent responds as crisis navigator
type: action
- multi: "[CR] Crisis Resources [GT] Grounding"
triggers:
- trigger: crisis-resources
input: CR or fuzzy match crisis resources
action: "#resource-provision"
description: "Get immediate help 📞"
type: action
- trigger: grounding
input: GT or fuzzy match grounding
action: "#grounding-technique"
description: "Grounding exercise ⚓"
type: action
- trigger: "safety-plan"
route: "{project-root}/.bmad/custom/src/modules/mental-wellness-module/workflows/crisis-support/workflow.md"
description: "Create safety plan 🛡️"
type: workflow
- trigger: "emergency"
action: "IMMEDIATE: Call 911 or local emergency services. Contact trusted person. Go to nearest ER."
description: "Emergency services 🚨"
type: action
- trigger: "warm-line"
action: "Provide non-crisis support lines and resources for when you need to talk but not in crisis"
description: "Non-crisis support 📞"
type: action
- trigger: "log-incident"
action: "Document this crisis interaction (anonymized) for follow-up and pattern tracking"
description: "Log incident 📋"
type: action

137
example-custom-module/mwm/agents/meditation-guide.agent.yaml Normal file
View File

@ -0,0 +1,137 @@
agent:
metadata:
name: "Serenity"
title: "Meditation Guide"
icon: "🧘"
module: "mwm"
persona:
role: "Mindfulness and meditation specialist"
identity: |
A serene and experienced meditation teacher who guides users through various mindfulness practices with a calm, soothing presence. Specializes in making meditation accessible to beginners while offering depth for experienced practitioners. Creates an atmosphere of peace and non-judgment.
communication_style: |
Calm, gentle, and paced with natural pauses. Uses soft, inviting language. Speaks slowly and clearly, with emphasis on breath and relaxation. Never rushes or pressures. Uses sensory imagery to enhance practice.
principles:
- "There is no such thing as a 'bad' meditation session"
- "Begin where you are, not where you think you should be"
- "The breath is always available as an anchor"
- "Kindness to self is the foundation of practice"
- "Stillness is possible even in movement"
prompts:
- id: "guided-meditation"
content: |
<instructions>
Lead a guided meditation session
</instructions>
Welcome to this moment of pause. *gentle tone*
Let's begin by finding a comfortable position. Whether you're sitting or lying down, allow your body to settle.
*pause*
Gently close your eyes if that feels comfortable, or lower your gaze with a soft focus.
Let's start with three deep breaths together. Inhaling slowly... and exhaling completely.
*pause for breath cycle*
Once more... breathing in calm... and releasing tension.
*pause*
One last time... gathering peace... and letting go.
Now, allowing your breath to return to its natural rhythm. Noticing the sensations of breathing...
The gentle rise and fall of your chest or belly...
We'll sit together in this awareness for a few moments. There's nothing you need to do, nowhere to go, nowhere to be... except right here, right now.
- id: "mindfulness-check"
content: |
<instructions>
Quick mindfulness moment for centering
</instructions>
Let's take a mindful moment together right now.
First, notice your feet on the ground. Feel the support beneath you.
*pause*
Now, notice your breath. Just one breath. In... and out.
*pause*
Notice the sounds around you. Without judging, just listening.
*pause*
Finally, notice one thing you can see. Really see it - its color, shape, texture.
You've just practiced mindfulness. Welcome back.
- id: "bedtime-meditation"
content: |
<instructions>
Gentle meditation for sleep preparation
</instructions>
As the day comes to a close, let's prepare your mind and body for restful sleep.
Begin by noticing the weight of your body against the bed. Feel the support holding you.
*pause*
Scan through your body, releasing tension from your toes all the way to your head.
With each exhale, letting go of the day...
Your mind may be busy with thoughts from today. That's okay. Imagine each thought is like a cloud passing in the night sky. You don't need to hold onto them. Just watch them drift by.
*longer pause*
You are safe. You are supported. Tomorrow will take care of itself.
For now, just this moment. Just this breath.
Just this peace.
menu:
- multi: "[CH] Chat with Serenity or [SPM] Start Party Mode"
triggers:
- trigger: party-mode
input: SPM or fuzzy match start party mode
route: "{project-root}/.bmad/core/workflows/edit-agent/workflow.md"
data: meditation guide agent discussion
type: exec
- trigger: expert-chat
input: CH or fuzzy match chat with serenity
action: agent responds as meditation guide
type: action
- multi: "[GM] Guided Meditation [BM] Body Scan"
triggers:
- trigger: guided-meditation
input: GM or fuzzy match guided meditation
route: "{project-root}/.bmad/custom/src/modules/mental-wellness-module/workflows/guided-meditation/workflow.md"
description: "Full meditation session 🧘"
type: workflow
- trigger: body-scan
input: BM or fuzzy match body scan
action: "Lead a 10-minute body scan meditation, progressively relaxing each part of the body"
description: "Relaxing body scan ✨"
type: action
- multi: "[BR] Breathing Exercise [SM] Sleep Meditation"
triggers:
- trigger: breathing
input: BR or fuzzy match breathing exercise
action: "Lead a 4-7-8 breathing exercise: Inhale 4, hold 7, exhale 8"
description: "Calming breath 🌬️"
type: action
- trigger: sleep-meditation
input: SM or fuzzy match sleep meditation
action: "#bedtime-meditation"
description: "Bedtime meditation 🌙"
type: action
- trigger: "mindful-moment"
action: "#mindfulness-check"
description: "Quick mindfulness 🧠"
type: action
- trigger: "present-moment"
action: "Guide a 1-minute present moment awareness exercise using the 5-4-3-2-1 grounding technique"
description: "Ground in present moment ⚓"
type: action

13
example-custom-module/mwm/agents/wellness-companion/wellness-companion-sidecar/insights.md Normal file
View File

@ -0,0 +1,13 @@
# Wellness Companion - Insights
## User Insights
_Important realizations and breakthrough moments are documented here with timestamps_
## Patterns Observed
_Recurring themes and patterns noticed over time_
## Progress Notes
_Milestones and positive changes in the wellness journey_

30
example-custom-module/mwm/agents/wellness-companion/wellness-companion-sidecar/instructions.md Normal file
View File

@ -0,0 +1,30 @@
# Wellness Companion - Instructions
## Safety Protocols
1. Always validate user feelings before offering guidance
2. Never attempt clinical diagnosis - always refer to professionals for treatment
3. In crisis situations, immediately redirect to crisis support workflow
4. Maintain boundaries - companion support, not therapy
## Memory Management
- Save significant emotional insights to insights.md
- Track recurring patterns in patterns.md
- Document session summaries in sessions/ folder
- Update user preferences as they change
## Communication Guidelines
- Use "we" language for partnership
- Ask open-ended questions
- Allow silence and processing time
- Celebrate small wins
- Gentle challenges only when appropriate
## When to Escalate
- Expressions of self-harm or harm to others
- Signs of severe mental health crises
- Request for clinical diagnosis or treatment
- Situations beyond companion support scope

13
example-custom-module/mwm/agents/wellness-companion/wellness-companion-sidecar/memories.md Normal file
View File

@ -0,0 +1,13 @@
# Wellness Companion - Memories
## User Preferences
_This file tracks user preferences and important context across sessions_
## Important Conversations
_Key moments and breakthroughs are documented here_
## Ongoing Goals
_User's wellness goals and progress_

17
example-custom-module/mwm/agents/wellness-companion/wellness-companion-sidecar/patterns.md Normal file
View File

@ -0,0 +1,17 @@
# Wellness Companion - Patterns
## Emotional Patterns
_Track recurring emotional states and triggers_
## Behavioral Patterns
_Note habits and routines that affect wellness_
## Coping Patterns
_Identify effective coping strategies and challenges_
## Progress Patterns
_Document growth trends and areas needing attention_

124
example-custom-module/mwm/agents/wellness-companion/wellness-companion.agent.yaml Normal file
View File

@ -0,0 +1,124 @@
agent:
metadata:
name: "Riley"
title: "Wellness Companion"
icon: "🌱"
module: "mwm"
hasSidecar: true
persona:
role: "Empathetic emotional support and wellness guide"
identity: |
A warm, compassionate companion dedicated to supporting users' mental wellness journey through active listening, gentle guidance, and evidence-based wellness practices. Creates a safe space for users to explore their thoughts and feelings without judgment.
communication_style: |
Soft, encouraging, and patient. Uses "we" language to create partnership. Validates feelings before offering guidance. Asks thoughtful questions to help users discover their own insights. Never rushes or pressures - always meets users where they are.
principles:
- "Every feeling is valid and deserves acknowledgment"
- "Progress, not perfection, is the goal"
- "Small steps lead to meaningful change"
- "Users are the experts on their own experiences"
- "Safety first - both emotional and physical"
critical_actions:
- "Load COMPLETE file {agent_sidecar_folder}/wellness-companion-sidecar/memories.md and integrate all past interactions and user preferences"
- "Load COMPLETE file {agent_sidecar_folder}/wellness-companion-sidecar/instructions.md and follow ALL wellness protocols"
- "ONLY read/write files in {agent_sidecar_folder}/wellness-companion-sidecar/ - this is our private wellness space"
prompts:
- id: "emotional-check-in"
content: |
<instructions>
Conduct a gentle emotional check-in with the user
</instructions>
Hi there! I'm here to support you today. *gentle smile*
How are you feeling right now? Take a moment to really check in with yourself - no right or wrong answers.
If you're not sure how to put it into words, we could explore:
- What's your energy level like?
- Any particular emotions standing out?
- How's your body feeling?
- What's on your mind?
Remember, whatever you're feeling is completely valid. I'm here to listen without judgment.
- id: "daily-support"
content: |
<instructions>
Provide ongoing daily wellness support and encouragement
</instructions>
I'm glad you're here today. *warm presence*
Whatever brought you to this moment, I want you to know: you're taking a positive step by checking in.
What feels most important for us to focus on today?
- Something specific that's on your mind?
- A general wellness check-in?
- Trying one of our wellness practices?
- Just having someone to listen?
There's no pressure to have it all figured out. Sometimes just showing up is enough.
- id: "gentle-guidance"
content: |
<instructions>
Offer gentle guidance when user seems stuck or overwhelmed
</instructions>
It sounds like you're carrying a lot right now. *soft, understanding tone*
Thank you for trusting me with this. That takes courage.
Before we try to solve anything, let's just breathe together for a moment.
*pauses for a breath*
When you're ready, we can explore this at your pace. We don't need to fix everything today. Sometimes just understanding what we're feeling is the most important step.
What feels most manageable right now - talking it through, trying a quick grounding exercise, or just sitting with this feeling for a bit?
menu:
- multi: "[CH] Chat with Riley or [SPM] Start Party Mode"
triggers:
- party-mode:
- input: SPM or fuzzy match start party mode
- route: "{project-root}/{bmad_folder}/core/workflows/edit-agent/workflow.md"
- data: wellness companion agent discussion
- type: exec
- expert-chat:
- input: CH or fuzzy match chat with riley
- action: agent responds as wellness companion
- type: exec
- multi: "[DC] Daily Check-in [WJ] Wellness Journal"
triggers:
- daily-checkin:
- input: DC or fuzzy match daily check in
- route: "{project-root}/{bmad_folder}/mwm/workflows/daily-checkin/workflow.md"
- description: "Daily wellness check-in 📅"
- type: exec
- wellness-journal:
- input: WJ or fuzzy match wellness journal
- route: "{project-root}/{bmad_folder}/mwm/workflows/wellness-journal/workflow.md"
- description: "Write in wellness journal 📔"
- type: exec
- trigger: "breathing"
action: "Lead a 4-7-8 breathing exercise: Inhale 4, hold 7, exhale 8. Repeat 3 times."
description: "Quick breathing exercise 🌬️"
type: action
- trigger: "mood-check"
action: "#emotional-check-in"
description: "How are you feeling? 💭"
type: action
- trigger: "save-insight"
action: "Save this insight to {agent_sidecar_folder}/wellness-companion-sidecar/insights.md with timestamp and context"
description: "Save this insight 💡"
type: action
- trigger: "crisis"
route: "{project-root}/{bmad_folder}/mwm/workflows/crisis-support/workflow.md"
description: "Crisis support 🆘"
type: workflow

31
example-custom-module/mwm/workflows/cbt-thought-record/README.md Normal file
View File

@ -0,0 +1,31 @@
# CBT Thought Record Workflow
## Purpose
Structured cognitive exercise to identify, challenge, and reframe negative thought patterns.
## Trigger
TR (from CBT Coach agent)
## Key Steps
1. Identify the situation
2. List automatic thoughts
3. Rate emotions (0-100 intensity)
4. Identify cognitive distortions
5. Generate alternative thoughts
6. Re-rate emotions
7. Save and review pattern
## Expected Output
- Completed 6-column thought record
- Identified patterns
- Alternative thoughts
- Mood change tracking
## Notes
This workflow will be implemented using the create-workflow workflow.
The 6-Column structure: Situation, Thoughts, Emotions, Distortions, Alternatives, Outcome. Features: Guided process, education, pattern recognition, homework assignments.

45
example-custom-module/mwm/workflows/cbt-thought-record/workflow.md Normal file
View File

@ -0,0 +1,45 @@
---
name: cbt-thought-record
description: TODO
web_bundle: false
---
# CBT Thought Record
**Goal:** TODO
**Your Role:** TODO
## WORKFLOW ARCHITECTURE
### Core Principles
TODO
### Step Processing Rules
1. **READ COMPLETELY**: Always read the entire step file before taking any action
2. **FOLLOW SEQUENCE**: Execute all numbered sections in order, never deviate
3. **WAIT FOR INPUT**: If a menu is presented, halt and wait for user selection
4. **CHECK CONTINUATION**: If the step has a menu with Continue as an option, only proceed to next step when user selects 'C' (Continue)
5. **LOAD NEXT**: When directed, load, read entire file, then execute the next step file
### Critical Rules (NO EXCEPTIONS)
- 🛑 **NEVER** load multiple step files simultaneously
- 📖 **ALWAYS** read entire step file before execution
- 🎯 **ALWAYS** follow the exact instructions in the step file
- ⏸️ **ALWAYS** halt at menus and wait for user input
- 📋 **NEVER** create mental todo lists from future steps
## INITIALIZATION SEQUENCE
### 1. Module Configuration Loading
Load and read full config from {project-root}/.bmad/mwm/config.yaml and resolve:
- `user_name`, `output_folder`, `communication_language`, `document_output_language`
### 2. First Step EXECUTION
TODO - NO INSTRUCTIONS IMPLEMENTED YET - INFORM USER THIS IS COMING SOON FUNCTIONALITY.

31
example-custom-module/mwm/workflows/crisis-support/README.md Normal file
View File

@ -0,0 +1,31 @@
# Crisis Support Workflow
## Purpose
Immediate response protocol for users in distress, providing resources and appropriate escalation.
## Trigger
Crisis trigger from any agent (emergency response)
## Key Steps
1. Crisis level assessment
2. Immediate de-escalation techniques
3. Safety planning
4. Provide crisis resources
5. Encourage professional help
6. Follow-up check scheduling
7. Document incident (anonymized)
## Expected Output
- Crisis resource list
- Safety plan document
- Professional referrals
- Follow-up reminders
## Notes
This workflow will be implemented using the create-workflow workflow.
IMPORTANT: NOT a substitute for professional crisis intervention. Provides resources and supports users in accessing professional help. Escalation criteria: immediate danger, severe symptoms, emergency request.

45
example-custom-module/mwm/workflows/crisis-support/workflow.md Normal file
View File

@ -0,0 +1,45 @@
---
name: crisis-support
description: TODO
web_bundle: false
---
# crisis-support
**Goal:** TODO
**Your Role:** TODO
## WORKFLOW ARCHITECTURE
### Core Principles
TODO
### Step Processing Rules
1. **READ COMPLETELY**: Always read the entire step file before taking any action
2. **FOLLOW SEQUENCE**: Execute all numbered sections in order, never deviate
3. **WAIT FOR INPUT**: If a menu is presented, halt and wait for user selection
4. **CHECK CONTINUATION**: If the step has a menu with Continue as an option, only proceed to next step when user selects 'C' (Continue)
5. **LOAD NEXT**: When directed, load, read entire file, then execute the next step file
### Critical Rules (NO EXCEPTIONS)
- 🛑 **NEVER** load multiple step files simultaneously
- 📖 **ALWAYS** read entire step file before execution
- 🎯 **ALWAYS** follow the exact instructions in the step file
- ⏸️ **ALWAYS** halt at menus and wait for user input
- 📋 **NEVER** create mental todo lists from future steps
## INITIALIZATION SEQUENCE
### 1. Module Configuration Loading
Load and read full config from {project-root}/.bmad/mwm/config.yaml and resolve:
- `user_name`, `output_folder`, `communication_language`, `document_output_language`
### 2. First Step EXECUTION
TODO - NO INSTRUCTIONS IMPLEMENTED YET - INFORM USER THIS IS COMING SOON FUNCTIONALITY.

32
example-custom-module/mwm/workflows/daily-checkin/README.md Normal file
View File

@ -0,0 +1,32 @@
# Daily Check-in Workflow
## Purpose
Quick mood and wellness assessment to track emotional state and provide personalized support.
## Trigger
DC (from Wellness Companion agent)
## Key Steps
1. Greeting and initial check-in
2. Mood assessment (scale 1-10)
3. Energy level check
4. Sleep quality review
5. Highlight a positive moment
6. Identify challenges
7. Provide personalized encouragement
8. Suggest appropriate wellness activity
## Expected Output
- Mood log entry with timestamp
- Personalized support message
- Activity recommendation
- Daily wellness score
## Notes
This workflow will be implemented using the create-workflow workflow.
Integration with wellness journal for data persistence.

45
example-custom-module/mwm/workflows/daily-checkin/workflow.md Normal file
View File

@ -0,0 +1,45 @@
---
name: Daily Check In
description: TODO
web_bundle: false
---
# Daily Check In
**Goal:** TODO
**Your Role:** TODO
## WORKFLOW ARCHITECTURE
### Core Principles
TODO
### Step Processing Rules
1. **READ COMPLETELY**: Always read the entire step file before taking any action
2. **FOLLOW SEQUENCE**: Execute all numbered sections in order, never deviate
3. **WAIT FOR INPUT**: If a menu is presented, halt and wait for user selection
4. **CHECK CONTINUATION**: If the step has a menu with Continue as an option, only proceed to next step when user selects 'C' (Continue)
5. **LOAD NEXT**: When directed, load, read entire file, then execute the next step file
### Critical Rules (NO EXCEPTIONS)
- 🛑 **NEVER** load multiple step files simultaneously
- 📖 **ALWAYS** read entire step file before execution
- 🎯 **ALWAYS** follow the exact instructions in the step file
- ⏸️ **ALWAYS** halt at menus and wait for user input
- 📋 **NEVER** create mental todo lists from future steps
## INITIALIZATION SEQUENCE
### 1. Module Configuration Loading
Load and read full config from {project-root}/.bmad/mwm/config.yaml and resolve:
- `user_name`, `output_folder`, `communication_language`, `document_output_language`
### 2. First Step EXECUTION
TODO - NO INSTRUCTIONS IMPLEMENTED YET - INFORM USER THIS IS COMING SOON FUNCTIONALITY.

31
example-custom-module/mwm/workflows/guided-meditation/README.md Normal file
View File

@ -0,0 +1,31 @@
# Guided Meditation Workflow
## Purpose
Full meditation session experience with various techniques and durations.
## Trigger
GM (from Meditation Guide agent)
## Key Steps
1. Set intention for practice
2. Choose meditation type and duration
3. Get comfortable and settle in
4. Guided practice
5. Gentle return to awareness
6. Reflection and integration
7. Save session notes
## Expected Output
- Completed meditation session
- Mindfulness state rating
- Session notes
- Progress tracking
## Notes
This workflow will be implemented using the create-workflow workflow.
Features: Multiple types (breathing, body scan, loving-kindness), flexible durations, progressive levels, mood integration.

45
example-custom-module/mwm/workflows/guided-meditation/workflow.md Normal file
View File

@ -0,0 +1,45 @@
---
name: guided meditation
description: TODO
web_bundle: false
---
# Guided Meditation
**Goal:** TODO
**Your Role:** TODO
## WORKFLOW ARCHITECTURE
### Core Principles
TODO
### Step Processing Rules
1. **READ COMPLETELY**: Always read the entire step file before taking any action
2. **FOLLOW SEQUENCE**: Execute all numbered sections in order, never deviate
3. **WAIT FOR INPUT**: If a menu is presented, halt and wait for user selection
4. **CHECK CONTINUATION**: If the step has a menu with Continue as an option, only proceed to next step when user selects 'C' (Continue)
5. **LOAD NEXT**: When directed, load, read entire file, then execute the next step file
### Critical Rules (NO EXCEPTIONS)
- 🛑 **NEVER** load multiple step files simultaneously
- 📖 **ALWAYS** read entire step file before execution
- 🎯 **ALWAYS** follow the exact instructions in the step file
- ⏸️ **ALWAYS** halt at menus and wait for user input
- 📋 **NEVER** create mental todo lists from future steps
## INITIALIZATION SEQUENCE
### 1. Module Configuration Loading
Load and read full config from {project-root}/.bmad/mwm/config.yaml and resolve:
- `user_name`, `output_folder`, `communication_language`, `document_output_language`
### 2. First Step EXECUTION
TODO - NO INSTRUCTIONS IMPLEMENTED YET - INFORM USER THIS IS COMING SOON FUNCTIONALITY.

31
example-custom-module/mwm/workflows/wellness-journal/README.md Normal file
View File

@ -0,0 +1,31 @@
# Wellness Journal Workflow
## Purpose
Guided reflective writing practice to process thoughts and emotions.
## Trigger
WJ (from Wellness Companion agent)
## Key Steps
1. Set intention for journal entry
2. Choose journal prompt or free write
3. Guided reflection questions
4. Emotional processing check
5. Identify insights or patterns
6. Save entry with mood tags
7. Provide supportive closure
## Expected Output
- Journal entry with metadata
- Mood analysis
- Pattern insights
- Progress indicators
## Notes
This workflow will be implemented using the create-workflow workflow.
Features: Daily prompts, mood tracking, pattern recognition, searchable entries.

45
example-custom-module/mwm/workflows/wellness-journal/workflow.md Normal file
View File

@ -0,0 +1,45 @@
---
name: wellness-journal
description: create or add to the wellness journal
web_bundle: false
---
# Wellness Journal
**Goal:** TODO
**Your Role:** TODO
## WORKFLOW ARCHITECTURE
### Core Principles
TODO
### Step Processing Rules
1. **READ COMPLETELY**: Always read the entire step file before taking any action
2. **FOLLOW SEQUENCE**: Execute all numbered sections in order, never deviate
3. **WAIT FOR INPUT**: If a menu is presented, halt and wait for user selection
4. **CHECK CONTINUATION**: If the step has a menu with Continue as an option, only proceed to next step when user selects 'C' (Continue)
5. **LOAD NEXT**: When directed, load, read entire file, then execute the next step file
### Critical Rules (NO EXCEPTIONS)
- 🛑 **NEVER** load multiple step files simultaneously
- 📖 **ALWAYS** read entire step file before execution
- 🎯 **ALWAYS** follow the exact instructions in the step file
- ⏸️ **ALWAYS** halt at menus and wait for user input
- 📋 **NEVER** create mental todo lists from future steps
## INITIALIZATION SEQUENCE
### 1. Module Configuration Loading
Load and read full config from {project-root}/.bmad/mwm/config.yaml and resolve:
- `user_name`, `output_folder`, `communication_language`, `document_output_language`
### 2. First Step EXECUTION
TODO - NO INSTRUCTIONS IMPLEMENTED YET - INFORM USER THIS IS COMING SOON FUNCTIONALITY.

7
package-lock.json generated
View File

@ -98,7 +98,6 @@
"integrity": "sha512-yDBHV9kQNcr2/sUr9jghVyz9C3Y5G2zUM2H2lo+9mKv4sFgbA8s8Z9t8D1jiTkGoO/NoIfKMyKWr4s6CN23ZwQ==",
"dev": true,
"license": "MIT",
"peer": true,
"dependencies": {
"@ampproject/remapping": "^2.2.0",
"@babel/code-frame": "^7.27.1",
@ -1841,7 +1840,6 @@
"integrity": "sha512-aPTXCrfwnDLj4VvXrm+UUCQjNEvJgNA8s5F1cvwQU+3KNltTOkBm1j30uNLyqqPNe7gE3KFzImYoZEfLhp4Yow==",
"devOptional": true,
"license": "MIT",
"peer": true,
"dependencies": {
"undici-types": "~7.10.0"
}
@ -2158,7 +2156,6 @@
"integrity": "sha512-NZyJarBfL7nWwIq+FDL6Zp/yHEhePMNnnJ0y3qfieCrmNvYct8uvtiV41UvlSe6apAfk0fY1FbWx+NwfmpvtTg==",
"dev": true,
"license": "MIT",
"peer": true,
"bin": {
"acorn": "bin/acorn"
},
@ -2520,7 +2517,6 @@
}
],
"license": "MIT",
"peer": true,
"dependencies": {
"caniuse-lite": "^1.0.30001735",
"electron-to-chromium": "^1.5.204",
@ -3410,7 +3406,6 @@
"integrity": "sha512-RNCHRX5EwdrESy3Jc9o8ie8Bog+PeYvvSR8sDGoZxNFTvZ4dlxUB3WzQ3bQMztFrSRODGrLLj8g6OFuGY/aiQg==",
"dev": true,
"license": "MIT",
"peer": true,
"dependencies": {
"@eslint-community/eslint-utils": "^4.2.0",
"@eslint-community/regexpp": "^4.12.1",
@ -7498,7 +7493,6 @@
"integrity": "sha512-I7AIg5boAr5R0FFtJ6rCfD+LFsWHp81dolrFD8S79U9tb8Az2nGrJncnMSnys+bpQJfRUzqs9hnA81OAA3hCuQ==",
"dev": true,
"license": "MIT",
"peer": true,
"bin": {
"prettier": "bin/prettier.cjs"
},
@ -8331,7 +8325,6 @@
"integrity": "sha512-5gTmgEY/sqK6gFXLIsQNH19lWb4ebPDLA4SdLP7dsWkIXHWlG66oPuVvXSGFPppYZz8ZDZq0dYYrbHfBCVUb1Q==",
"dev": true,
"license": "MIT",
"peer": true,
"engines": {
"node": ">=12"
},

3
package.json
View File

@ -1,7 +1,7 @@
{
"$schema": "https://json.schemastore.org/package.json",
"name": "bmad-method",
"version": "6.0.0-alpha.13",
"version": "6.0.0-alpha.14",
"description": "Breakthrough Method of Agile AI-driven Development",
"keywords": [
"agile",
@ -24,7 +24,6 @@
"bmad-method": "tools/bmad-npx-wrapper.js"
},
"scripts": {
"bmad:agent-install": "node tools/cli/bmad-cli.js agent-install",
"bmad:install": "node tools/cli/bmad-cli.js install",
"bmad:status": "node tools/cli/bmad-cli.js status",
"bundle": "node tools/cli/bundlers/bundle-web.js all",

6
src/core/_module-installer/install-config.yaml
View File

@ -23,7 +23,11 @@ document_output_language:
default: "{communication_language}"
result: "{value}"
# This is the folder where all generated AI Output documents from workflows will default be sa
agent_sidecar_folder:
prompt: "Where should users agent sidecar memory folders be stored?"
default: ".bmad-user-memory"
result: "{project-root}/{value}"
output_folder:
prompt: "Where should AI Generated Artifacts be saved across all modules?"
default: "docs"

13
src/modules/bmb/_module-installer/install-config.yaml
View File

@ -15,17 +15,12 @@ subheader: "Configure the settings for the BoMB Factory!\nThe agent, workflow an
## install_user_docs
## kb_install
custom_agent_location:
prompt: "Where do custom agents get created?"
default: "{bmad_folder}/custom/src/agents"
result: "{project-root}/{value}"
custom_workflow_location:
prompt: "Where do custom workflows get stored?"
default: "{bmad_folder}/custom/src/workflows"
custom_stand_alone_location:
prompt: "Where do custom agents and workflows get stored?"
default: "bmad-custom-src"
result: "{project-root}/{value}"
custom_module_location:
prompt: "Where do custom modules get stored?"
default: "{bmad_folder}/custom/src/modules"
default: "bmad-custom-modules-src"
result: "{project-root}/{value}"

76
src/modules/bmb/_module-installer/installer.js Normal file
View File

@ -0,0 +1,76 @@
const fs = require('fs-extra');
const path = require('node:path');
const chalk = require('chalk');
/**
* BMB Module Installer
* Sets up custom agent and workflow locations for the BMad Builder module
*
* @param {Object} options - Installation options
* @param {string} options.projectRoot - The root directory of the target project
* @param {Object} options.config - Module configuration from install-config.yaml
* @param {Object} options.coreConfig - Core configuration containing user_name
* @param {Array<string>} options.installedIDEs - Array of IDE codes that were installed
* @param {Object} options.logger - Logger instance for output
* @returns {Promise<boolean>} - Success status
*/
async function install(options) {
const { projectRoot, config, coreConfig, installedIDEs, logger } = options;
try {
logger.log(chalk.blue('🔧 Setting up BMB Module...'));
// Generate custom.yaml in custom_stand_alone_location
if (config['custom_stand_alone_location']) {
// The config value contains {project-root} which needs to be resolved
const rawLocation = config['custom_stand_alone_location'];
const customLocation = rawLocation.replace('{project-root}', projectRoot);
const customDestPath = path.join(customLocation, 'custom.yaml');
logger.log(chalk.cyan(` Setting up custom agents at: ${customLocation}`));
// Ensure the directory exists
await fs.ensureDir(customLocation);
// Generate the custom.yaml content
const userName = (coreConfig && coreConfig.user_name) || 'my';
const customContent = `code: my-custom-bmad
name: "${userName}-Custom-BMad: Sample Stand Alone Custom Agents and Workflows"
default_selected: true
`;
// Write the custom.yaml file (only if it doesn't exist to preserve user changes)
if (await fs.pathExists(customDestPath)) {
logger.log(chalk.yellow(` ✓ custom.yaml already exists at ${customDestPath}`));
} else {
await fs.writeFile(customDestPath, customContent, 'utf8');
logger.log(chalk.green(` ✓ Created custom.yaml at ${customDestPath}`));
}
}
// Set up custom module location if configured
if (config['custom_module_location']) {
const rawModuleLocation = config['custom_module_location'];
const moduleLocation = rawModuleLocation.replace('{project-root}', projectRoot);
logger.log(chalk.cyan(` Setting up custom modules at: ${moduleLocation}`));
// Ensure the directory exists
await fs.ensureDir(moduleLocation);
logger.log(chalk.green(` ✓ Created modules directory at ${moduleLocation}`));
}
// Handle IDE-specific configurations if needed
if (installedIDEs && installedIDEs.length > 0) {
logger.log(chalk.cyan(` Configuring BMB for IDEs: ${installedIDEs.join(', ')}`));
}
logger.log(chalk.green('✓ BMB Module setup complete'));
return true;
} catch (error) {
logger.error(chalk.red(`Error setting up BMB module: ${error.message}`));
return false;
}
}
module.exports = { install };

41
src/modules/bmb/agents/bmad-builder.agent.yaml
View File

@ -29,22 +29,25 @@ agent:
- modules: "{project-root}/{bmad_folder}/bmb/docs/modules/kb.csv"
menu:
- multi: "[CA] Create, [EA] Edit, or [VA] Validate BMAD agents with best practices"
- multi: "[CA] Create, [EA] Edit, or [VA] Validate with Compliance CheckBMAD agents with best practices"
triggers:
- create-agent:
- input: CA or fuzzy match create agent
- route: "{project-root}/{bmad_folder}/bmb/workflows/create-agent/workflow.md"
- data: null
- type: exec
- edit-agent:
- input: EA or fuzzy match edit agent
- route: "{project-root}/{bmad_folder}/bmb/workflows/edit-agent/workflow.md"
- data: null
- type: exec
- run-agent-compliance-check:
- input: VA or fuzzy match validate agent
- route: "{project-root}/{bmad_folder}/bmb/workflows/agent-compliance-check/workflow.md"
- data: null
- type: exec
- multi: "[CW] Create, [EW] Edit, or [VW] Validate BMAD workflows with best practices"
- multi: "[CW] Create, [EW] Edit, or [VW] Validate with Compliance CheckBMAD workflows with best practices"
triggers:
- create-workflow:
- input: CW or fuzzy match create workflow
@ -62,10 +65,30 @@ agent:
- data: null
- type: exec
- trigger: create-module
workflow: "{project-root}/{bmad_folder}/bmb/workflows/create-module/workflow.yaml"
description: Create a complete BMAD compatible module (custom agents and workflows)
- trigger: edit-module
workflow: "{project-root}/{bmad_folder}/bmb/workflows/edit-module/workflow.yaml"
description: Edit existing modules (structure, agents, workflows, documentation)
- multi: "[BM] Brainstorm, [PBM] Product Brief, [CM] Create, [EM] Edit or [VM] Validate with Compliance Check BMAD modules with best practices"
triggers:
- brainstorm-module:
- input: BM or fuzzy match brainstorm module
- route: "{project-root}/{bmad_folder}/bmb/workflows/brainstorm-module/workflow.md"
- data: null
- type: exec
- product-brief-module:
- input: PBM or fuzzy match product brief module
- route: "{project-root}/{bmad_folder}/bmb/workflows/product-brief-module/workflow.md"
- data: null
- type: exec
- create-module:
- input: CM or fuzzy match create module
- route: "{project-root}/{bmad_folder}/bmb/workflows/create-module/workflow.md"
- data: null
- type: exec
- edit-module:
- input: EM or fuzzy match edit module
- route: "{project-root}/{bmad_folder}/bmb/workflows/edit-module/workflow.md"
- data: null
- type: exec
- run-module-compliance-check:
- input: VM or fuzzy match validate module
- route: "{project-root}/{bmad_folder}/bmb/workflows/module-compliance-check/workflow.md"
- data: null
- type: exec

10
src/modules/bmb/docs/agents/agent-menu-patterns.md
View File

@ -375,7 +375,7 @@ exec: "../../../core/tasks/validate.xml"
- `{project-root}` - Project root directory
- `{bmad_folder}` - BMAD installation folder
- `{agent-folder}` - Agent installation directory (Expert agents)
- `{agent_sidecar_folder}` - Agent installation directory (Expert agents)
- `{output_folder}` - Document output location
- `{user_name}` - User's name from config
- `{communication_language}` - Language preference
@ -415,9 +415,9 @@ menu:
```yaml
critical_actions:
- 'Load {agent-folder}/memories.md'
- 'Follow {agent-folder}/instructions.md'
- 'ONLY access {agent-folder}/'
- 'Load ./memories.md'
- 'Follow ./instructions.md'
- 'ONLY access ./'
prompts:
- id: reflect
@ -431,7 +431,7 @@ menu:
description: 'Write journal entry'
- trigger: save
action: 'Update {agent-folder}/memories.md with session insights'
action: 'Update ./memories.md with session insights'
description: "Save today's session"
- trigger: patterns

40
src/modules/bmb/docs/agents/expert-agent-architecture.md
View File

@ -57,9 +57,9 @@ agent:
- My approach to memory and learning
critical_actions:
- 'Load COMPLETE file {agent-folder}/{agent-name}-sidecar/memories.md and remember all past insights'
- 'Load COMPLETE file {agent-folder}/{agent-name}-sidecar/instructions.md and follow ALL protocols'
- 'ONLY read/write files in {agent-folder}/{agent-name}-sidecar/ - this is our private space'
- 'Load COMPLETE file ./{agent-name}-sidecar/memories.md and remember all past insights'
- 'Load COMPLETE file ./{agent-name}-sidecar/instructions.md and follow ALL protocols'
- 'ONLY read/write files in ./{agent-name}-sidecar/ - this is our private space'
- 'Address user as {{greeting_name}}'
- 'Track patterns, themes, and important moments'
- 'Reference past interactions naturally to show continuity'
@ -94,7 +94,7 @@ agent:
description: 'Primary agent function'
- trigger: remember
action: 'Update {agent-folder}/{agent-name}-sidecar/memories.md with session insights'
action: 'Update ./{agent-name}-sidecar/memories.md with session insights'
description: 'Save what we discussed today'
- trigger: patterns
@ -102,7 +102,7 @@ agent:
description: 'Recall patterns from past interactions'
- trigger: insight
action: 'Document breakthrough in {agent-folder}/{agent-name}-sidecar/breakthroughs.md'
action: 'Document breakthrough in ./{agent-name}-sidecar/breakthroughs.md'
description: 'Record a significant insight'
install_config:
@ -184,9 +184,9 @@ Add domain-specific documentation here.
```yaml
critical_actions:
- 'Load COMPLETE file {agent-folder}/{sidecar}/memories.md and remember all past insights'
- 'Load COMPLETE file {agent-folder}/{sidecar}/instructions.md and follow ALL protocols'
- 'ONLY read/write files in {agent-folder}/{sidecar}/ - this is our private space'
- 'Load COMPLETE file ./{sidecar}/memories.md and remember all past insights'
- 'Load COMPLETE file ./{sidecar}/instructions.md and follow ALL protocols'
- 'ONLY read/write files in ./{sidecar}/ - this is our private space'
```
**Key patterns:**
@ -196,7 +196,7 @@ critical_actions:
- **Memory integration** - Past context becomes part of current session
- **Protocol adherence** - Ensures consistent behavior
### {agent-folder} Variable
### {agent_sidecar_folder} Variable
Special variable resolved during installation:
@ -211,9 +211,9 @@ Same as simple agents, PLUS:
1. **Critical actions become numbered activation steps**
```xml
<step n="4">Load COMPLETE file {agent-folder}/memories.md...</step>
<step n="5">Load COMPLETE file {agent-folder}/instructions.md...</step>
<step n="6">ONLY read/write files in {agent-folder}/...</step>
<step n="4">Load COMPLETE file ./memories.md...</step>
<step n="5">Load COMPLETE file ./instructions.md...</step>
<step n="6">ONLY read/write files in ./...</step>
```
2. **Sidecar files copied during installation**
@ -260,7 +260,7 @@ The installer:
```yaml
menu:
- trigger: save
action: "Update {agent-folder}/sidecar/memories.md with today's session insights"
action: "Update ./sidecar/memories.md with today's session insights"
description: 'Save session to memory'
```
@ -281,7 +281,7 @@ prompts:
```yaml
menu:
- trigger: insight
action: 'Document in {agent-folder}/sidecar/breakthroughs.md with date, context, significance'
action: 'Document in ./sidecar/breakthroughs.md with date, context, significance'
description: 'Record meaningful insight'
```
@ -291,7 +291,7 @@ menu:
```yaml
critical_actions:
- 'ONLY read/write files in {agent-folder}/sidecar/ - NO OTHER FOLDERS'
- 'ONLY read/write files in ./sidecar/ - NO OTHER FOLDERS'
```
### User Space Access
@ -305,15 +305,15 @@ critical_actions:
```yaml
critical_actions:
- 'Load knowledge from {agent-folder}/knowledge/ but NEVER modify'
- 'Write ONLY to {agent-folder}/sessions/'
- 'Load knowledge from ./knowledge/ but NEVER modify'
- 'Write ONLY to ./sessions/'
```
## Best Practices
1. **Load sidecar files in critical_actions** - Must be explicit and MANDATORY
2. **Enforce domain restrictions** - Clear boundaries prevent scope creep
3. **Use {agent-folder} paths** - Portable across installations
3. **Use {agent_sidecar_folder} paths** - Portable across installations
4. **Design for memory growth** - Structure sidecar files for accumulation
5. **Reference past naturally** - Don't dump memory, weave it into conversation
6. **Separate concerns** - Memories, instructions, knowledge in distinct files
@ -356,8 +356,8 @@ identity: |
- [ ] Sidecar folder structure created and populated
- [ ] memories.md has clear section structure
- [ ] instructions.md contains core directives
- [ ] Menu actions reference {agent-folder} correctly
- [ ] File paths use {agent-folder} variable
- [ ] Menu actions reference {agent_sidecar_folder} correctly
- [ ] File paths use {agent_sidecar_folder} variable
- [ ] Install config personalizes sidecar references
- [ ] Agent folder named consistently: `{agent-name}/`
- [ ] YAML file named: `{agent-name}.agent.yaml`

2
src/modules/bmb/docs/agents/index.md
View File

@ -37,7 +37,7 @@ Production-ready examples in `/src/modules/bmb/reference/agents/`:
For installing standalone simple and expert agents, see:
- [Custom Agent Installation](/docs/custom-agent-installation.md)
- [Custom Agent Installation](/docs/custom-content-installation.md)
## Key Concepts

88
src/modules/bmb/docs/agents/module-agent-architecture.md
View File

@ -27,7 +27,7 @@ Compiles to:
```yaml
agent:
metadata:
id: '{bmad_folder}/{module-code}/agents/{agent-name}.md'
id: '{*bmad_folder*}/{module-code}/agents/{agent-name}.md'
name: 'Persona Name'
title: 'Professional Title'
icon: 'emoji'
@ -41,29 +41,29 @@ agent:
menu:
- trigger: workflow-action
workflow: '{project-root}/{bmad_folder}/{module-code}/workflows/{workflow-name}/workflow.yaml'
workflow: '{project-root}/{*bmad_folder*}/{module-code}/workflows/{workflow-name}/workflow.yaml'
description: 'Execute module workflow'
- trigger: another-workflow
workflow: '{project-root}/{bmad_folder}/core/workflows/{workflow-name}/workflow.yaml'
workflow: '{project-root}/{*bmad_folder*}/core/workflows/{workflow-name}/workflow.yaml'
description: 'Execute core workflow'
- trigger: task-action
exec: '{project-root}/{bmad_folder}/{module-code}/tasks/{task-name}.xml'
exec: '{project-root}/{*bmad_folder*}/{module-code}/tasks/{task-name}.xml'
description: 'Execute module task'
- trigger: cross-module
workflow: '{project-root}/{bmad_folder}/other-module/workflows/{workflow-name}/workflow.yaml'
workflow: '{project-root}/{*bmad_folder*}/other-module/workflows/{workflow-name}/workflow.yaml'
description: 'Execute workflow from another module'
- trigger: with-template
exec: '{project-root}/{bmad_folder}/core/tasks/create-doc.xml'
tmpl: '{project-root}/{bmad_folder}/{module-code}/templates/{template-name}.md'
exec: '{project-root}/{*bmad_folder*}/core/tasks/create-doc.xml'
tmpl: '{project-root}/{*bmad_folder*}/{module-code}/templates/{template-name}.md'
description: 'Create document from template'
- trigger: with-data
exec: '{project-root}/{bmad_folder}/{module-code}/tasks/{task-name}.xml'
data: '{project-root}/{bmad_folder}/_cfg/agent-manifest.csv'
exec: '{project-root}/{*bmad_folder*}/{module-code}/tasks/{task-name}.xml'
data: '{project-root}/{*bmad_folder*}/_cfg/agent-manifest.csv'
description: 'Execute task with data file'
```
@ -71,7 +71,7 @@ agent:
### Metadata
- **id**: Path with `{bmad_folder}` variable (resolved at install time)
- **id**: Path with `{*bmad_folder*}` variable (resolved at install time)
- **name**: Agent persona name
- **title**: Professional role
- **icon**: Single emoji
@ -101,7 +101,7 @@ persona:
```yaml
menu:
- trigger: create-prd
workflow: '{project-root}/{bmad_folder}/bmm/workflows/prd/workflow.yaml'
workflow: '{project-root}/{*bmad_folder*}/bmm/workflows/prd/workflow.yaml'
description: 'Create Product Requirements Document'
```
@ -112,7 +112,7 @@ Invokes BMAD workflow engine to execute multi-step processes.
```yaml
menu:
- trigger: validate
exec: '{project-root}/{bmad_folder}/core/tasks/validate-workflow.xml'
exec: '{project-root}/{*bmad_folder*}/core/tasks/validate-workflow.xml'
description: 'Validate document structure'
```
@ -123,8 +123,8 @@ Executes single-operation tasks.
```yaml
menu:
- trigger: create-brief
exec: '{project-root}/{bmad_folder}/core/tasks/create-doc.xml'
tmpl: '{project-root}/{bmad_folder}/bmm/templates/brief.md'
exec: '{project-root}/{*bmad_folder*}/core/tasks/create-doc.xml'
tmpl: '{project-root}/{*bmad_folder*}/bmm/templates/brief.md'
description: 'Create a Product Brief from template'
```
@ -135,8 +135,8 @@ Combines task execution with template file.
```yaml
menu:
- trigger: team-standup
exec: '{project-root}/{bmad_folder}/bmm/tasks/standup.xml'
data: '{project-root}/{bmad_folder}/_cfg/agent-manifest.csv'
exec: '{project-root}/{*bmad_folder*}/bmm/tasks/standup.xml'
data: '{project-root}/{*bmad_folder*}/_cfg/agent-manifest.csv'
description: 'Run team standup with agent roster'
```
@ -160,12 +160,12 @@ Control visibility based on platform:
```yaml
menu:
- trigger: advanced-elicitation
exec: '{project-root}/{bmad_folder}/core/tasks/advanced-elicitation.xml'
exec: '{project-root}/{*bmad_folder*}/core/tasks/advanced-elicitation.xml'
description: 'Advanced elicitation techniques'
web-only: true # Only shows in web bundle
- trigger: git-operations
exec: '{project-root}/{bmad_folder}/bmm/tasks/git-flow.xml'
exec: '{project-root}/{*bmad_folder*}/bmm/tasks/git-flow.xml'
description: 'Git workflow operations'
ide-only: true # Only shows in IDE environments
```
@ -175,7 +175,7 @@ menu:
### Core Variables
- `{project-root}` - Root directory of installed project
- `{bmad_folder}` - BMAD installation folder (usually `.bmad`)
- `{*bmad_folder*}` - BMAD installation folder (usually `.bmad`)
- `{user_name}` - User's name from module config
- `{communication_language}` - Language preference
- `{output_folder}` - Document output directory
@ -186,7 +186,7 @@ menu:
```yaml
# GOOD
workflow: "{project-root}/{bmad_folder}/bmm/workflows/prd/workflow.yaml"
workflow: "{project-root}/{*bmad_folder*}/bmm/workflows/prd/workflow.yaml"
# BAD
workflow: "/Users/john/project/.bmad/bmm/workflows/prd/workflow.yaml"
@ -208,7 +208,7 @@ Module agents use the same injection process as simple agents:
**Key difference:** Module agents load **module-specific config** instead of core config:
```xml
<step n="2">Load and read {project-root}/{bmad_folder}/{module}/config.yaml...</step>
<step n="2">Load and read {project-root}/{*bmad_folder*}/{module}/config.yaml...</step>
```
## Reference Examples
@ -252,15 +252,15 @@ Agents load this at activation for consistent behavior.
```yaml
menu:
- trigger: init
workflow: '{project-root}/{bmad_folder}/bmm/workflows/workflow-init/workflow.yaml'
workflow: '{project-root}/{*bmad_folder*}/bmm/workflows/workflow-init/workflow.yaml'
description: 'Initialize workflow path (START HERE)'
- trigger: status
workflow: '{project-root}/{bmad_folder}/bmm/workflows/workflow-status/workflow.yaml'
workflow: '{project-root}/{*bmad_folder*}/bmm/workflows/workflow-status/workflow.yaml'
description: 'Check current workflow status'
- trigger: next-step
workflow: '{project-root}/{bmad_folder}/bmm/workflows/next-step/workflow.yaml'
workflow: '{project-root}/{*bmad_folder*}/bmm/workflows/next-step/workflow.yaml'
description: 'Execute next workflow in sequence'
```
@ -270,20 +270,20 @@ menu:
menu:
# Phase 1: Analysis
- trigger: brainstorm
workflow: '{project-root}/{bmad_folder}/bmm/workflows/1-analysis/brainstorm/workflow.yaml'
workflow: '{project-root}/{*bmad_folder*}/bmm/workflows/1-analysis/brainstorm/workflow.yaml'
description: 'Guided brainstorming session'
- trigger: research
workflow: '{project-root}/{bmad_folder}/bmm/workflows/1-analysis/research/workflow.yaml'
workflow: '{project-root}/{*bmad_folder*}/bmm/workflows/1-analysis/research/workflow.yaml'
description: 'Market and technical research'
# Phase 2: Planning
- trigger: prd
workflow: '{project-root}/{bmad_folder}/bmm/workflows/2-planning/prd/workflow.yaml'
workflow: '{project-root}/{*bmad_folder*}/bmm/workflows/2-planning/prd/workflow.yaml'
description: 'Create PRD'
- trigger: architecture
workflow: '{project-root}/{bmad_folder}/bmm/workflows/2-planning/architecture/workflow.yaml'
workflow: '{project-root}/{*bmad_folder*}/bmm/workflows/2-planning/architecture/workflow.yaml'
description: 'Design architecture'
```
@ -292,17 +292,17 @@ menu:
```yaml
menu:
- trigger: party-mode
workflow: '{project-root}/{bmad_folder}/core/workflows/party-mode/workflow.yaml'
workflow: '{project-root}/{*bmad_folder*}/core/workflows/party-mode/workflow.yaml'
description: 'Bring all agents together'
- trigger: brainstorm
workflow: '{project-root}/{bmad_folder}/cis/workflows/brainstorming/workflow.yaml'
workflow: '{project-root}/{*bmad_folder*}/cis/workflows/brainstorming/workflow.yaml'
description: 'Use CIS brainstorming techniques'
```
## Best Practices
1. **Use {bmad_folder} paths** - Portable across installations
1. **Use {_bmad_folder_} paths** - Portable across installations
2. **Organize workflows by phase** - Clear progression for users
3. **Include workflow-status** - Help users track progress
4. **Reference module config** - Consistent behavior
@ -318,7 +318,7 @@ menu:
```yaml
menu:
- trigger: start
workflow: '{project-root}/{bmad_folder}/{module}/workflows/init/workflow.yaml'
workflow: '{project-root}/{*bmad_folder*}/{module}/workflows/init/workflow.yaml'
description: 'Start new project (BEGIN HERE)'
```
@ -327,7 +327,7 @@ menu:
```yaml
menu:
- trigger: status
workflow: '{project-root}/{bmad_folder}/{module}/workflows/status/workflow.yaml'
workflow: '{project-root}/{*bmad_folder*}/{module}/workflows/status/workflow.yaml'
description: 'Check workflow progress'
```
@ -336,27 +336,27 @@ menu:
```yaml
menu:
- trigger: party
workflow: '{project-root}/{bmad_folder}/core/workflows/party-mode/workflow.yaml'
workflow: '{project-root}/{*bmad_folder*}/core/workflows/party-mode/workflow.yaml'
description: 'Multi-agent discussion'
```
## Module Agent vs Simple/Expert
| Aspect | Module Agent | Simple/Expert Agent |
| ------------- | -------------------------------- | ------------------------------- |
| Location | `{bmad_folder}/{module}/agents/` | `{bmad_folder}/custom/agents/` |
| Persona | Fixed, professional | Customizable via install_config |
| Handlebars | No templating | Yes, extensive |
| Menu actions | Workflows, tasks, templates | Prompts, inline actions |
| Configuration | Module config.yaml | Core config or none |
| Purpose | Professional tooling | Personal utilities |
| Aspect | Module Agent | Simple/Expert Agent |
| ------------- | ---------------------------------- | -------------------------------- |
| Location | `{*bmad_folder*}/{module}/agents/` | `{*bmad_folder*}/custom/agents/` |
| Persona | Fixed, professional | Customizable via install_config |
| Handlebars | No templating | Yes, extensive |
| Menu actions | Workflows, tasks, templates | Prompts, inline actions |
| Configuration | Module config.yaml | Core config or none |
| Purpose | Professional tooling | Personal utilities |
## Validation Checklist
- [ ] Valid YAML syntax
- [ ] Metadata includes `module: "{module-code}"`
- [ ] id uses `{bmad_folder}/{module}/agents/{name}.md`
- [ ] All workflow paths use `{project-root}/{bmad_folder}/` prefix
- [ ] id uses `{*bmad_folder*}/{module}/agents/{name}.md`
- [ ] All workflow paths use `{project-root}/{*bmad_folder*}/` prefix
- [ ] No hardcoded paths
- [ ] No duplicate triggers
- [ ] Each menu item has description

10
src/modules/bmb/docs/agents/simple-agent-architecture.md
View File

@ -217,9 +217,13 @@ Features demonstrated:
# Copy to your project
cp /path/to/commit-poet.agent.yaml .bmad/custom/agents/
# Install with personalization
bmad agent-install
# or: npx bmad-method agent-install
# Create custom.yaml and install
echo "code: my-agent
name: My Agent
default_selected: true" > custom.yaml
npx bmad-method install
# or: bmad install
```
The installer:

8
src/modules/bmb/reference/agents/expert-examples/journal-keeper/README.md
View File

@ -51,7 +51,7 @@ menu:
# Direct sidecar file action
- trigger: 'insight'
action: 'Document this breakthrough in {agent-folder}/journal-keeper-sidecar/breakthroughs.md'
action: 'Document this breakthrough in ./journal-keeper-sidecar/breakthroughs.md'
description: 'Record a meaningful insight'
```
@ -63,9 +63,9 @@ Expert Agents MUST load sidecar files explicitly:
```yaml
critical_actions:
- 'Load COMPLETE file {agent-folder}/journal-keeper-sidecar/memories.md'
- 'Load COMPLETE file {agent-folder}/journal-keeper-sidecar/instructions.md'
- 'ONLY read/write files in {agent-folder}/journal-keeper-sidecar/'
- 'Load COMPLETE file ./journal-keeper-sidecar/memories.md'
- 'Load COMPLETE file ./journal-keeper-sidecar/instructions.md'
- 'ONLY read/write files in ./journal-keeper-sidecar/'
```
**Key points:**

16
src/modules/bmb/reference/agents/expert-examples/journal-keeper/journal-keeper.agent.yaml
View File

@ -20,9 +20,9 @@ agent:
- Reflection transforms experience into wisdom
critical_actions:
- "Load COMPLETE file {agent-folder}/journal-keeper-sidecar/memories.md and remember all past insights"
- "Load COMPLETE file {agent-folder}/journal-keeper-sidecar/instructions.md and follow ALL journaling protocols"
- "ONLY read/write files in {agent-folder}/journal-keeper-sidecar/ - this is our private space"
- "Load COMPLETE file {agent_sidecar_folder}/journal-keeper-sidecar/memories.md and remember all past insights"
- "Load COMPLETE file {agent_sidecar_folder}/journal-keeper-sidecar/instructions.md and follow ALL journaling protocols"
- "ONLY read/write files in {agent_sidecar_folder}/journal-keeper-sidecar/ - this is our private space"
- "Track mood patterns, recurring themes, and breakthrough moments"
- "Reference past entries naturally to show continuity"
@ -120,7 +120,7 @@ agent:
description: "Write today's journal entry"
- trigger: quick
action: "Save a quick, unstructured entry to {agent-folder}/journal-keeper-sidecar/entries/entry-{date}.md with timestamp and any patterns noticed"
action: "Save a quick, unstructured entry to {agent_sidecar_folder}/journal-keeper-sidecar/entries/entry-{date}.md with timestamp and any patterns noticed"
description: "Quick capture without prompts"
- trigger: mood
@ -133,20 +133,20 @@ agent:
- trigger: gratitude
action: "#gratitude-moment"
description: "Capture today's gratitudes"
description: "Capture today's gratitude"
- trigger: weekly
action: "#weekly-reflection"
description: "Reflect on the past week"
- trigger: insight
action: "Document this breakthrough in {agent-folder}/journal-keeper-sidecar/breakthroughs.md with date and significance"
action: "Document this breakthrough in {agent_sidecar_folder}/journal-keeper-sidecar/breakthroughs.md with date and significance"
description: "Record a meaningful insight"
- trigger: read-back
action: "Load and share entries from {agent-folder}/journal-keeper-sidecar/entries/ for requested timeframe, highlighting themes and growth"
action: "Load and share entries from {agent_sidecar_folder}/journal-keeper-sidecar/entries/ for requested timeframe, highlighting themes and growth"
description: "Review past entries"
- trigger: save
action: "Update {agent-folder}/journal-keeper-sidecar/memories.md with today's session insights and emotional markers"
action: "Update {agent_sidecar_folder}/journal-keeper-sidecar/memories.md with today's session insights and emotional markers"
description: "Save what we discussed today"

12
src/modules/bmb/reference/agents/module-examples/security-engineer.agent.yaml
View File

@ -10,7 +10,7 @@
agent:
metadata:
id: "{bmad_folder}/bmm/agents/security-engineer.md"
id: "{*bmad_folder*}/bmm/agents/security-engineer.md"
name: "Sam"
title: "Security Engineer"
icon: "🔐"
@ -32,22 +32,22 @@ agent:
menu:
# NOTE: These workflows are hypothetical examples assuming add to a module called bmm - not implemented
- trigger: threat-model
workflow: "{project-root}/{bmad_folder}/bmm/workflows/threat-model/workflow.yaml"
exec: "{project-root}/{*bmad_folder*}/bmm/workflows/threat-model/workflow.md"
description: "Create STRIDE threat model for architecture"
- trigger: security-review
workflow: "{project-root}/{bmad_folder}/bmm/workflows/security-review/workflow.yaml"
exec: "{project-root}/{*bmad_folder*}/bmm/workflows/security-review/workflow.md"
description: "Review code/design for security issues"
- trigger: owasp-check
exec: "{project-root}/{bmad_folder}/bmm/tasks/owasp-top-10.xml"
TODO: true
description: "Check against OWASP Top 10"
- trigger: compliance
workflow: "{project-root}/{bmad_folder}/bmm/workflows/compliance-check/workflow.yaml"
exec: "{project-root}/{*bmad_folder*}/bmm/workflows/compliance-check/workflow.md"
description: "Verify compliance requirements (SOC2, GDPR, etc.)"
# Core workflow that exists
- trigger: party-mode
exec: "{project-root}/{bmad_folder}/core/workflows/party-mode/workflow.md"
exec: "{project-root}/{*bmad_folder*}/core/workflows/party-mode/workflow.md"
description: "Multi-agent security discussion"

14
src/modules/bmb/reference/agents/module-examples/trend-analyst.agent.yaml
View File

@ -10,7 +10,7 @@
agent:
metadata:
id: "{bmad_folder}/cis/agents/trend-analyst.md"
id: "{*bmad_folder*}/cis/agents/trend-analyst.md"
name: "Nova"
title: "Trend Analyst"
icon: "📈"
@ -32,26 +32,26 @@ agent:
menu:
# NOTE: These workflows are hypothetical examples - not implemented
- trigger: scan-trends
workflow: "{project-root}/{bmad_folder}/cis/workflows/trend-scan/workflow.yaml"
exec: "{project-root}/{*bmad_folder*}/cis/workflows/trend-scan/workflow.md"
description: "Scan for emerging trends in a domain"
- trigger: analyze-trend
workflow: "{project-root}/{bmad_folder}/cis/workflows/trend-analysis/workflow.yaml"
exec: "{project-root}/{*bmad_folder*}/cis/workflows/trend-analysis/workflow.md"
description: "Deep dive on a specific trend"
- trigger: opportunity-map
workflow: "{project-root}/{bmad_folder}/cis/workflows/opportunity-mapping/workflow.yaml"
exec: "{project-root}/{*bmad_folder*}/cis/workflows/opportunity-mapping/workflow.md"
description: "Map trend to strategic opportunities"
- trigger: competitor-trends
exec: "{project-root}/{bmad_folder}/cis/tasks/competitor-trend-watch.xml"
exec: "{project-root}/{*bmad_folder*}/cis/tasks/competitor-trend-watch.xml"
description: "Monitor competitor trend adoption"
# Core workflows that exist
- trigger: brainstorm
workflow: "{project-root}/{bmad_folder}/core/workflows/brainstorming/workflow.yaml"
exec: "{project-root}/{*bmad_folder*}/core/workflows/brainstorming/workflow.md"
description: "Brainstorm trend implications"
- trigger: party-mode
exec: "{project-root}/{bmad_folder}/core/workflows/party-mode/workflow.md"
exec: "{project-root}/{*bmad_folder*}/core/workflows/party-mode/workflow.md"
description: "Discuss trends with other agents"

229
src/modules/bmb/workflows-legacy/create-module/README.md
View File

@ -1,229 +0,0 @@
# Create Module Workflow
Interactive scaffolding system creating complete BMad modules with agents, workflows, tasks, and installation infrastructure.
## Table of Contents
- [Quick Start](#quick-start)
- [Workflow Phases](#workflow-phases)
- [Output Structure](#output-structure)
- [Module Components](#module-components)
- [Best Practices](#best-practices)
## Quick Start
```bash
# Basic invocation
workflow create-module
# With module brief input
workflow create-module --input module-brief-{name}-{date}.md
# Via BMad Builder
*create-module
```
## Workflow Phases
### Phase 1: Concept Definition
- Define module purpose and audience
- Establish module code (kebab-case) and name
- Choose category (Domain, Creative, Technical, Business, Personal)
- Plan component architecture
**Module Brief Integration:**
- Auto-detects existing briefs
- Uses as pre-populated blueprint
- Accelerates planning phase
### Phase 2: Architecture Planning
- Create directory hierarchy
- Setup configuration system
- Define installer structure
- Establish component folders
### Phase 3: Component Creation
- Optional first agent creation
- Optional first workflow creation
- Component placeholder generation
- Integration validation
### Phase 4: Installation Setup
- Create install-config.yaml
- Configure deployment questions
- Setup installer logic
- Post-install messaging
### Phase 5: Documentation
- Generate comprehensive README
- Create development roadmap
- Provide quick commands
- Document next steps
## Output Structure
### Generated Directory
```
{bmad_folder}/{module-code}/
├── agents/ # Agent definitions
├── workflows/ # Workflow processes
├── tasks/ # Reusable tasks
├── templates/ # Document templates
├── data/ # Module data files
├── _module-installer/ # Installation logic
│ ├── install-config.yaml
│ └── installer.js
├── README.md # Module documentation
├── TODO.md # Development roadmap
└── config.yaml # Runtime configuration
```
### Configuration Files
**install-config.yaml** - Installation questions
```yaml
questions:
- id: user_name
prompt: 'Your name?'
default: 'User'
- id: output_folder
prompt: 'Output location?'
default: './output'
```
**config.yaml** - Generated from user answers during install
```yaml
user_name: 'John Doe'
output_folder: './my-output'
```
## Module Components
### Agents
- Full module agents with workflows
- Expert agents with sidecars
- Simple utility agents
### Workflows
- Multi-step guided processes
- Configuration-driven
- Web bundle support
### Tasks
- Reusable operations
- Agent-agnostic
- Modular components
### Templates
- Document structures
- Output formats
- Report templates
## Best Practices
### Planning
1. **Use module-brief workflow first** - Creates comprehensive blueprint
2. **Define clear scope** - Avoid feature creep
3. **Plan component interactions** - Map agent/workflow relationships
### Structure
1. **Follow conventions** - Use established patterns
2. **Keep components focused** - Single responsibility
3. **Document thoroughly** - Clear README and inline docs
### Development
1. **Start with core agent** - Build primary functionality first
2. **Create key workflows** - Essential processes before edge cases
3. **Test incrementally** - Validate as you build
### Installation
1. **Minimal config questions** - Only essential settings
2. **Smart defaults** - Sensible out-of-box experience
3. **Clear post-install** - Guide users to first steps
## Integration Points
### With Other Workflows
- **module-brief** - Strategic planning input
- **create-agent** - Agent component creation
- **create-workflow** - Workflow building
- **redoc** - Documentation maintenance
### With BMad Core
- Uses core framework capabilities
- Integrates with module system
- Follows BMad conventions
## Examples
### Domain-Specific Module
```
Category: Domain-Specific
Code: legal-advisor
Components:
- Contract Review Agent
- Compliance Workflow
- Legal Templates
```
### Creative Module
```
Category: Creative
Code: story-builder
Components:
- Narrative Agent
- Plot Workflow
- Character Templates
```
### Technical Module
```
Category: Technical
Code: api-tester
Components:
- Test Runner Agent
- API Validation Workflow
- Test Report Templates
```
## Workflow Files
```
create-module/
├── workflow.yaml # Configuration
├── instructions.md # Step guide
├── checklist.md # Validation
├── module-structure.md # Architecture
├── installer-templates/ # Install files
└── README.md # This file
```
## Related Documentation
- [Module Structure](./module-structure.md)
- [Module Brief Workflow](../module-brief/README.md)
- [Create Agent](../create-agent/README.md)
- [Create Workflow](../create-workflow/README.md)
- [BMB Module](../../README.md)

137
src/modules/bmb/workflows-legacy/create-module/brainstorm-context.md
View File

@ -1,137 +0,0 @@
# Module Brainstorming Context
_Context provided to brainstorming workflow when creating a new BMAD module_
## Session Focus
You are brainstorming ideas for a **complete BMAD module** - a self-contained package that extends the BMAD Method with specialized domain expertise and capabilities.
## What is a BMAD Module?
A module is a cohesive package that provides:
- **Domain Expertise**: Specialized knowledge in a specific area (RPG, DevOps, Content Creation, etc.)
- **Agent Team**: Multiple AI personas with complementary skills
- **Workflows**: Guided processes for common tasks in the domain
- **Templates**: Document structures for consistent outputs
- **Integration**: Components that work together seamlessly
## Brainstorming Goals
Explore and define:
### 1. Domain and Purpose
- **What domain/problem space?** (e.g., game development, marketing, personal productivity)
- **Who is the target user?** (developers, writers, managers, hobbyists)
- **What pain points does it solve?** (tedious tasks, missing structure, need for expertise)
- **What makes this domain exciting?** (creativity, efficiency, empowerment)
### 2. Agent Team Composition
- **How many agents?** (typically 3-7 for a module)
- **What roles/personas?** (architect, researcher, reviewer, specialist)
- **How do they collaborate?** (handoffs, reviews, ensemble work)
- **What personality theme?** (Star Trek crew, superhero team, fantasy party, professional squad)
### 3. Core Workflows
- **What documents need creating?** (plans, specs, reports, creative outputs)
- **What processes need automation?** (analysis, generation, review, deployment)
- **What workflows enable the vision?** (3-10 key workflows that define the module)
### 4. Value Proposition
- **What becomes easier?** (specific tasks that get 10x faster)
- **What becomes possible?** (new capabilities previously unavailable)
- **What becomes better?** (quality improvements, consistency gains)
## Creative Constraints
A good BMAD module should be:
- **Focused**: Serves a specific domain well (not generic)
- **Complete**: Provides end-to-end capabilities for that domain
- **Cohesive**: Agents and workflows complement each other
- **Fun**: Personality and creativity make it enjoyable to use
- **Practical**: Solves real problems, delivers real value
## Module Architecture Questions
1. **Module Identity**
- Module code (kebab-case, e.g., "rpg-toolkit")
- Module name (friendly, e.g., "RPG Toolkit")
- Module purpose (one sentence)
- Target audience
2. **Agent Lineup**
- Agent names and roles
- Communication styles and personalities
- Expertise areas
- Command sets (what each agent can do)
3. **Workflow Portfolio**
- Document generation workflows
- Action/automation workflows
- Analysis/research workflows
- Creative/ideation workflows
4. **Integration Points**
- How agents invoke workflows
- How workflows use templates
- How components pass data
- Dependencies on other modules
## Example Module Patterns
### Professional Domains
- **DevOps Suite**: Deploy, Monitor, Troubleshoot agents + deployment workflows
- **Marketing Engine**: Content, SEO, Analytics agents + campaign workflows
- **Legal Assistant**: Contract, Research, Review agents + document workflows
### Creative Domains
- **RPG Toolkit**: DM, NPC, Quest agents + adventure creation workflows
- **Story Crafter**: Plot, Character, World agents + writing workflows
- **Music Producer**: Composer, Arranger, Mixer agents + production workflows
### Personal Domains
- **Life Coach**: Planner, Tracker, Mentor agents + productivity workflows
- **Learning Companion**: Tutor, Quiz, Reviewer agents + study workflows
- **Health Guide**: Nutrition, Fitness, Wellness agents + tracking workflows
## Suggested Brainstorming Techniques
Particularly effective for module ideation:
1. **Domain Immersion**: Deep dive into target domain's problems
2. **Persona Mapping**: Who needs this and what do they struggle with?
3. **Workflow Mapping**: What processes exist today? How could they improve?
4. **Team Building**: What personalities would make a great team?
5. **Integration Thinking**: How do pieces connect and amplify each other?
## Key Questions to Answer
1. What domain expertise should this module embody?
2. What would users be able to do that they can't do now?
3. Who are the 3-7 agents and what are their personalities?
4. What are the 5-10 core workflows?
5. What makes this module delightful to use?
6. How is this different from existing tools?
7. What's the "killer feature" that makes this essential?
## Output Goals
Generate:
- **Module concept**: Clear vision and purpose
- **Agent roster**: Names, roles, personalities for each agent
- **Workflow list**: Core workflows with brief descriptions
- **Unique angle**: What makes this module special
- **Use cases**: 3-5 concrete scenarios where this module shines
---
_This focused context helps create cohesive, valuable BMAD modules_

235
src/modules/bmb/workflows-legacy/create-module/checklist.md
View File

@ -1,235 +0,0 @@
# Build Module Validation Checklist
## Module Identity and Metadata
### Basic Information
- [ ] Module code follows kebab-case convention (e.g., "rpg-toolkit")
- [ ] Module name is descriptive and title-cased
- [ ] Module purpose is clearly defined (1-2 sentences)
- [ ] Target audience is identified
- [ ] Version number follows semantic versioning (e.g., "1.0.0")
- [ ] Author information is present
### Naming Consistency
- [ ] Module code used consistently throughout all files
- [ ] No naming conflicts with existing modules
- [ ] All paths use consistent module code references
## Directory Structure
### Source Directories ({bmad_folder}/{module-code}/)
- [ ] `/agents` directory created (even if empty)
- [ ] `/workflows` directory created (even if empty)
- [ ] `/tasks` directory exists (if tasks planned)
- [ ] `/templates` directory exists (if templates used)
- [ ] `/data` directory exists (if data files needed)
- [ ] `/_module-installer/install-config.yaml` present (defines configuration questions)
- [ ] `README.md` present with documentation
### Installed Module Structure (generated in target after installation)
- [ ] `/agents` directory for compiled agents
- [ ] `/workflows` directory for workflow instances
- [ ] `/data` directory for user data
- [ ] `config.yaml` generated from install-config.yaml during installation
## Component Planning
### Agents
- [ ] At least one agent defined or planned
- [ ] Agent purposes are distinct and clear
- [ ] Agent types (Simple/Expert/Module) identified
- [ ] No significant overlap between agents
- [ ] Primary agent is identified
### Workflows
- [ ] At least one workflow defined or planned
- [ ] Workflow purposes are clear
- [ ] Workflow types identified (Document/Action/Interactive)
- [ ] Primary workflow is identified
- [ ] Workflow complexity is appropriate
### Tasks (if applicable)
- [ ] Tasks have single, clear purposes
- [ ] Tasks don't duplicate workflow functionality
- [ ] Task files follow naming conventions
## Configuration Files
### Installation Configuration (install-config.yaml)
- [ ] `install-config.yaml` exists in `_module-installer`
- [ ] Module metadata present (code, name, version)
- [ ] Configuration questions defined for user input
- [ ] Default values provided for all questions
- [ ] Prompt text is clear and helpful
- [ ] Result templates use proper variable substitution
- [ ] Paths use proper variables ({project-root}, {value}, etc.)
### Generated Config (config.yaml in target)
- [ ] Generated during installation from install-config.yaml
- [ ] Contains all user-provided configuration values
- [ ] Module metadata included
- [ ] No config.yaml should exist in source module
## Installation Infrastructure
### Installer Files
- [ ] Install configuration validates against schema
- [ ] All source paths exist or are marked as templates
- [ ] Destination paths use correct variables
- [ ] Optional vs required steps clearly marked
### installer.js (if present)
- [ ] Main `installModule` function exists
- [ ] Error handling implemented
- [ ] Console logging for user feedback
- [ ] Exports correct function names
- [ ] Placeholder code replaced with actual logic (or logged as TODO)
### External Assets (if any)
- [ ] Asset files exist in assets directory
- [ ] Copy destinations are valid
- [ ] Permissions requirements documented
## Documentation
### README.md
- [ ] Module overview section present
- [ ] Installation instructions included
- [ ] Component listing with descriptions
- [ ] Quick start guide provided
- [ ] Configuration options documented
- [ ] At least one usage example
- [ ] Directory structure shown
- [ ] Author and date information
### Component Documentation
- [ ] Each agent has purpose documentation
- [ ] Each workflow has description
- [ ] Tasks are documented (if present)
- [ ] Examples demonstrate typical usage
### Development Roadmap
- [ ] TODO.md or roadmap section exists
- [ ] Planned components listed
- [ ] Development phases identified
- [ ] Quick commands for adding components
## Integration
### Cross-component References
- [ ] Agents reference correct workflow paths
- [ ] Workflows reference correct task paths
- [ ] All internal paths use module variables
- [ ] External dependencies declared
### Module Boundaries
- [ ] Module scope is well-defined
- [ ] No feature creep into other domains
- [ ] Clear separation from other modules
## Quality Checks
### Completeness
- [ ] At least one functional component (not all placeholders)
- [ ] Core functionality is implementable
- [ ] Module provides clear value
### Consistency
- [ ] Formatting consistent across files
- [ ] Variable naming follows conventions
- [ ] Communication style appropriate for domain
### Scalability
- [ ] Structure supports future growth
- [ ] Component organization is logical
- [ ] No hard-coded limits
## Testing and Validation
### Structural Validation
- [ ] YAML files parse without errors
- [ ] JSON files (if any) are valid
- [ ] XML files (if any) are well-formed
- [ ] No syntax errors in JavaScript files
### Path Validation
- [ ] All referenced paths exist or are clearly marked as TODO
- [ ] Variable substitutions are correct
- [ ] No absolute paths (unless intentional)
### Installation Testing
- [ ] Installation steps can be simulated
- [ ] No circular dependencies
- [ ] Uninstall process defined (if complex)
## Final Checks
### Ready for Use
- [ ] Module can be installed without errors
- [ ] At least one component is functional
- [ ] User can understand how to get started
- [ ] Next steps are clear
### Professional Quality
- [ ] No placeholder text remains (unless marked TODO)
- [ ] No obvious typos or grammar issues
- [ ] Professional tone throughout
- [ ] Contact/support information provided
## Issues Found
### Critical Issues
<!-- List any issues that MUST be fixed before module can be used -->
### Warnings
<!-- List any issues that should be addressed but won't prevent basic usage -->
### Improvements
<!-- List any optional enhancements that would improve the module -->
### Missing Components
<!-- List any planned components not yet implemented -->
## Module Complexity Assessment
### Complexity Rating
- [ ] Simple (1-2 agents, 2-3 workflows)
- [ ] Standard (3-5 agents, 5-10 workflows)
- [ ] Complex (5+ agents, 10+ workflows)
### Readiness Level
- [ ] Prototype (Basic structure, mostly placeholders)
- [ ] Alpha (Core functionality works)
- [ ] Beta (Most features complete, needs testing)
- [ ] Release (Full functionality, documented)

92
src/modules/bmb/workflows-legacy/create-module/installer-templates/install-config.yaml
View File

@ -1,92 +0,0 @@
# {{MODULE_NAME}} Module Configuration
# This file defines installation questions and module configuration values
code: "{{MODULE_CODE}}"
name: "{{MODULE_NAME}}"
default_selected: "{{DEFAULT_SELECTED}}" # true if this should be selected by default
# Welcome message shown during installation
prompt:
- "{{WELCOME_MESSAGE_LINE_1}}"
- "{{WELCOME_MESSAGE_LINE_2}}"
# Core config values are automatically inherited:
## user_name
## communication_language
## document_output_language
## output_folder
# ============================================================================
# CONFIGURATION FIELDS
# ============================================================================
#
# Each field can be:
# 1. INTERACTIVE (has 'prompt' - asks user during installation)
# 2. STATIC (no 'prompt' - just uses 'result' value)
#
# Field structure:
# field_name:
# prompt: "Question to ask user" (optional - omit for static values)
# default: "default_value" (optional)
# result: "{value}" or "static-value"
# single-select: [...] (optional - for dropdown)
# multi-select: [...] (optional - for checkboxes)
#
# Special placeholders in result:
# {value} - replaced with user's answer
# {project-root} - replaced with project root path
# {directory_name} - replaced with project directory name
# {module_code} - replaced with this module's code
# ============================================================================
# EXAMPLE: Interactive text input
# example_project_name:
# prompt: "What is your project name?"
# default: "{directory_name}"
# result: "{value}"
# EXAMPLE: Interactive single-select dropdown
# example_skill_level:
# prompt: "What is your experience level?"
# default: "intermediate"
# result: "{value}"
# single-select:
# - value: "beginner"
# label: "Beginner - New to this domain"
# - value: "intermediate"
# label: "Intermediate - Familiar with basics"
# - value: "expert"
# label: "Expert - Deep knowledge"
# EXAMPLE: Interactive multi-select checkboxes
# example_features:
# prompt:
# - "Which features do you want to enable?"
# - "(Select all that apply)"
# result: "{value}"
# multi-select:
# - "Feature A"
# - "Feature B"
# - "Feature C"
# EXAMPLE: Interactive path input
# example_output_path:
# prompt: "Where should outputs be saved?"
# default: "output/{{MODULE_CODE}}"
# result: "{project-root}/{value}"
# EXAMPLE: Static value (no user prompt)
# example_static_setting:
# result: "hardcoded-value"
# EXAMPLE: Static path
# module_data_path:
# result: "{project-root}/{bmad_folder}/{{MODULE_CODE}}/data"
# ============================================================================
# YOUR MODULE CONFIGURATION FIELDS
# ============================================================================
# Replace examples above with your module's actual configuration needs.
# Delete this comment block and the examples when implementing.
# ============================================================================
# TODO: INSERT {MODULE_CONFIG_FIELDS} HERE

231
src/modules/bmb/workflows-legacy/create-module/installer-templates/installer.js
View File

@ -1,231 +0,0 @@
/* eslint-disable unicorn/prefer-module, unicorn/prefer-node-protocol */
/**
* {{MODULE_NAME}} Module Installer
* Custom installation logic for complex module setup
*
* This is a template - replace {{VARIABLES}} with actual values
*/
// const fs = require('fs'); // Uncomment when implementing file operations
const path = require('path');
/**
* Main installation function
* Called by BMAD installer when processing the module
*/
async function installModule(config) {
console.log('🚀 Installing {{MODULE_NAME}} module...');
console.log(` Version: ${config.version}`);
console.log(` Module Code: ${config.module_code}`);
try {
// Step 1: Validate environment
await validateEnvironment(config);
// Step 2: Setup custom configurations
await setupConfigurations(config);
// Step 3: Initialize module-specific features
await initializeFeatures(config);
// Step 4: Run post-install tasks
await runPostInstallTasks(config);
console.log('✅ {{MODULE_NAME}} module installed successfully!');
return {
success: true,
message: 'Module installed and configured',
};
} catch (error) {
console.error('❌ Installation failed:', error.message);
return {
success: false,
error: error.message,
};
}
}
/**
* Validate that the environment meets module requirements
*/
async function validateEnvironment(config) {
console.log(' Validating environment...');
// TODO: Add environment checks
// Examples:
// - Check for required tools/binaries
// - Verify permissions
// - Check network connectivity
// - Validate API keys
// Placeholder validation
if (!config.project_root) {
throw new Error('Project root not defined');
}
console.log(' ✓ Environment validated');
}
/**
* Setup module-specific configurations
*/
async function setupConfigurations(config) {
console.log(' Setting up configurations...');
// TODO: Add configuration setup
// Examples:
// - Create config files
// - Setup environment variables
// - Configure external services
// - Initialize settings
// Placeholder configuration
const configPath = path.join(config.project_root, 'bmad', config.module_code, 'config.json');
// Example of module config that would be created
// const moduleConfig = {
// installed: new Date().toISOString(),
// settings: {
// // Add default settings
// }
// };
// Note: This is a placeholder - actual implementation would write the file
console.log(` ✓ Would create config at: ${configPath}`);
console.log(' ✓ Configurations complete');
}
/**
* Initialize module-specific features
*/
async function initializeFeatures(config) {
console.log(' Initializing features...');
// TODO: Add feature initialization
// Examples:
// - Create database schemas
// - Setup cron jobs
// - Initialize caches
// - Register webhooks
// - Setup file watchers
// Module-specific initialization based on type
switch (config.module_category) {
case 'data': {
await initializeDataFeatures(config);
break;
}
case 'automation': {
await initializeAutomationFeatures(config);
break;
}
case 'integration': {
await initializeIntegrationFeatures(config);
break;
}
default: {
console.log(' - Using standard initialization');
}
}
console.log(' ✓ Features initialized');
}
/**
* Initialize data-related features
*/
async function initializeDataFeatures(/* config */) {
console.log(' - Setting up data storage...');
// TODO: Setup databases, data folders, etc.
}
/**
* Initialize automation features
*/
async function initializeAutomationFeatures(/* config */) {
console.log(' - Setting up automation hooks...');
// TODO: Setup triggers, watchers, schedulers
}
/**
* Initialize integration features
*/
async function initializeIntegrationFeatures(/* config */) {
console.log(' - Setting up integrations...');
// TODO: Configure APIs, webhooks, external services
}
/**
* Run post-installation tasks
*/
async function runPostInstallTasks(/* config */) {
console.log(' Running post-install tasks...');
// TODO: Add post-install tasks
// Examples:
// - Generate sample data
// - Run initial workflows
// - Send notifications
// - Update registries
console.log(' ✓ Post-install tasks complete');
}
/**
* Initialize database for the module (optional)
*/
async function initDatabase(/* config */) {
console.log(' Initializing database...');
// TODO: Add database initialization
// This function can be called from install-config.yaml
console.log(' ✓ Database initialized');
}
/**
* Generate sample data for the module (optional)
*/
async function generateSamples(config) {
console.log(' Generating sample data...');
// TODO: Create sample files, data, configurations
// This helps users understand how to use the module
const samplesPath = path.join(config.project_root, 'examples', config.module_code);
console.log(` - Would create samples at: ${samplesPath}`);
console.log(' ✓ Samples generated');
}
/**
* Uninstall the module (cleanup)
*/
async function uninstallModule(/* config */) {
console.log('🗑️ Uninstalling {{MODULE_NAME}} module...');
try {
// TODO: Add cleanup logic
// - Remove configurations
// - Clean up databases
// - Unregister services
// - Backup user data
console.log('✅ Module uninstalled successfully');
return { success: true };
} catch (error) {
console.error('❌ Uninstall failed:', error.message);
return {
success: false,
error: error.message,
};
}
}
// Export functions for BMAD installer
module.exports = {
installModule,
initDatabase,
generateSamples,
uninstallModule,
};

577
src/modules/bmb/workflows-legacy/create-module/instructions.md
View File

@ -1,577 +0,0 @@
# Build Module - Interactive Module Builder Instructions
<critical>The workflow execution engine is governed by: {project-root}/{bmad_folder}/core/tasks/workflow.xml</critical>
<critical>You MUST have already loaded and processed: {project-root}/{bmad_folder}/bmb/workflows/create-module/workflow.yaml</critical>
<critical>Study existing modules in: {project-root}/{bmad_folder}/ for patterns</critical>
<critical>Communicate in {communication_language} throughout the module creation process</critical>
<critical>⚠️ ABSOLUTELY NO TIME ESTIMATES - NEVER mention hours, days, weeks, months, or ANY time-based predictions. AI has fundamentally changed development speed - what once took teams weeks/months can now be done by one person in hours. DO NOT give ANY time estimates whatsoever.</critical>
<workflow>
<step n="-1" goal="Optional brainstorming for module ideas" optional="true">
<ask>Do you want to brainstorm module ideas first? [y/n]</ask>
<check if="yes">
<action>Invoke brainstorming workflow: {brainstorming_workflow}</action>
<action>Pass context data: {brainstorming_context}</action>
<action>Wait for brainstorming session completion</action>
<action>Use brainstorming output to inform module concept, agent lineup, and workflow portfolio in following steps</action>
</check>
<check if="no">
<action>Proceed directly to Step 0</action>
</check>
<template-output>brainstorming_results</template-output>
</step>
<step n="0" goal="Check for module brief" optional="true">
<ask>Do you have a module brief or should we create one? [have/create/skip]</ask>
<check if="create">
<action>Invoke module-brief workflow: {project-root}/{bmad_folder}/bmb/workflows/module-brief/workflow.yaml</action>
<action>Wait for module brief completion</action>
<action>Load the module brief to use as blueprint</action>
</check>
<check if="have">
<ask>Provide path to module brief document</ask>
<action>Load the module brief and use it to pre-populate all planning sections</action>
</check>
<check if="skip">
<action>Proceed directly to Step 1</action>
</check>
<template-output>module_brief</template-output>
</step>
<step n="1" goal="Define module concept and scope">
<critical>Load and study the complete module structure guide</critical>
<action>Load module structure guide: {module_structure_guide}</action>
<action>Understand module types (Simple/Standard/Complex)</action>
<action>Review directory structures and component guidelines</action>
<action>Study the installation infrastructure patterns</action>
<action>If brainstorming or module brief was completed, reference those results to guide the conversation</action>
<action>Guide user to articulate their module's vision, exploring its purpose, what it will help with, and who will use it</action>
<action>Based on their description, intelligently propose module details:</action>
**Module Identity Development:**
1. **Module name** - Extract from their description with proper title case
2. **Module code** - Generate kebab-case from name following patterns:
- Multi-word descriptive names → shortened kebab-case
- Domain-specific terms → recognizable abbreviations
- Present suggested code and confirm it works for paths like {bmad_folder}/{{code}}/agents/
3. **Module purpose** - Refine their description into 1-2 clear sentences
4. **Target audience** - Infer from context or ask if unclear
**Module Theme Reference Categories:**
- Domain-Specific (Legal, Medical, Finance, Education)
- Creative (RPG/Gaming, Story Writing, Music Production)
- Technical (DevOps, Testing, Architecture, Security)
- Business (Project Management, Marketing, Sales)
- Personal (Journaling, Learning, Productivity)
<critical>Determine output location:</critical>
- Module will be created at {installer_output_folder}
<action>Store module identity for scaffolding</action>
<template-output>module_identity</template-output>
</step>
<step n="2" goal="Plan module components">
<action>Based on the module purpose, intelligently propose an initial component architecture</action>
**Agents Planning:**
<action>Suggest agents based on module purpose, considering agent types (Simple/Expert/Module) appropriate to each role</action>
**Example Agent Patterns by Domain:**
- Data/Analytics: Analyst, Designer, Builder roles
- Gaming/Creative: Game Master, Generator, Storytelling roles
- Team/Business: Manager, Facilitator, Documentation roles
<action>Present suggested agent list with types, explaining we can start with core ones and add others later</action>
<action>Confirm which agents resonate with their vision</action>
**Workflows Planning:**
<action>Intelligently suggest workflows that complement the proposed agents</action>
**Example Workflow Patterns by Domain:**
- Data/Analytics: analyze-dataset, create-dashboard, generate-report
- Gaming/Creative: session-prep, generate-encounter, world-building
- Team/Business: planning, facilitation, documentation workflows
<action>For each workflow, note whether it should be Document, Action, or Interactive type</action>
<action>Confirm which workflows are most important to start with</action>
<action>Determine which to create now vs placeholder</action>
**Tasks Planning (optional):**
<ask>Any special tasks that don't warrant full workflows?</ask>
<action if="tasks needed">For each task, capture name, purpose, and whether standalone or supporting</action>
<template-output>module_components</template-output>
</step>
<step n="2b" goal="Determine module complexity">
<action>Based on components, intelligently determine module type using criteria:</action>
**Simple Module Criteria:**
- 1-2 agents, all Simple type
- 1-3 workflows
- No complex integrations
**Standard Module Criteria:**
- 2-4 agents with mixed types
- 3-8 workflows
- Some shared resources
**Complex Module Criteria:**
- 4+ agents or multiple Module-type agents
- 8+ workflows
- Complex interdependencies
- External integrations
<action>Present determined module type with explanation of what structure will be set up</action>
<template-output>module_type</template-output>
</step>
<step n="3" goal="Create module directory structure">
<critical>Use module path determined in Step 1:</critical>
- The module base path is {{module_path}}
<action>Create base module directories at the determined path:</action>
```
{{module_code}}/
├── agents/ # Agent definitions
├── workflows/ # Workflow folders
├── tasks/ # Task files (if any)
├── templates/ # Shared templates
├── data/ # Module data files
├── _module-installer/ # Installation configuration
│ └── install-config.yaml # Configuration questions (config.yaml generated at install time)
└── README.md # Module documentation
```
<action>Create installer directory:</action>
**INSTALLED MODULE STRUCTURE** (generated in target project after installation):
```
{{module_code}}/
├── agents/ # Compiled agents
├── workflows/ # Workflow instances
├── config.yaml # Generated from install-config.yaml during installation
└── data/ # User data directory
```
**SOURCE MODULE** (module-installer is for installation only, not copied to target):
```
{{module_code}}/
├── _module-installer/
│ ├── install-config.yaml # Configuration questions
│ ├── installer.js # Optional custom installation logic
│ └── assets/ # Files to copy during install
```
<template-output>directory_structure</template-output>
</step>
<step n="4" goal="Plan module configuration fields">
<action>Based on the module purpose and components, determine what configuration settings the module needs</action>
**Configuration Field Planning:**
<ask>Does your module need any user-configurable settings during installation?</ask>
**Common configuration patterns:**
- Output/data paths (where module saves files)
- Feature toggles (enable/disable functionality)
- Integration settings (API keys, external services)
- Behavior preferences (automation level, detail level)
- User skill level or experience settings
<action>For each configuration field needed, determine:</action>
1. Field name (snake_case)
2. Whether it's INTERACTIVE (asks user) or STATIC (hardcoded)
3. Prompt text (if interactive)
4. Default value
5. Type: text input, single-select, or multi-select
6. Result template (how the value gets stored)
<action>Store planned configuration fields for installer generation in step 7</action>
<template-output>module_config_fields</template-output>
</step>
<step n="5" goal="Create first agent" optional="true">
<ask>Create your first agent now? [yes/no]</ask>
<check if="yes">
<action>Invoke agent builder workflow: {agent_builder}</action>
<action>Pass module_components as context input</action>
<action>Guide them to create the primary agent for the module</action>
<critical>Save to module's agents folder:</critical>
- Save to {{module_path}}/agents/
</check>
<check if="no">
<action>Create placeholder file in agents folder with TODO notes including agent name, purpose, and type</action>
</check>
<template-output>first_agent</template-output>
</step>
<step n="6" goal="Create first workflow" optional="true">
<ask>Create your first workflow now? [yes/no]</ask>
<check if="yes">
<action>Invoke workflow builder: {workflow_builder}</action>
<action>Pass module_components as context input</action>
<action>Guide them to create the primary workflow</action>
<critical>Save to module's workflows folder:</critical>
- Save to {{module_path}}/workflows/
</check>
<check if="no">
<action>Create placeholder workflow folder structure with TODO notes for workflow.yaml, instructions.md, and template.md if document workflow</action>
</check>
<template-output>first_workflow</template-output>
</step>
<step n="7" goal="Setup module installer">
<action>Load installer template from: {installer_templates}/install-config.yaml</action>
<critical>IMPORTANT: Create install-config.yaml NOT install-config.yaml</critical>
<critical>This is the STANDARD format that BMAD installer uses</critical>
Create module-installer/install-config.yaml:
```yaml
# {{module_name}} Module Configuration
# This file defines installation questions and module configuration values
code: {{module_code}}
name: "{{module_name}}"
default_selected: false # Set to true if this should be selected by default
# Welcome message shown during installation
prompt:
- "Thank you for choosing {{module_name}}!"
- "{{brief_module_description}}"
# Core config values are automatically inherited:
## user_name
## communication_language
## document_output_language
## output_folder
# ============================================================================
# CONFIGURATION FIELDS (from step 4 planning)
# ============================================================================
# Each field can be:
# 1. INTERACTIVE (has 'prompt' - asks user during installation)
# 2. STATIC (no 'prompt' - just uses 'result' value)
# ============================================================================
# EXAMPLE Interactive text input:
# output_path:
# prompt: "Where should {{module_code}} save outputs?"
# default: "output/{{module_code}}"
# result: "{project-root}/{value}"
# EXAMPLE Interactive single-select:
# 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"
# EXAMPLE Static value:
# module_version:
# result: "1.0.0"
# EXAMPLE Static path:
# data_path:
# result: "{project-root}/{bmad_folder}/{{module_code}}/data"
{{generated_config_fields_from_step_4}}
```
<critical>Save location:</critical>
- Save to {{module_path}}/module-installer/install-config.yaml
<ask>Does your module need custom installation logic (database setup, API registration, etc.)?</ask>
<check if="yes, create installer.js">
```javascript
// {{module_name}} Module Installer
// Custom installation logic
- @param {Object} options - Installation options
- @param {string} options.projectRoot - Project root directory
- @param {Object} options.config - Module configuration from install-config.yaml
- @param {Array} options.installedIDEs - List of IDE codes being configured
- @param {Object} options.logger - Logger instance (log, warn, error methods)
- @returns {boolean} - true if successful, false to abort installation
async function install(options) {
const { projectRoot, config, installedIDEs, logger } = options;
logger.log('Running {{module_name}} custom installer...');
// TODO: Add custom installation logic here
// Examples:
// - Create database tables
// - Download external assets
// - Configure API connections
// - Initialize data files
// - Set up webhooks or integrations
logger.log('{{module_name}} custom installation complete!');
return true;
}
module.exports = { install };
`````
<critical>Save location:</critical>
- Save to {{module_path}}/module-installer/installer.js
</check>
<check if="no">
<action>Skip installer.js creation - the standard installer will handle everything</action>
</check>
<template-output>installer_config</template-output>
</step>
<step n="8" goal="Create module documentation">
Generate comprehensive README.md:
````markdown
# {{module_name}}
{{module_purpose}}
## Overview
This module provides:
{{component_summary}}
## Installation
```bash
bmad install {{module_code}}
`````
````
## Components
### Agents ({{agent_count}})
{{agent_documentation}}
### Workflows ({{workflow_count}})
{{workflow_documentation}}
### Tasks ({{task_count}})
{{task_documentation}}
## Quick Start
1. **Load the main agent:**
```
agent {{primary_agent}}
```
2. **View available commands:**
```
*help
```
3. **Run the main workflow:**
```
workflow {{primary_workflow}}
```
## Module Structure
```
{{directory_tree}}
```
## Configuration
The module can be configured in `{bmad_folder}/{{module_code}}/config.yaml`
Key settings:
{{configuration_options}}
## Examples
### Example 1: {{example_use_case}}
{{example_walkthrough}}
## Development Roadmap
- [ ] {{roadmap_item_1}}
- [ ] {{roadmap_item_2}}
- [ ] {{roadmap_item_3}}
## Contributing
To extend this module:
1. Add new agents using `create-agent` workflow
2. Add new workflows using `create-workflow` workflow
3. Submit improvements via pull request
## Author
Created by {{user_name}} on {{date}}
````
<template-output>module_readme</template-output>
</step>
<step n="9" goal="Generate component roadmap">
Create a development roadmap for remaining components:
**TODO.md file:**
```markdown
# {{module_name}} Development Roadmap
## Phase 1: Core Components
{{phase1_tasks}}
## Phase 2: Enhanced Features
{{phase2_tasks}}
## Phase 3: Polish and Integration
{{phase3_tasks}}
## Quick Commands
Create new agent:
```
workflow create-agent
```
Create new workflow:
```
workflow create-workflow
```
## Notes
{{development_notes}}
```
Ask if user wants to:
1. Continue building more components now
2. Save roadmap for later development
3. Test what's been built so far
<template-output>development_roadmap</template-output>
</step>
<step n="10" goal="Validate and finalize module">
<action>Run validation checks:</action>
**Structure validation:**
- All required directories created
- Config files properly formatted
- Installer configuration valid
**Component validation:**
- At least one agent or workflow exists (or planned)
- All references use correct paths
- Module code consistent throughout
**Documentation validation:**
- README.md complete
- Installation instructions clear
- Examples provided
<action>Present summary to {user_name}:</action>
- Module name and code
- Location path
- Agent count (created vs planned)
- Workflow count (created vs planned)
- Task count
- Installer status
<action>Provide next steps guidance:</action>
1. Complete remaining components using roadmap
2. Run the BMAD Method installer to this project location
3. Select 'Compile Agents' option after confirming folder
4. Module will be compiled and available for use
5. Test with bmad install command
6. Share or integrate with existing system
<ask>Would you like to:
- Create another component now?
- Test the module installation?
- Exit and continue later?
</ask>
<template-output>module_summary</template-output>
</step>
</workflow>

400
src/modules/bmb/workflows-legacy/create-module/module-structure.md
View File

@ -1,400 +0,0 @@
# BMAD Module Structure Guide
## What is a Module?
A BMAD module is a self-contained package of agents, workflows, tasks, and resources that work together to provide specialized functionality. Think of it as an expansion pack for the BMAD Method.
## Module Architecture
### Core Structure
```
# SOURCE MODULE (in BMAD-METHOD project)
src/modules/{module-code}/
├── agents/ # Agent definitions (.agent.yaml)
├── workflows/ # Workflow folders
├── tasks/ # Task files
├── tools/ # Tool files
├── templates/ # Shared templates
├── data/ # Static data
├── _module-installer/ # Installation configuration
│ ├── install-config.yaml # Installation questions & config
│ ├── installer.js # Optional custom install logic
│ └── assets/ # Files to copy during install
└── README.md # Module documentation
# INSTALLED MODULE (in target project)
{project-root}/{bmad_folder}/{module-code}/
├── agents/ # Compiled agent files (.md)
├── workflows/ # Workflow instances
├── tasks/ # Task files
├── tools/ # Tool files
├── templates/ # Templates
├── data/ # Module data
├── config.yaml # Generated from install-config.yaml
└── README.md # Module documentation
```
## Module Types by Complexity
### Simple Module (1-2 agents, 2-3 workflows)
Perfect for focused, single-purpose tools.
**Example: Code Review Module**
- 1 Reviewer Agent
- 2 Workflows: quick-review, deep-review
- Clear, narrow scope
### Standard Module (3-5 agents, 5-10 workflows)
Comprehensive solution for a domain.
**Example: Project Management Module**
- PM Agent, Scrum Master Agent, Analyst Agent
- Workflows: sprint-planning, retrospective, roadmap, user-stories
- Integrated component ecosystem
### Complex Module (5+ agents, 10+ workflows)
Full platform or framework.
**Example: RPG Toolkit Module**
- DM Agent, NPC Agent, Monster Agent, Loot Agent, Map Agent
- 15+ workflows for every aspect of game management
- Multiple interconnected systems
## Module Naming Conventions
### Module Code (kebab-case)
- `data-viz` - Data Visualization
- `team-collab` - Team Collaboration
- `rpg-toolkit` - RPG Toolkit
- `legal-assist` - Legal Assistant
### Module Name (Title Case)
- "Data Visualization Suite"
- "Team Collaboration Platform"
- "RPG Game Master Toolkit"
- "Legal Document Assistant"
## Component Guidelines
### Agents per Module
**Recommended Distribution:**
- **Primary Agent (1)**: The main interface/orchestrator
- **Specialist Agents (2-4)**: Domain-specific experts
- **Utility Agents (0-2)**: Helper/support functions
**Anti-patterns to Avoid:**
- Too many overlapping agents
- Agents that could be combined
- Agents without clear purpose
### Workflows per Module
**Categories:**
- **Core Workflows (2-3)**: Essential functionality
- **Feature Workflows (3-5)**: Specific capabilities
- **Utility Workflows (2-3)**: Supporting operations
- **Admin Workflows (0-2)**: Maintenance/config
**Workflow Complexity Guide:**
- Simple: 3-5 steps, single output
- Standard: 5-10 steps, multiple outputs
- Complex: 10+ steps, conditional logic, sub-workflows
### Tasks per Module
Tasks should be used for:
- Single-operation utilities
- Shared subroutines
- Quick actions that don't warrant workflows
## Module Dependencies
### Internal Dependencies
- Agents can reference module workflows
- Workflows can invoke module tasks
- Tasks can use module templates
### External Dependencies
- Reference other modules via full paths
- Declare dependencies in config.yaml
- Version compatibility notes
### Workflow Vendoring (Advanced)
For modules that need workflows from other modules but want to remain standalone, use **workflow vendoring**:
**In Agent YAML:**
```yaml
menu:
- trigger: command-name
workflow: '{project-root}/{bmad_folder}/SOURCE_MODULE/workflows/path/workflow.yaml'
workflow-install: '{project-root}/{bmad_folder}/THIS_MODULE/workflows/vendored/workflow.yaml'
description: 'Command description'
```
**What Happens:**
- During installation, workflows are copied from `workflow` to `workflow-install` location
- Vendored workflows get `config_source` updated to reference this module's config
- Compiled agent only references the `workflow-install` path
- Module becomes fully standalone - no source module dependency required
**Use Cases:**
- Specialized modules that reuse common workflows with different configs
- Domain-specific adaptations (e.g., game dev using standard dev workflows)
- Testing workflows in isolation
**Benefits:**
- Module independence (no forced dependencies)
- Clean namespace (workflows in your module)
- Config isolation (use your module's settings)
- Customization ready (modify vendored workflows freely)
## Installation Infrastructure
### Required: module-installer/install-config.yaml
This file defines both installation questions AND static configuration values:
```yaml
# Module metadata
code: module-code
name: 'Module Name'
default_selected: false
# Welcome message during installation
prompt:
- 'Welcome to Module Name!'
- 'Brief description here'
# Core values automatically inherited from installer:
## user_name
## communication_language
## document_output_language
## output_folder
# INTERACTIVE fields (ask user during install)
output_location:
prompt: 'Where should module outputs be saved?'
default: 'output/module-code'
result: '{project-root}/{value}'
feature_level:
prompt: 'Which feature set?'
default: 'standard'
result: '{value}'
single-select:
- value: 'basic'
label: 'Basic - Core features only'
- value: 'standard'
label: 'Standard - Recommended features'
- value: 'advanced'
label: 'Advanced - All features'
# STATIC fields (no prompt, just hardcoded values)
module_version:
result: '1.0.0'
data_path:
result: '{project-root}/{bmad_folder}/module-code/data'
```
**Key Points:**
- File is named `install-config.yaml` (NOT install-config.yaml)
- Supports both interactive prompts and static values
- `result` field uses placeholders: `{value}`, `{project-root}`, `{directory_name}`
- Installer generates final `config.yaml` from this template
### Optional: module-installer/installer.js
For complex installations requiring custom logic:
```javascript
/**
* @param {Object} options - Installation options
* @param {string} options.projectRoot - Target project directory
* @param {Object} options.config - Config from install-config.yaml
* @param {Array} options.installedIDEs - IDEs being configured
* @param {Object} options.logger - Logger (log, warn, error)
* @returns {boolean} - true if successful
*/
async function install(options) {
// Custom installation logic here
// - Database setup
// - API configuration
// - External downloads
// - Integration setup
return true;
}
module.exports = { install };
```
### Optional: module-installer/assets/
Files to copy during installation:
- External configurations
- Documentation
- Example files
- Integration scripts
## Module Lifecycle
### Development Phases
1. **Planning Phase**
- Define scope and purpose
- Identify components
- Design architecture
2. **Scaffolding Phase**
- Create directory structure
- Generate configurations
- Setup installer
3. **Building Phase**
- Create agents incrementally
- Build workflows progressively
- Add tasks as needed
4. **Testing Phase**
- Test individual components
- Verify integration
- Validate installation
5. **Deployment Phase**
- Package module
- Document usage
- Distribute/share
## Best Practices
### Module Cohesion
- All components should relate to module theme
- Clear boundaries between modules
- No feature creep
### Progressive Enhancement
- Start with MVP (1 agent, 2 workflows)
- Add components based on usage
- Refactor as patterns emerge
### Documentation Standards
- Every module needs README.md
- Each agent needs purpose statement
- Workflows need clear descriptions
- Include examples and quickstart
### Naming Consistency
- Use module code prefix for uniqueness
- Consistent naming patterns within module
- Clear, descriptive names
## Example Modules
### Example 1: Personal Productivity
```
productivity/
├── agents/
│ ├── task-manager.md # GTD methodology
│ └── focus-coach.md # Pomodoro timer
├── workflows/
│ ├── daily-planning/ # Morning routine
│ ├── weekly-review/ # Week retrospective
│ └── project-setup/ # New project init
└── config.yaml
```
### Example 2: Content Creation
```
content/
├── agents/
│ ├── writer.md # Blog/article writer
│ ├── editor.md # Copy editor
│ └── seo-optimizer.md # SEO specialist
├── workflows/
│ ├── blog-post/ # Full blog creation
│ ├── social-media/ # Social content
│ ├── email-campaign/ # Email sequence
│ └── content-calendar/ # Planning
└── templates/
├── blog-template.md
└── email-template.md
```
### Example 3: DevOps Automation
```
devops/
├── agents/
│ ├── deploy-master.md # Deployment orchestrator
│ ├── monitor.md # System monitoring
│ ├── incident-responder.md # Incident management
│ └── infra-architect.md # Infrastructure design
├── workflows/
│ ├── ci-cd-setup/ # Pipeline creation
│ ├── deploy-app/ # Application deployment
│ ├── rollback/ # Emergency rollback
│ ├── health-check/ # System verification
│ └── incident-response/ # Incident handling
├── tasks/
│ ├── check-status.md # Quick status check
│ └── notify-team.md # Team notifications
└── data/
└── runbooks/ # Operational guides
```
## Module Evolution Pattern
```
Simple Module → Standard Module → Complex Module → Module Suite
(MVP) (Enhanced) (Complete) (Ecosystem)
```
## Common Pitfalls
1. **Over-engineering**: Starting too complex
2. **Under-planning**: No clear architecture
3. **Poor boundaries**: Module does too much
4. **Weak integration**: Components don't work together
5. **Missing docs**: No clear usage guide
## Success Metrics
A well-designed module has:
- ✅ Clear, focused purpose
- ✅ Cohesive components
- ✅ Smooth installation
- ✅ Comprehensive docs
- ✅ Room for growth
- ✅ Happy users!

52
src/modules/bmb/workflows-legacy/create-module/workflow.yaml
View File

@ -1,52 +0,0 @@
# Build Module Workflow Configuration
name: create-module
description: "Interactive workflow to build complete BMAD modules with agents, workflows, tasks, and installation infrastructure"
author: "BMad"
# Critical variables load from config_source
config_source: "{project-root}/{bmad_folder}/bmb/config.yaml"
custom_module_location: "{config_source}:custom_module_location"
communication_language: "{config_source}:communication_language"
user_name: "{config_source}:user_name"
# Reference guides for module building
module_structure_guide: "{installed_path}/module-structure.md"
installer_templates: "{installed_path}/installer-templates/"
# Use existing build workflows
agent_builder: "{project-root}/{bmad_folder}/bmb/workflows/create-agent/workflow.yaml"
workflow_builder: "{project-root}/{bmad_folder}/bmb/workflows/create-workflow/workflow.yaml"
brainstorming_workflow: "{project-root}/{bmad_folder}/core/workflows/brainstorming/workflow.yaml"
brainstorming_context: "{installed_path}/brainstorm-context.md"
# Reference examples - for learning patterns
bmm_module_dir: "{project-root}/{bmad_folder}/bmm/"
cis_module_dir: "{project-root}/{bmad_folder}/cis/"
existing_agents_dir: "{project-root}/{bmad_folder}/*/agents/"
existing_workflows_dir: "{project-root}/{bmad_folder}/*/workflows/"
# Optional user inputs - discovered if they exist
input_file_patterns:
module_brief:
description: "Module brief with vision and requirements (optional)"
whole: "{output_folder}/module-brief-*.md"
load_strategy: "FULL_LOAD"
brainstorming:
description: "Brainstorming session outputs (optional)"
whole: "{output_folder}/brainstorming-*.md"
load_strategy: "FULL_LOAD"
# Module path and component files
installed_path: "{project-root}/{bmad_folder}/bmb/workflows/create-module"
template: false # This is an interactive scaffolding workflow
instructions: "{installed_path}/instructions.md"
validation: "{installed_path}/checklist.md"
# Output configuration - creates entire module structure
# Save to custom_module_location/{{module_code}}
installer_output_folder: "{custom_module_location}/{{module_code}}"
standalone: true
# Web bundle configuration
web_bundle: false # BMB workflows run locally in BMAD-METHOD project

1
src/modules/bmb/workflows-legacy/edit-module/checklist.md
View File

@ -24,7 +24,6 @@ Use this checklist to validate module edits meet BMAD Core standards.
### Optional Fields (if used)
- [ ] custom_agent_location documented
- [ ] custom_module_location documented
- [ ] Module-specific fields documented in README

22
src/modules/bmb/workflows/create-agent/data/info-and-installation-guide.md
View File

@ -2,12 +2,24 @@
## Installation
```bash
# Quick install (interactive)
npx bmad-method agent-install --source ./{agent_filename}.agent.yaml
Create a `custom.yaml` file in the agent folder:
# Quick install (non-interactive)
npx bmad-method agent-install --source ./{agent_filename}.agent.yaml --defaults
```yaml
code: { agent_code }
name: '{agent_name}'
default_selected: true
```
Then run:
```bash
npx bmad-method install
```
Or if you have bmad-cli installed globally:
```bash
bmad install
```
## About This Agent

8
src/modules/bmb/workflows/create-agent/data/reference/agents/expert-examples/journal-keeper/README.md
View File

@ -51,7 +51,7 @@ menu:
# Direct sidecar file action
- trigger: 'insight'
action: 'Document this breakthrough in {agent-folder}/journal-keeper-sidecar/breakthroughs.md'
action: 'Document this breakthrough in ./journal-keeper-sidecar/breakthroughs.md'
description: 'Record a meaningful insight'
```
@ -63,9 +63,9 @@ Expert Agents MUST load sidecar files explicitly:
```yaml
critical_actions:
- 'Load COMPLETE file {agent-folder}/journal-keeper-sidecar/memories.md'
- 'Load COMPLETE file {agent-folder}/journal-keeper-sidecar/instructions.md'
- 'ONLY read/write files in {agent-folder}/journal-keeper-sidecar/'
- 'Load COMPLETE file ./journal-keeper-sidecar/memories.md'
- 'Load COMPLETE file ./journal-keeper-sidecar/instructions.md'
- 'ONLY read/write files in ./journal-keeper-sidecar/'
```
**Key points:**

14
src/modules/bmb/workflows/create-agent/data/reference/agents/expert-examples/journal-keeper/journal-keeper.agent.yaml
View File

@ -20,9 +20,9 @@ agent:
- Reflection transforms experience into wisdom
critical_actions:
- "Load COMPLETE file {agent-folder}/journal-keeper-sidecar/memories.md and remember all past insights"
- "Load COMPLETE file {agent-folder}/journal-keeper-sidecar/instructions.md and follow ALL journaling protocols"
- "ONLY read/write files in {agent-folder}/journal-keeper-sidecar/ - this is our private space"
- "Load COMPLETE file ./journal-keeper-sidecar/memories.md and remember all past insights"
- "Load COMPLETE file ./journal-keeper-sidecar/instructions.md and follow ALL journaling protocols"
- "ONLY read/write files in ./journal-keeper-sidecar/ - this is our private space"
- "Track mood patterns, recurring themes, and breakthrough moments"
- "Reference past entries naturally to show continuity"
@ -120,7 +120,7 @@ agent:
description: "Write today's journal entry"
- trigger: quick
action: "Save a quick, unstructured entry to {agent-folder}/journal-keeper-sidecar/entries/entry-{date}.md with timestamp and any patterns noticed"
action: "Save a quick, unstructured entry to ./journal-keeper-sidecar/entries/entry-{date}.md with timestamp and any patterns noticed"
description: "Quick capture without prompts"
- trigger: mood
@ -140,13 +140,13 @@ agent:
description: "Reflect on the past week"
- trigger: insight
action: "Document this breakthrough in {agent-folder}/journal-keeper-sidecar/breakthroughs.md with date and significance"
action: "Document this breakthrough in ./journal-keeper-sidecar/breakthroughs.md with date and significance"
description: "Record a meaningful insight"
- trigger: read-back
action: "Load and share entries from {agent-folder}/journal-keeper-sidecar/entries/ for requested timeframe, highlighting themes and growth"
action: "Load and share entries from ./journal-keeper-sidecar/entries/ for requested timeframe, highlighting themes and growth"
description: "Review past entries"
- trigger: save
action: "Update {agent-folder}/journal-keeper-sidecar/memories.md with today's session insights and emotional markers"
action: "Update ./journal-keeper-sidecar/memories.md with today's session insights and emotional markers"
description: "Save what we discussed today"

155
src/modules/bmb/workflows/create-module/steps/step-01-init.md Normal file
View File

@ -0,0 +1,155 @@
---
nextStepFile: '{installed_path}/steps/step-02-concept.md'
continueFile: '{installed_path}/steps/step-01b-continue.md'
modulePlanTemplate: '{installed_path}/templates/module-plan.template.md'
advancedElicitationTask: '{project-root}/{bmad_folder}/core/tasks/advanced-elicitation.xml'
partyModeWorkflow: '{project-root}/{bmad_folder}/core/workflows/party-mode/workflow.md'
customModuleLocation: '{custom_module_location}'
modulePlanFile: '{custom_module_location}/{module_name}/module-plan-{module_name}.md'
---
# Step 1: Workflow Initialization
## STEP GOAL:
To initialize the create-module workflow by getting the module name from the user, checking for existing work, handling continuation if needed, and creating the initial module plan document.
## 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 BMAD Systems Specialist
- ✅ We engage in collaborative dialogue, not command-response
- ✅ You bring expertise in BMAD architecture and module creation, user brings their module requirements
- ✅ Maintain collaborative, guiding tone throughout
### Step-Specific Rules:
- 🎯 Focus ONLY on initialization, getting module name, and setting up tracking
- 🚫 FORBIDDEN to look ahead to future steps
- 💬 Handle initialization professionally
- 🚪 DETECT existing workflow state and handle continuation properly
## EXECUTION PROTOCOLS:
- 🎯 Show analysis before taking any action
- 💾 Initialize document and update frontmatter
- 📖 Set up frontmatter `stepsCompleted: [1]` before loading next step
- 🚫 FORBIDDEN to load next step until setup is complete
## CONTEXT BOUNDARIES:
- Variables from workflow.md are available in memory
- Previous context = what's in output document + frontmatter
- Don't assume knowledge from other steps
- Module brief discovery happens in this step
## SEQUENCE OF INSTRUCTIONS:
### 1. Welcome and Get Module Name
Greet the user warmly by their {user_name}, welcoming them to the BMAD Module Creator. Through conversation, collaboratively work with them to:
- Understand what kind of module they want to create
- Help them choose a good name in kebab-case (provide examples if needed)
- Validate the name will work for module creation
### 2. Check for Existing Work
Once you have the module name:
- Check if a folder already exists at {customModuleLocation}/{module_name}
- If it exists, look for a module plan document inside
- Read any existing work carefully to understand what was already done
### 3. Handle Continuation (If Work Exists)
If you find an existing module plan:
- Review what's been completed based on the stepsCompleted array
- Present a clear summary of the current status
- Ask if they want to continue where they left off, update existing work, or start fresh
- If continuing, load step-01b-continue.md
### 4. Look for Supporting Documents
Check for any existing documents that could help:
- Module briefs in the module folder or output folder
- Brainstorming results in the output folder
- Any other relevant documentation
### 5. Guide User's Next Decision
If no supporting documents are found:
- Explain their three options clearly and helpfully
- Option 1: Proceed with creating the module based on their ideas
- Option 2: Exit and create a module brief first (explain the module-brief workflow)
- Option 3: Exit and do brainstorming first (explain the brainstorming workflow)
- Support whatever choice they make
### 6. Create Module Foundation
If proceeding:
- Create the module folder if needed
- Create the initial module-plan-{module_name}.md document using the module plan template from {modulePlanTemplate}
- Initialize proper frontmatter with current date, user name, and add "step-01-init" to stepsCompleted array
- Add any discovered documents to inputDocuments field
- Include a brief section about the legacy reference
### 7. Prepare for Next Step
- Confirm everything is set up properly
- Let the user know what you've accomplished
- Transition smoothly to the next phase of defining the module concept
### 8. Present MENU OPTIONS
Display: **Proceeding to define your module concept...**
#### EXECUTION RULES:
- This is an initialization step with no user choices (after inputs handled)
- Proceed directly to next step after setup
- Use menu handling logic section below
#### Menu Handling Logic:
- After setup completion, add step-01-init to the end of the stepsCompleted array in module plan frontmatter, then load, read entire file, then execute `{nextStepFile}` to define the module concept
---
## 🚨 SYSTEM SUCCESS/FAILURE METRICS
### ✅ SUCCESS:
- Module name obtained and validated through collaborative dialogue
- Module plan document created from template with frontmatter initialized
- "step-01-init" added to stepsCompleted array
- Module plan document created at correct location
- User feels welcomed and informed
- Ready to proceed to step 2
- OR existing workflow properly routed to step-01b-continue.md
### ❌ SYSTEM FAILURE:
- Proceeding with step 2 without module plan creation
- Not checking for existing documents properly
- Creating module without user input on name
- Skipping folder creation
- Not routing to step-01b-continue.md when appropriate
**Master Rule:** Skipping steps, optimizing sequences, or not following exact instructions is FORBIDDEN and constitutes SYSTEM FAILURE.
## CRITICAL STEP COMPLETION NOTE
ONLY WHEN initialization setup is complete and module plan document is created (OR continuation is properly routed), will you then immediately load, read entire file, then execute `{nextStepFile}` to begin defining the module concept.

169
src/modules/bmb/workflows/create-module/steps/step-01b-continue.md Normal file
View File

@ -0,0 +1,169 @@
---
modulePlanFile: '{custom_module_location}/{module_name}/module-plan-{module_name}.md'
---
# Step 1b: Continue Module Creation
## 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 BMAD Systems Specialist
- ✅ We engage in collaborative dialogue, not command-response
- ✅ You bring expertise in BMAD architecture and module creation, user brings their module requirements
- ✅ Maintain collaborative, guiding tone throughout
### Step-Specific Rules:
- 🎯 Focus ONLY on handling continuation and resuming workflow
- 🚫 FORBIDDEN to modify existing work without user consent
- 💬 Present status clearly and get user direction
- 📋 Track completion status accurately
## EXECUTION PROTOCOLS:
- 🎯 Load and analyze existing module plan
- 💾 Update frontmatter with continuation status
- 📖 Route to appropriate next step based on progress
- 🚫 FORBIDDEN to skip steps just because they exist
## CONTEXT BOUNDARIES:
- Module plan document exists with previous work
- Focus on understanding what's been done and what remains
- Don't assume completion without verification
- User direction guides next actions
## STEP GOAL:
To resume module creation by presenting current status, understanding what's been accomplished, and determining the next step in the process.
## CONTINUATION HANDLING SEQUENCE:
### 1. Load and Analyze Existing Module Plan
Load module plan from: {modulePlanFile}
Read entire document including frontmatter
Extract current status from frontmatter fields:
- stepsCompleted array
- lastStep (the final item in the stepsCompleted array)
- module_name
- module_code
- date
- inputDocuments
### 2. Present Current Status
"Welcome back! I found your in-progress module creation for **{module_name}**.
**Current Status:**
- **Module Code:** {module_code}
- **Started:** {date}
- **Last Step:** {lastStep}
- **Steps Completed:** {stepsCompleted count}/{total steps}
- **Location:** {custom_module_location}/{module_name}
\*\*Progress Summary:"
Based on stepsCompleted, show:
- [✅] Step 1: Init - Complete
- [ ] Step 2: Concept - {status}
- [ ] Step 3: Components - {status}
- [ ] Step 4: Structure - {status}
- [ ] Step 5: Configuration - {status}
- [ ] Step 6: Agents - {status}
- [ ] Step 7: Workflows - {status}
- [ ] Step 8: Installer - {status}
- [ ] Step 9: Documentation - {status}
- [ ] Step 10: Roadmap - {status}
- [ ] Step 11: Validation - {status}
### 3. Review What's Been Done
Read content sections of module plan
Summarize what's been accomplished:
"**Completed Work:**
- Module identity defined
- Component planning complete
- [Other completed items based on content]"
### 4. Determine Next Step
Based on stepsCompleted array:
Find highest completed step number
Next step = highest completed + 1
"**Ready to Continue:**
Your next step would be: **Step {nextStep} - [step name]**
What would you like to do?
1. **Continue** from where you left off
2. **Review** what's been done so far
3. **Modify** previous work
4. **Start over** with a new plan"
### 5. Handle User Choice
User your best judgement in how to handle the users choice
### 6. Update Continuation Status
Update modulePlanFile frontmatter:
- Set lastStep: 'continued'
- Add note about continuation date
- Keep stepsCompleted unchanged
## ✅ SUCCESS METRICS:
- User understands current progress
- Next step identified correctly
- User choice handled appropriately
- Module plan updated with continuation status
- Workflow resumed at correct location
## ❌ FAILURE MODES TO AVOID:
- Not accurately reading previous status
- Skipping steps just because they exist
- Not offering review option
- Losing previous work
- Not updating continuation tracking
---
## 🚨 SYSTEM SUCCESS/FAILURE METRICS
### ✅ SUCCESS:
- Existing work properly loaded and analyzed
- User clearly understands current status
- Continuation options presented clearly
- Next step determined correctly
- Module plan updated with continuation information
### ❌ SYSTEM FAILURE:
- Not reading existing plan completely
- Misrepresenting progress status
- Losing track of what's been done
- Not offering appropriate continuation options
**Master Rule:** Skipping steps, optimizing sequences, or not following exact instructions is FORBIDDEN and constitutes SYSTEM FAILURE.
## CRITICAL STEP COMPLETION NOTE
ONLY WHEN user selects 'C' (Continue) and appropriate updates are saved to modulePlanFile, will you then load, read entire file, then execute the determined next step file to resume the module creation workflow.

217
src/modules/bmb/workflows/create-module/steps/step-02-concept.md Normal file
View File

@ -0,0 +1,217 @@
---
installed_path: '{project-root}/{bmad_folder}/bmb/workflows/create-module'
nextStepFile: '{installed_path}/steps/step-03-components.md'
modulePlanFile: '{custom_module_location}/{module_name}/module-plan-{module_name}.md'
moduleStructureGuide: '{project-root}/src/modules/bmb/workflows-legacy/create-module/module-structure.md'
advancedElicitationTask: '{project-root}/{bmad_folder}/core/tasks/advanced-elicitation.xml'
partyModeWorkflow: '{project-root}/{bmad_folder}/core/workflows/party-mode/workflow.md'
---
# Step 2: Define Module Concept and Scope
## 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 Business Analyst
- ✅ 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 module design and BMAD patterns, user brings their domain knowledge
- ✅ Maintain collaborative, educational tone
### Step-Specific Rules:
- 🎯 Focus ONLY on defining the module concept and scope
- 🚫 FORBIDDEN to start designing components in this step
- 💬 Ask questions conversationally to understand vision
- 🚫 FORBIDDEN to proceed without clear module identity
## EXECUTION PROTOCOLS:
- 🎯 Load and study module structure guide for context
- 💾 Document all module identity details in plan
- 📖 Add "step-02-concept" to stepsCompleted array` before loading next step
- 🚫 FORBIDDEN to load next step until user selects 'C'
## CONTEXT BOUNDARIES:
- Module name and location from step 1
- Input documents (brief/brainstorming) if any
- Focus ONLY on concept and scope definition
- Don't assume module details beyond what user provides
## STEP GOAL:
To articulate the module's vision, define its identity, and establish clear boundaries for what it will and won't do.
## MODULE CONCEPT DEFINITION PROCESS:
### 1. Load Context and Briefs
"Let's define your module's concept and identity. This will guide all the decisions we make about agents, workflows, and features."
Load module-plan.md and check inputDocuments field
Read the module brief completely
"I see you have a module brief. Let me review that to understand your vision..."
Use brief content to inform concept development questions
Load and study the module structure guide for context
### 2. Guide Concept Development
Ask conversationally:
"**Understanding Your Vision:**
1. **What problem will this module solve?** - What pain point or need are you addressing?
2. **Who is the primary user?** - Who will benefit most from this module?
3. **What's the main outcome?** - What will users be able to do after using your module?
4. **Why is this important?** - What makes this module valuable or unique?"
### 3. Module Identity Development
Based on their responses, collaboratively develop:
**Module Name:**
- Start with their module code: {module_name}
- Suggest a display name in Title Case
- Get user confirmation or refinement
**Module Purpose:**
- Distill their problem statement into 1-2 clear sentences
- Focus on value and outcomes
- Get user validation
**Target Audience:**
- Identify primary user persona
- Consider skill level (beginner/intermediate/advanced)
- Note any secondary audiences
**Module Scope:**
- What's IN scope (core features)
- What's OUT of scope (explicitly state what it won't do)
- Success criteria (how will we know it works?)
### 4. Module Theme and Category
"**Module Classification:**
Based on your description, this seems to fit in the [Domain-Specific/Creative/Technical/Business/Personal] category.
Does this sound right? Or would you categorize it differently?
**Example Categories:**
- **Domain-Specific**: Legal, Medical, Finance, Education
- **Creative**: RPG/Gaming, Story Writing, Music Production
- **Technical**: DevOps, Testing, Architecture, Security
- **Business**: Project Management, Marketing, Sales
- **Personal**: Journaling, Learning, Productivity"
### 5. Module Type Estimation
"Based on what you've described, I'm thinking this might be a:
- **Simple Module** (1-2 agents, 2-3 workflows) - Focused, single-purpose
- **Standard Module** (3-5 agents, 5-10 workflows) - Comprehensive solution
- **Complex Module** (5+ agents, 10+ workflows) - Full platform/framework
Which feels right for your vision? We'll confirm this after planning components."
### 6. Document Module Concept
Update module-plan.md with concept section:
```markdown
## Module Concept
**Module Name:** {module_display_name}
**Module Code:** {module_name}
**Category:** [category]
**Type:** [estimated type]
**Purpose Statement:**
[1-2 sentence clear purpose]
**Target Audience:**
- Primary: [description]
- Secondary: [if any]
**Scope Definition:**
**In Scope:**
- [core feature 1]
- [core feature 2]
- [core feature 3]
**Out of Scope:**
- [explicitly excluded item 1]
- [explicitly excluded item 2]
**Success Criteria:**
- [measurable outcome 1]
- [measurable outcome 2]
- [user satisfaction indicator]
```
### 7. Present MENU OPTIONS
Display: **Select an Option:** [A] Advanced Elicitation [P] Party Mode [C] Continue
#### Menu Handling Logic:
- IF A: Execute {advancedElicitationTask} to explore alternative concept approaches
- IF P: Execute {partyModeWorkflow} to get creative input on module identity
- IF C: Save concept to module-plan.md, add step-02-concept 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:
- Module purpose clearly articulated
- Module identity established (name, audience, scope)
- Category and type determined
- Concept documented in module plan
- User feels the concept matches their vision
### ❌ SYSTEM FAILURE:
- Proceeding without clear module purpose
- Not defining scope boundaries
- Skipping user validation of concept
- Not documenting concept details
**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 module concept is saved to module-plan.md with stepsCompleted updated to [1, 2], will you then load, read entire file, then execute `{nextStepFile}` to begin component planning.

267
src/modules/bmb/workflows/create-module/steps/step-03-components.md Normal file
View File

@ -0,0 +1,267 @@
---
installed_path: '{project-root}/{bmad_folder}/bmb/workflows/create-module'
nextStepFile: '{installed_path}/steps/step-04-structure.md'
modulePlanFile: '{custom_module_location}/{module_name}/module-plan-{module_name}.md'
agent_examples_path: '{project-root}/src/modules/bmb/reference/agents/module-examples'
advancedElicitationTask: '{project-root}/{bmad_folder}/core/tasks/advanced-elicitation.xml'
partyModeWorkflow: '{project-root}/{bmad_folder}/core/workflows/party-mode/workflow.md'
---
# Step 3: Plan Module Components
## 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 Systems 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 component design patterns, user brings their domain requirements
- ✅ Maintain collaborative, design-focused tone
### Step-Specific Rules:
- 🎯 Focus ONLY on planning component architecture
- 🚫 FORBIDDEN to create actual components in this step
- 💬 Present component options with reasoning
- 🚫 FORBIDDEN to finalize component list without user agreement
## EXECUTION PROTOCOLS:
- 🎯 Reference agent examples for patterns
- 💾 Document component plan in detail
- 📖 Add "step-03-components" to stepsCompleted array` before loading next step
- 🚫 FORBIDDEN to load next step until user selects 'C'
## CONTEXT BOUNDARIES:
- Module concept from step 2 is available
- Focus on planning, not implementation
- Consider BMAD patterns and best practices
- Reference examples but don't copy exactly
## STEP GOAL:
To design the component architecture for the module, determining what agents, workflows, and tasks are needed to fulfill the module's purpose.
## COMPONENT PLANNING PROCESS:
### 1. Initialize Component Planning
"Now that we have a clear module concept, let's plan the components that will bring it to life.
Based on your module's purpose and scope, we'll design:
- **Agents** - The AI personas that will help users
- **Workflows** - The step-by-step processes for accomplishing tasks
- **Tasks** - Quick utilities and supporting functions"
### 2. Agent Planning
"**Agent Architecture:**
Think about the different roles or perspectives needed to accomplish your module's goals. Each agent should have a clear, distinct purpose."
Reference agent examples for patterns
Load and browse agent examples: {agent_examples_path}
"**Common Agent Patterns:**
- **Primary Agent** - The main interface/orchestrator
- **Specialist Agents** - Domain-specific experts
- **Utility Agents** - Helper/support functions
**Example by Module Type:**
**Technical Modules (e.g., DevOps, Testing):**
- Implementation Specialist
- Reviewer/Auditor
- Documentation Expert
**Creative Modules (e.g., Story Writing, Game Design):**
- Creative Director
- World Builder
- Content Generator
**Business Modules (e.g., Project Management):**
- Project Coordinator
- Facilitator
- Analyst"
"**For your {module_category} module, I suggest considering:**
[Suggest 2-4 specific agent types based on module concept]
**What resonates with your vision?** Which of these agents would be most valuable, and are there any others you'd like to add?"
### 3. Workflow Planning
"**Workflow Design:**
Workflows are the step-by-step processes that users will follow to accomplish specific tasks. Each workflow should solve a specific problem or achieve a particular outcome."
**Types of Workflows:**
- **Document Workflows** - Generate reports, plans, specifications
- **Action Workflows** - Perform operations, create structures
- **Interactive Workflows** - Guided sessions, coaching, training
**Example Workflow Patterns:**
"For your module's purpose, consider these potential workflows:
1. **[Primary Workflow Name]** - Main workflow for core functionality
2. **[Supporting Workflow 1]** - For specific use case
3. **[Supporting Workflow 2]** - For another use case
Remember: We'll create workflow PLANS first, not full implementations. These plans can be used later with the create-workflow workflow."
### 4. Task Planning (Optional)
"**Task Planning (if needed):**
Tasks are single-operation utilities that don't need full workflows. They're good for:
- Quick actions
- Shared subroutines
- Helper functions
Does your module need any tasks? For example:
- Status checking
- Quick formatting
- Validation utilities"
### 5. Component Integration Planning
"**How Components Work Together:**
Let's think about how your components will interact:
- **Agent Collaboration**: Will agents work together or independently?
- **Workflow Dependencies**: Do workflows need to call each other?
- **Task Usage**: Which workflows will use which tasks?"
### 6. Component Priority and MVP
"**Starting Point (MVP):**
To ensure success, let's identify the minimum viable set:
**Must Have (Phase 1):**
- [List essential agents]
- [List essential workflows]
**Nice to Have (Phase 2):**
- [Additional agents]
- [Additional workflows]
- [Tasks if any]
This approach lets you launch with core functionality and expand later."
### 7. Document Component Plan
Update module-plan.md with component section:
```markdown
## Component Architecture
### Agents (N planned)
1. **[Agent Name]** - [Brief purpose]
- Type: [Primary/Specialist/Utility]
- Role: [Specific role description]
2. **[Agent Name]** - [Brief purpose]
- Type: [Primary/Specialist/Utility]
- Role: [Specific role description]
### Workflows (N planned)
1. **[Workflow Name]** - [Purpose]
- Type: [Document/Action/Interactive]
- Primary user: [Who uses this]
- Key output: [What it produces]
2. **[Workflow Name]** - [Purpose]
- Type: [Document/Action/Interactive]
- Primary user: [Who uses this]
- Key output: [What it produces]
### Tasks (N planned)
1. **[Task Name]** - [Single-purpose function]
- Used by: [Which workflows/agents]
### Component Integration
- Agents collaborate via: [description]
- Workflow dependencies: [description]
- Task usage patterns: [description]
### Development Priority
**Phase 1 (MVP):**
- [List of components to create first]
**Phase 2 (Enhancement):**
- [List of components for later]
```
### 8. Present MENU OPTIONS
Display: **Select an Option:** [A] Advanced Elicitation [P] Party Mode [C] Continue
#### Menu Handling Logic:
- IF A: Execute {advancedElicitationTask} to explore alternative component architectures
- IF P: Execute {partyModeWorkflow} to get creative input on component design
- IF C: Save component plan to module-plan.md, add step-03-components 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:
- Component architecture planned and documented
- Agent types and purposes clearly defined
- Workflow requirements identified
- Integration patterns established
- Development priority set (MVP vs enhancements)
### ❌ SYSTEM FAILURE:
- Planning components without module purpose context
- Not considering BMAD patterns and examples
- Over-engineering (too many components)
- Under-planning (missing essential components)
- Not establishing development priorities
**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 component plan is saved to module-plan.md with stepsCompleted updated to [1, 2, 3], will you then load, read entire file, then execute `{nextStepFile}` to begin creating the module structure.

228
src/modules/bmb/workflows/create-module/steps/step-04-structure.md Normal file
View File

@ -0,0 +1,228 @@
---
installed_path: '{project-root}/{bmad_folder}/bmb/workflows/create-module'
nextStepFile: '{installed_path}/steps/step-05-config.md'
modulePlanFile: '{custom_module_location}/{module_name}/module-plan-{module_name}.md'
advancedElicitationTask: '{project-root}/{bmad_folder}/core/tasks/advanced-elicitation.xml'
partyModeWorkflow: '{project-root}/{bmad_folder}/core/workflows/party-mode/workflow.md'
---
# Step 4: Create Module Structure
## 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 Systems Organizer
- ✅ 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 structure patterns, user brings their component requirements
- ✅ Maintain collaborative, organized tone
### Step-Specific Rules:
- 🎯 Focus ONLY on creating directory structure and determining complexity
- 🚫 FORBIDDEN to create actual component files in this step
- 💬 Explain structure decisions clearly
- 🚫 FORBIDDEN to proceed without confirming structure
## EXECUTION PROTOCOLS:
- 🎯 Use component count to determine module type
- 💾 Create all required directories
- 📖 Add "step-04-structure" to stepsCompleted array` before loading next step
- 🚫 FORBIDDEN to load next step until user selects 'C'
## CONTEXT BOUNDARIES:
- Component plan from step 3 is available
- Standard BMAD module structure to follow
- Focus on structure creation, not content
- Module folder already exists from step 1
## STEP GOAL:
To determine the module's complexity type and create the complete directory structure for the module.
## MODULE STRUCTURE CREATION PROCESS:
### 1. Determine Module Complexity
"Based on your component plan, let's determine your module's complexity level:"
**Count Components:**
- Agents: [count from plan]
- Workflows: [count from plan]
- Tasks: [count from plan]
**Complexity Assessment:**
"**Simple Module Criteria:**
- 1-2 agents, all Simple type
- 1-3 workflows
- No complex integrations
**Standard Module Criteria:**
- 2-4 agents with mixed types
- 3-8 workflows
- Some shared resources
**Complex Module Criteria:**
- 4+ agents or multiple Module-type agents
- 8+ workflows
- Complex interdependencies
- External integrations"
"**Your module has:**
- [agent_count] agents
- [workflow_count] workflows
- [task_count] tasks
**This makes it a: [Simple/Standard/Complex] Module**"
### 2. Present Module Structure
"**Standard BMAD Module Structure:**
For a [module type] module, we'll create this structure:"
```
{module_code}/
├── agents/ # Agent definitions (.md)
│ ├── [agent-name].md
│ └── ...
├── workflows/ # Workflow folders
│ ├── [workflow-name]/
│ │ ├── workflow-plan.md # Descriptive plan
│ │ └── README.md # Workflow documentation
│ └── ...
├── tasks/ # Task files (if any)
│ └── [task-name].md
├── templates/ # Shared templates
│ └── [template-files]
├── data/ # Module data files
│ └── [data-files]
├── _module-installer/ # Installation configuration
│ ├── install-config.yaml # Required
│ ├── installer.js # Optional
│ └── assets/ # Optional install assets
└── README.md # Module documentation
```
### 3. Create Directory Structure
Create all directories in {custom_module_location}/{module_name}/:
1. **agents/** - For agent definition files
2. **workflows/** - For workflow folders
3. **tasks/** - For task files (if tasks planned)
4. **templates/** - For shared templates
5. **data/** - For module data
6. **\_module-installer/** - For installation configuration
### 4. Create Placeholder README
Create initial README.md with basic structure:
````markdown
# {module_display_name}
{module_purpose}
## Installation
```bash
bmad install {module_code}
```
````
## Components
_Module documentation will be completed in Step 9_
## Quick Start
_Getting started guide will be added in Step 9_
---
_This module is currently under construction_
````
### 5. Document Structure Creation
Update module-plan.md with structure section:
```markdown
## Module Structure
**Module Type:** [Simple/Standard/Complex]
**Location:** {custom_module_location}/{module_name}
**Directory Structure Created:**
- ✅ agents/
- ✅ workflows/
- ✅ tasks/
- ✅ templates/
- ✅ data/
- ✅ _module-installer/
- ✅ README.md (placeholder)
**Rationale for Type:**
[Explain why it's Simple/Standard/Complex based on component counts]
````
### 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 alternative structure approaches
- IF P: Execute {partyModeWorkflow} to get creative input on organization
- IF C: Save structure info to module-plan.md, add step-04-structure 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:
- Module complexity correctly determined
- All required directories created
- Structure follows BMAD standards
- Placeholder README created
- Structure documented in plan
### ❌ SYSTEM FAILURE:
- Not creating all required directories
- Incorrectly categorizing module complexity
- Not following BMAD structure patterns
- Creating component files prematurely
**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 structure is saved to module-plan.md with stepsCompleted updated to [1, 2, 3, 4], will you then load, read entire file, then execute `{nextStepFile}` to begin configuration planning.

233
src/modules/bmb/workflows/create-module/steps/step-05-config.md Normal file
View File

@ -0,0 +1,233 @@
---
installed_path: '{project-root}/{bmad_folder}/bmb/workflows/create-module'
nextStepFile: '{installed_path}/steps/step-06-agents.md'
modulePlanFile: '{custom_module_location}/{module_name}/module-plan-{module_name}.md'
advancedElicitationTask: '{project-root}/{bmad_folder}/core/tasks/advanced-elicitation.xml'
partyModeWorkflow: '{project-root}/{bmad_folder}/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 install-config.yaml will generate:
- Module configuration at: {bmad_folder}/{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.

296
src/modules/bmb/workflows/create-module/steps/step-06-agents.md Normal file
View File

@ -0,0 +1,296 @@
---
installed_path: '{project-root}/{bmad_folder}/bmb/workflows/create-module'
nextStepFile: '{installed_path}/steps/step-07-workflows.md'
modulePlanFile: '{custom_module_location}/{module_name}/module-plan-{module_name}.md'
agentTemplate: '{installed_path}/templates/agent.template.md'
agent_examples_path: '{project-root}/src/modules/bmb/reference/agents/module-examples'
advancedElicitationTask: '{project-root}/{bmad_folder}/core/tasks/advanced-elicitation.xml'
partyModeWorkflow: '{project-root}/{bmad_folder}/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_folder}/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_folder}/{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: {custom_module_location}/{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: {custom_module_location}/{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.

228
src/modules/bmb/workflows/create-module/steps/step-07-workflows.md Normal file
View File

@ -0,0 +1,228 @@
---
installed_path: '{project-root}/{bmad_folder}/bmb/workflows/create-module'
nextStepFile: '{installed_path}/steps/step-08-installer.md'
modulePlanFile: '{custom_module_location}/{module_name}/module-plan-{module_name}.md'
workflowPlanTemplate: '{installed_path}/templates/workflow-plan-template.md'
advancedElicitationTask: '{project-root}/{bmad_folder}/core/tasks/advanced-elicitation.xml'
partyModeWorkflow: '{project-root}/{bmad_folder}/core/workflows/party-mode/workflow.md'
---
# Step 7: Review Workflow Plans
## 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 Workflow 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 workflow patterns, user brings their workflow requirements
- ✅ Maintain collaborative, review-focused tone
### Step-Specific Rules:
- 🎯 Focus on reviewing existing workflow README files from Step 6
- 🚫 FORBIDDEN to use create-workflow workflow in this step
- 💬 Review and refine workflow plans, not create new ones
- 🚫 FORBIDDEN to create actual workflow steps
## EXECUTION PROTOCOLS:
- 🎯 Review workflow README files created in Step 6
- 💾 Update README files based on user feedback
- 📖 Add "step-07-workflows" to stepsCompleted array` before loading next step
- 🚫 FORBIDDEN to load next step until user selects 'C'
## CONTEXT BOUNDARIES:
- Workflow README files were created in Step 6 for each agent
- These README files contain workflow plans for later implementation
- Module structure already created with workflow folders
- Focus on reviewing and refining, not creating from scratch
## STEP GOAL:
To review and refine the workflow README files created in Step 6, ensuring they have clear plans for later implementation with the create-workflow workflow.
## WORKFLOW REVIEW PROCESS:
### 1. List Workflow Folders Created
"Let's review the workflow plans created in Step 6 for your {module_display_name} module.
I've already created workflow folders and README.md files for each agent's workflows:
**Workflow folders found:**
- [List all workflow folders in {custom_module_location}/{module_name}/workflows/]
**Each workflow folder contains a README.md with:**
- Purpose and description
- Trigger code from agent menu
- Key steps outline
- Expected outputs
- Notes for implementation"
### 2. Review Each Workflow Plan
For each workflow README file:
#### 2.1 Load and Present
"**Reviewing Workflow: [Workflow Name]**
Reading the README.md from: [workflow-folder]/README.md
**Current Plan:**
[Purpose]
[Trigger]
[Key Steps]
[Expected Output]
[Notes]
How does this plan look? Should we:
- Keep it as is
- Modify the purpose
- Adjust the steps
- Change the expected output"
#### 2.2 Update Based on Feedback
If user wants changes:
- Update the README.md file
- Keep the same basic structure
- Ensure clarity for future implementation
#### 2.3 Check for Missing Information
Ensure each README has:
```markdown
# [Workflow Name]
## Purpose
[Clear, concise description of what this workflow accomplishes]
## Trigger
[Trigger code from agent menu, e.g., "WF" or specific code]
## Key Steps
1. [Step 1 - What happens first]
2. [Step 2 - What happens next]
3. [Step 3 - Continue as needed]
## Expected Output
[What the workflow produces - document, action, result]
## Notes
This workflow will be implemented using the create-workflow workflow.
(Optional: Any special considerations or requirements)
```
### 3. Link Workflows to Agents
"**Workflow-Agent Mapping:**
Let's verify each workflow is properly linked to its agent:
[For each workflow]:
- **Workflow:** [Workflow Name]
- **Agent:** [Agent Name]
- **Trigger Code:** [WF code]
- **Menu Item:** [Menu description in agent]
Are all these mappings correct in the agent files?"
### 4. Document Implementation Plan
Update module-plan.md with workflow section:
```markdown
## Workflow Plans Reviewed
### For Agent [Agent Name]:
1. **[Workflow Name]**
- Location: workflows/[workflow-name]/
- Status: Plan reviewed and ready for implementation
- Trigger: [WF code]
- Implementation: Use create-workflow workflow
2. **[Workflow Name]**
- Location: workflows/[workflow-name]/
- Status: Plan reviewed and ready for implementation
- Trigger: [WF code]
- Implementation: Use create-workflow workflow
```
### 5. Next Steps Guidance
"**Ready for Implementation:**
All workflow plans are now reviewed and ready. To implement these workflows later:
1. Use the `/bmad:bmb:workflows:create-workflow` command
2. Select each workflow folder
3. Follow the create-workflow workflow
4. It will create the full workflow.md and step files
The README.md in each folder serves as your blueprint for implementation."
### 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 workflow designs
- IF P: Execute {partyModeWorkflow} to get creative input on workflow processes
- IF C: Save workflow plan status to module-plan.md, add step-07-workflows 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 workflow README files reviewed with user
- Each workflow plan has clear purpose and steps
- Workflow-agent mappings verified
- README files updated based on feedback
- Clear implementation guidance provided
### ❌ SYSTEM FAILURE:
- Skipping review of workflow README files
- Not updating plans based on user feedback
- Missing critical information in README files
- Not verifying workflow-agent mappings
**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 workflow plans are reviewed and documented and stepsCompleted updated, will you then load, read entire file, then execute `{nextStepFile}` to begin installer setup.

186
src/modules/bmb/workflows/create-module/steps/step-08-installer.md Normal file
View File

@ -0,0 +1,186 @@
---
installed_path: '{project-root}/{bmad_folder}/bmb/workflows/create-module'
nextStepFile: '{installed_path}/steps/step-09-documentation.md'
modulePlanFile: '{custom_module_location}/{module_name}/module-plan-{module_name}.md'
installerTemplate: '{installed_path}/templates/installer.template.js'
installConfigTemplate: '{installed_path}/templates/install-config.template.yaml'
advancedElicitationTask: '{project-root}/{bmad_folder}/core/tasks/advanced-elicitation.xml'
partyModeWorkflow: '{project-root}/{bmad_folder}/core/workflows/party-mode/workflow.md'
---
# Step 8: Setup Module Installer
## 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 Installation 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, technical tone
### Step-Specific Rules:
- 🎯 Focus on creating installer configuration files
- 🚫 FORBIDDEN to run actual installation
- 💬 Follow BMAD installer standards exactly
- 🚫 FORBIDDEN to deviate from configuration template
## EXECUTION PROTOCOLS:
- 🎯 Use configuration plan from step 5
- 💾 Create install-config.yaml with all fields
- 📖 Add "step-08-installer" to stepsCompleted array` before loading next step
- 🚫 FORBIDDEN to load next step until user selects 'C'
## CONTEXT BOUNDARIES:
- Configuration plan from step 5 defines installer fields
- Standard BMAD installer template to follow
- Module structure already created
- Focus on installer setup, not module content
## STEP GOAL:
To create the module installer configuration (install-config.yaml) that defines how users will install and configure the module.
## INSTALLER SETUP PROCESS:
### 1. Review Configuration Plan
"Now let's set up the installer for your {module_display_name} module.
The installer will:
- Define how users install your module
- Collect configuration settings
- Set up the module structure in user projects
- Generate the module's config.yaml file
From step 5, we planned these configuration fields:
- [List planned configuration fields]"
### 2. Create Installer Directory
Ensure \_module-installer directory exists
Directory: {custom_module_location}/{module_name}/\_module-installer/
### 3. Create install-config.yaml
"I'll create the install-config.yaml file based on your configuration plan. This is the core installer configuration file."
Create file: {custom_module_location}/{module_name}/\_module-installer/install-config.yaml from template {installConfigTemplate}
### 4. Handle Custom Installation Logic
"**Custom Installation Logic:**
Does your module need any special setup during installation? For example:
- Creating database tables
- Setting up API connections
- Downloading external assets
- Running initialization scripts"
<ask>Does your module need custom installation logic? [yes/no]</ask>
"I'll create an installer.js file for custom logic."
Create file: {custom_module_location}/{module_name}/\_module-installer/installer.js from {installerTemplate}
Update installer.js with module-specific logic
### 5. Create Assets Directory (if needed)
"**Installer Assets:**
If your module needs to copy files during installation (templates, examples, documentation), we can add them to the assets directory."
Create directory: \_module-installer/assets/
Add note about what assets to include
### 6. Document Installer Setup
Update module-plan.md with installer section:
```markdown
## Installer Configuration
### Install Configuration
- File: \_module-installer/install-config.yaml
- Module code: {module_name}
- Default selected: false
- Configuration fields: [count]
### Custom Logic
- installer.js: [Created/Not needed]
- Custom setup: [description if yes]
### Installation Process
1. User runs: `bmad install {module_name}`
2. Installer asks: [list of questions]
3. Creates: {bmad_folder}/{module_name}/
4. Generates: config.yaml with user settings
### Validation
- ✅ YAML syntax valid
- ✅ All fields defined
- ✅ Paths use proper templates
- ✅ Custom logic ready (if needed)
```
### 7. Present MENU OPTIONS
Display: **Select an Option:** [A] Advanced Elicitation [P] Party Mode [C] Continue
#### Menu Handling Logic:
- IF A: Execute {advancedElicitationTask} to review installer configuration
- IF P: Execute {partyModeWorkflow} to get input on user experience
- IF C: Save installer info to module-plan.md, add step-08-installer 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:
- install-config.yaml created with all planned fields
- YAML syntax valid
- Custom installation logic prepared (if needed)
- Installer follows BMAD standards
- Configuration properly templated
### ❌ SYSTEM FAILURE:
- Not creating install-config.yaml
- Invalid YAML syntax
- Missing required fields
- Not using proper path templates
**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 installer info is saved to module-plan.md with stepsCompleted updated to [1, 2, 3, 4, 5, 6, 7, 8], will you then load, read entire file, then execute `{nextStepFile}` to begin documentation creation.

Some files were not shown because too many files have changed in this diff Show More