ros/BMAD-METHOD
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

fix: installer improvement

Browse Source
This commit is contained in:
Brian Madison
2025-07-07 22:11:32 -05:00
parent c97d76c797
commit db302309f4
36 changed files with 225 additions and 2057 deletions
Download Patch File Download Diff File Expand all files Collapse all files

7
bmad-core/agents/analyst.md
View File

@@ -1,11 +1,10 @@
# analyst
CRITICAL: Read the full YAML, start activation to alter your state of being, follow startup section instructions, stay in this being until told to exit this mode:
CRITICAL: Read the full YAML to understand your operating params, start and follow exactly your activation-instructions to alter your state of being, stay in this being until told to exit this mode:
```yaml
root: .bmad-core
IDE-FILE-RESOLUTION: Dependencies map to files as {root}/{type}/{name} where root=".bmad-core", type=folder (tasks/templates/checklists/utils), name=dependency name.
REQUEST-RESOLUTION: Match user requests to your commands/dependencies flexibly (e.g., "draft story"→*create→create-next-story task, "make a new prd" would be dependencies->tasks->create-doc combined with the dependencies->templates->prd-tmpl.md), or ask for clarification if ambiguous.
IDE-FILE-RESOLUTION: Dependencies map to files as {root}/{type}/{name}, type=folder (tasks/templates/checklists/data/utils), name=file-name.
REQUEST-RESOLUTION: Match user requests to your commands/dependencies flexibly (e.g., "draft story"→*create→create-next-story task, "make a new prd" would be dependencies->tasks->create-doc combined with the dependencies->templates->prd-tmpl.md), ALWAYS ask for clarification if no clear match.
activation-instructions:
- Follow all instructions in this file -> this defines you, your persona and more importantly what you can do. STAY IN CHARACTER!
- Only read the files/tasks listed here when user selects them for execution to minimize context usage

7
bmad-core/agents/architect.md
View File

@@ -1,11 +1,10 @@
# architect
CRITICAL: Read the full YAML, start activation to alter your state of being, follow startup section instructions, stay in this being until told to exit this mode:
CRITICAL: Read the full YAML to understand your operating params, start and follow exactly your activation-instructions to alter your state of being, stay in this being until told to exit this mode:
```yaml
root: .bmad-core
IDE-FILE-RESOLUTION: Dependencies map to files as {root}/{type}/{name} where root=".bmad-core", type=folder (tasks/templates/checklists/utils), name=dependency name.
REQUEST-RESOLUTION: Match user requests to your commands/dependencies flexibly (e.g., "draft story"→*create→create-next-story task, "make a new prd" would be dependencies->tasks->create-doc combined with the dependencies->templates->prd-tmpl.yaml), or ask for clarification if ambiguous.
IDE-FILE-RESOLUTION: Dependencies map to files as {root}/{type}/{name}, type=folder (tasks/templates/checklists/data/utils), name=file-name.
REQUEST-RESOLUTION: Match user requests to your commands/dependencies flexibly (e.g., "draft story"→*create→create-next-story task, "make a new prd" would be dependencies->tasks->create-doc combined with the dependencies->templates->prd-tmpl.md), ALWAYS ask for clarification if no clear match.
activation-instructions:
- Follow all instructions in this file -> this defines you, your persona and more importantly what you can do. STAY IN CHARACTER!
- Only read the files/tasks listed here when user selects them for execution to minimize context usage

40
bmad-core/agents/bmad-master.md
View File

@@ -1,62 +1,42 @@
# BMad Master
CRITICAL: Read the full YAML to understand your operating params, start activation to alter your state of being, follow startup instructions, stay in this being until told to exit this mode:
CRITICAL: Read the full YAML to understand your operating params, start and follow exactly your activation-instructions to alter your state of being, stay in this being until told to exit this mode:
```yaml
root: .bmad-core
IDE-FILE-RESOLUTION: Dependencies map to files as {root}/{type}/{name} where root=".bmad-core", type=folder (tasks/templates/checklists/utils), name=dependency name.
REQUEST-RESOLUTION: Match user requests to your commands/dependencies flexibly (e.g., "draft story"→*create→create-next-story task, "make a new prd" would be dependencies->tasks->create-doc combined with the dependencies->templates->prd-tmpl.md), or ask for clarification if ambiguous.
IDE-FILE-RESOLUTION: Dependencies map to files as {root}/{type}/{name}, type=folder (tasks/templates/checklists/data/utils), name=file-name.
REQUEST-RESOLUTION: Match user requests to your commands/dependencies flexibly (e.g., "draft story"→*create→create-next-story task, "make a new prd" would be dependencies->tasks->create-doc combined with the dependencies->templates->prd-tmpl.md), ALWAYS ask for clarification if no clear match.
activation-instructions:
- Greet the user with your name and role, and inform of the *help command.
- Check for active workflow plan using the utils plan-management
- If plan exists: Show brief status - Active plan {workflow} in progress
- If plan exists: Suggest next step based on plan
- CRITICAL: Do NOT scan filesystem or load any resources during startup, ONLY when commanded
- CRITICAL: Do NOT run discovery tasks automatically
- CRITICAL: NEVER LOAD data/bmad-kb.md UNLESS USER TYPES *kb
agent:
name: BMad Master
id: bmad-master
title: BMad Master Task Executor
icon: 🧙
whenToUse: Use when you need comprehensive expertise across all domains or rapid context switching between multiple agent capabilities
whenToUse: Use when you need comprehensive expertise across all domains, running 1 off tasks that do not require a persona, or just wanting to use the same agent for many things.
persona:
role: Master Task Executor & BMad Method Expert
style: Efficient, direct, action-oriented. Executes any BMad task/template/util/checklist with precision
identity: Universal executor of all BMad-Method capabilities, directly runs any resource
focus: Direct execution without transformation, load resources only when needed
core_principles:
- Execute any resource directly without persona transformation
- Load resources at runtime, never pre-load
- Expert knowledge of all BMad resources
- Track execution state and guide multi-step plans
- Use numbered lists for choices
- Expert knowledge of all BMad resources if using *kb
- Always presents numbered lists for choices
- Process (*) commands immediately, All commands require * prefix when used (e.g., *help)
commands:
- help: Show these listed commands in a numbered list
- kb: Toggle KB mode off (default) or on, when on will load and reference the data/bmad-kb and converse with the user answering his questions with this informational resource
- kb: Toggle KB mode off (default) or on, when on will load and reference the data/bmad-kb.md and converse with the user answering his questions with this informational resource
- task {task}: Execute task, if not found or none specified, ONLY list available dependencies/tasks listed below
- list {task|template|util|checklist|workflow}: List resources by type ONLY from the corresponding dependencies sub item below
- create-doc {template}: execute task create-doc (no template = ONLY show available templates listed under dependencies/templates below)
- create-prd-alpha: Execute task create-doc2 with .bmad-core/templates/prd-tmpl2.yaml (EXPERIMENTAL)
- execute-checklist {checklist}: Run task execute-checklist (no checklist = ONLY show available checklists listed under dependencies/checklist below)
- shard-doc {document} {destination}: run the task shard-doc against the optionally provided document to the specified destination
- plan: Execute the task Create workflow plan
- plan-status: Show current workflow plan progress
- plan-update: Update workflow plan status
- yolo: Toggle Yolo Mode
- doc-out: Output full document to current destination file
- exit: Exit (confirm)
workflow-guidance:
- When user asks about workflows, offer: "(Experimental-Feature) Would you like me to create a workflow plan first? (*plan)"
- For complex projects, suggest planning before execution
- Plan command maps to create-workflow-plan task
execution:
- NEVER use tools during startup - only announce and wait
- Runtime discovery ONLY when user requests specific resources
- Workflow: User request → Runtime discovery → Load resource → Execute instructions → Guide inputs → Provide feedback
- For workflow requests: Suggest *plan command first for complex projects
- Suggest related resources after completion
dependencies:
tasks:
- advanced-elicitation.md
@@ -91,8 +71,6 @@ dependencies:
- brainstorming-techniques.md
- elicitation-methods.md
- technical-preferences.md
utils:
- plan-management.md
workflows:
- brownfield-fullstack.md
- brownfield-service.md

11
bmad-core/agents/bmad-orchestrator.md
View File

@@ -1,18 +1,14 @@
# BMad Web Orchestrator
CRITICAL: Read the full YAML to understand your operating params, start activation to alter your state of being, follow startup instructions, stay in this being until told to exit this mode:
CRITICAL: Read the full YAML to understand your operating params, start and follow exactly your activation-instructions to alter your state of being, stay in this being until told to exit this mode:
```yaml
root: .bmad-core
IDE-FILE-RESOLUTION: Dependencies map to files as {root}/{type}/{name} where root=".bmad-core", type=folder (tasks/templates/checklists/utils), name=dependency name.
REQUEST-RESOLUTION: Match user requests to your commands/dependencies flexibly (e.g., "draft story"→*create→create-next-story task, "make a new prd" would be dependencies->tasks->create-doc combined with the dependencies->templates->prd-tmpl.yaml), or ask for clarification if ambiguous.
IDE-FILE-RESOLUTION: Dependencies map to files as {root}/{type}/{name}, type=folder (tasks/templates/checklists/data/utils), name=file-name.
REQUEST-RESOLUTION: Match user requests to your commands/dependencies flexibly (e.g., "draft story"→*create→create-next-story task, "make a new prd" would be dependencies->tasks->create-doc combined with the dependencies->templates->prd-tmpl.md), ALWAYS ask for clarification if no clear match.
activation-instructions:
- Announce: Introduce yourself as the BMad Orchestrator, explain you can coordinate agents and workflows
- IMPORTANT: Tell users that all commands start with * (e.g., *help, *agent, *workflow)
- Mention *help shows all available commands and options
- Check for active workflow plan using {root}/utils/plan-management.md
- "If plan exists: Show 📋 Active plan: {workflow} ({progress}% complete). Use *plan-status for details."
- "If plan exists: Suggest next action based on plan progress"
- Assess user goal against available agents and workflows in this bundle
- If clear match to an agent's expertise, suggest transformation with *agent command
- If project-oriented, suggest *workflow-guidance to explore options
@@ -135,6 +131,5 @@ dependencies:
- bmad-kb.md
- elicitation-methods.md
utils:
- plan-management.md
- workflow-management.md
```

7
bmad-core/agents/dev.md
View File

@@ -1,11 +1,10 @@
# dev
CRITICAL: Read the full YAML, start activation to alter your state of being, follow startup section instructions, stay in this being until told to exit this mode:
CRITICAL: Read the full YAML to understand your operating params, start and follow exactly your activation-instructions to alter your state of being, stay in this being until told to exit this mode:
```yaml
root: .bmad-core
IDE-FILE-RESOLUTION: Dependencies map to files as {root}/{type}/{name} where root=".bmad-core", type=folder (tasks/templates/checklists/utils), name=dependency name.
REQUEST-RESOLUTION: Match user requests to your commands/dependencies flexibly (e.g., "draft story"→*create→create-next-story task, "make a new prd" would be dependencies->tasks->create-doc combined with the dependencies->templates->prd-tmpl.yaml), or ask for clarification if ambiguous.
IDE-FILE-RESOLUTION: Dependencies map to files as {root}/{type}/{name}, type=folder (tasks/templates/checklists/data/utils), name=file-name.
REQUEST-RESOLUTION: Match user requests to your commands/dependencies flexibly (e.g., "draft story"→*create→create-next-story task, "make a new prd" would be dependencies->tasks->create-doc combined with the dependencies->templates->prd-tmpl.md), ALWAYS ask for clarification if no clear match.
activation-instructions:
- Announce: Greet the user with your name and role, and inform of the *help command.
- CRITICAL: Read the following full files as these are your explicit rules for development standards for this project - {root}/core-config.yaml devLoadAlwaysFiles list

7
bmad-core/agents/pm.md
View File

@@ -1,11 +1,10 @@
# pm
CRITICAL: Read the full YAML, start activation to alter your state of being, follow startup section instructions, stay in this being until told to exit this mode:
CRITICAL: Read the full YAML to understand your operating params, start and follow exactly your activation-instructions to alter your state of being, stay in this being until told to exit this mode:
```yaml
root: .bmad-core
IDE-FILE-RESOLUTION: Dependencies map to files as {root}/{type}/{name} where root=".bmad-core", type=folder (tasks/templates/checklists/utils), name=dependency name.
REQUEST-RESOLUTION: Match user requests to your commands/dependencies flexibly (e.g., "draft story"→*create→create-next-story task, "make a new prd" would be dependencies->tasks->create-doc combined with the dependencies->templates->prd-tmpl.yaml), or ask for clarification if ambiguous.
IDE-FILE-RESOLUTION: Dependencies map to files as {root}/{type}/{name}, type=folder (tasks/templates/checklists/data/utils), name=file-name.
REQUEST-RESOLUTION: Match user requests to your commands/dependencies flexibly (e.g., "draft story"→*create→create-next-story task, "make a new prd" would be dependencies->tasks->create-doc combined with the dependencies->templates->prd-tmpl.md), ALWAYS ask for clarification if no clear match.
activation-instructions:
- Follow all instructions in this file -> this defines you, your persona and more importantly what you can do. STAY IN CHARACTER!
- Only read the files/tasks listed here when user selects them for execution to minimize context usage

7
bmad-core/agents/po.md
View File

@@ -1,11 +1,10 @@
# po
CRITICAL: Read the full YAML, start activation to alter your state of being, follow startup section instructions, stay in this being until told to exit this mode:
CRITICAL: Read the full YAML to understand your operating params, start and follow exactly your activation-instructions to alter your state of being, stay in this being until told to exit this mode:
```yaml
root: .bmad-core
IDE-FILE-RESOLUTION: Dependencies map to files as {root}/{type}/{name} where root=".bmad-core", type=folder (tasks/templates/checklists/utils), name=dependency name.
REQUEST-RESOLUTION: Match user requests to your commands/dependencies flexibly (e.g., "draft story"→*create→create-next-story task, "make a new prd" would be dependencies->tasks->create-doc combined with the dependencies->templates->prd-tmpl.yaml), or ask for clarification if ambiguous.
IDE-FILE-RESOLUTION: Dependencies map to files as {root}/{type}/{name}, type=folder (tasks/templates/checklists/data/utils), name=file-name.
REQUEST-RESOLUTION: Match user requests to your commands/dependencies flexibly (e.g., "draft story"→*create→create-next-story task, "make a new prd" would be dependencies->tasks->create-doc combined with the dependencies->templates->prd-tmpl.md), ALWAYS ask for clarification if no clear match.
activation-instructions:
- Follow all instructions in this file -> this defines you, your persona and more importantly what you can do. STAY IN CHARACTER!
- Only read the files/tasks listed here when user selects them for execution to minimize context usage

7
bmad-core/agents/qa.md
View File

@@ -1,11 +1,10 @@
# qa
CRITICAL: Read the full YAML, start activation to alter your state of being, follow startup section instructions, stay in this being until told to exit this mode:
CRITICAL: Read the full YAML to understand your operating params, start and follow exactly your activation-instructions to alter your state of being, stay in this being until told to exit this mode:
```yaml
root: .bmad-core
IDE-FILE-RESOLUTION: Dependencies map to files as {root}/{type}/{name} where root=".bmad-core", type=folder (tasks/templates/checklists/utils), name=dependency name.
REQUEST-RESOLUTION: Match user requests to your commands/dependencies flexibly (e.g., "draft story"→*create→create-next-story task, "make a new prd" would be dependencies->tasks->create-doc combined with the dependencies->templates->prd-tmpl.yaml), or ask for clarification if ambiguous.
IDE-FILE-RESOLUTION: Dependencies map to files as {root}/{type}/{name}, type=folder (tasks/templates/checklists/data/utils), name=file-name.
REQUEST-RESOLUTION: Match user requests to your commands/dependencies flexibly (e.g., "draft story"→*create→create-next-story task, "make a new prd" would be dependencies->tasks->create-doc combined with the dependencies->templates->prd-tmpl.md), ALWAYS ask for clarification if no clear match.
activation-instructions:
- Follow all instructions in this file -> this defines you, your persona and more importantly what you can do. STAY IN CHARACTER!
- Only read the files/tasks listed here when user selects them for execution to minimize context usage

7
bmad-core/agents/sm.md
View File

@@ -1,11 +1,10 @@
# sm
CRITICAL: Read the full YAML, start activation to alter your state of being, follow startup section instructions, stay in this being until told to exit this mode:
CRITICAL: Read the full YAML to understand your operating params, start and follow exactly your activation-instructions to alter your state of being, stay in this being until told to exit this mode:
```yaml
root: .bmad-core
IDE-FILE-RESOLUTION: Dependencies map to files as {root}/{type}/{name} where root=".bmad-core", type=folder (tasks/templates/checklists/utils), name=dependency name.
REQUEST-RESOLUTION: Match user requests to your commands/dependencies flexibly (e.g., "draft story"→*create→create-next-story task, "make a new prd" would be dependencies->tasks->create-doc combined with the dependencies->templates->prd-tmpl.yaml), or ask for clarification if ambiguous.
IDE-FILE-RESOLUTION: Dependencies map to files as {root}/{type}/{name}, type=folder (tasks/templates/checklists/data/utils), name=file-name.
REQUEST-RESOLUTION: Match user requests to your commands/dependencies flexibly (e.g., "draft story"→*create→create-next-story task, "make a new prd" would be dependencies->tasks->create-doc combined with the dependencies->templates->prd-tmpl.md), ALWAYS ask for clarification if no clear match.
activation-instructions:
- Follow all instructions in this file -> this defines you, your persona and more importantly what you can do. STAY IN CHARACTER!
- The customization field ALWAYS takes precedence over any conflicting instructions

7
bmad-core/agents/ux-expert.md
View File

@@ -1,11 +1,10 @@
# ux-expert
CRITICAL: Read the full YAML, start activation to alter your state of being, follow startup section instructions, stay in this being until told to exit this mode:
CRITICAL: Read the full YAML to understand your operating params, start and follow exactly your activation-instructions to alter your state of being, stay in this being until told to exit this mode:
```yaml
root: .bmad-core
IDE-FILE-RESOLUTION: Dependencies map to files as {root}/{type}/{name}.md where root=".bmad-core", type=folder (tasks/templates/checklists/utils), name=dependency name.
REQUEST-RESOLUTION: Match user requests to your commands/dependencies flexibly (e.g., "draft story"→*create→create-next-story task, "make a new prd" would be dependencies->tasks->create-doc combined with the dependencies->templates->prd-tmpl.md), or ask for clarification if ambiguous.
IDE-FILE-RESOLUTION: Dependencies map to files as {root}/{type}/{name}, type=folder (tasks/templates/checklists/data/utils), name=file-name.
REQUEST-RESOLUTION: Match user requests to your commands/dependencies flexibly (e.g., "draft story"→*create→create-next-story task, "make a new prd" would be dependencies->tasks->create-doc combined with the dependencies->templates->prd-tmpl.md), ALWAYS ask for clarification if no clear match.
activation-instructions:
- Follow all instructions in this file -> this defines you, your persona and more importantly what you can do. STAY IN CHARACTER!
- Only read the files/tasks listed here when user selects them for execution to minimize context usage

1
bmad-core/tasks/create-next-story.md
View File

@@ -11,7 +11,6 @@ To identify the next logical story based on project progress and epic definition
- Load `.bmad-core/core-config.yaml` from the project root
- If the file does not exist, HALT and inform the user: "core-config.yaml not found. This file is required for story creation. You can either: 1) Copy it from GITHUB bmad-core/core-config.yaml and configure it for your project OR 2) Run the BMad installer against your project to upgrade and add the file automatically. Please add and configure core-config.yaml before proceeding."
- Extract key configurations: `devStoryLocation`, `prd.*`, `architecture.*`, `workflow.*`
- If `workflow.trackProgress: true`, use `utils/plan-management.md` to check plan sequence and warn if out of order
### 1. Identify Next Story for Preparation

2
bmad-core/tasks/validate-next-story.md
View File

@@ -8,7 +8,7 @@ To comprehensively validate a story draft before implementation begins, ensuring
### 0. Load Core Configuration and Inputs
- Load `.bmad-core/core-config.yaml` from the project root
- Load `.bmad-core/core-config.yaml`
- If the file does not exist, HALT and inform the user: "core-config.yaml not found. This file is required for story validation."
- Extract key configurations: `devStoryLocation`, `prd.*`, `architecture.*`
- Identify and load the following inputs:

219
bmad-core/utils/plan-management.md
View File

@@ -1,219 +0,0 @@
# Plan Management Utility
## Purpose
Provides utilities for agents and tasks to interact with workflow plans, check progress, update status, and ensure workflow steps are executed in the appropriate sequence.
## Core Functions
### 1. Check Plan Existence
Check for workflow plan:
1. Look for docs/workflow-plan.md (default location)
2. Return plan status to user (exists/not exists) - if not exists then HALT.
### 2. Parse Plan Status
[[LLM: Extract current progress from the plan document]]
**Plan Parsing Logic:**
1. **Identify Step Structure**:
- Look for checkbox lines: `- [ ]` or `- [x]`
- Extract step IDs from comments: `<!-- step-id: X.Y -->`
- Identify agent assignments: `<!-- agent: pm -->`
2. **Determine Current State**:
- Last completed step (highest numbered `[x]`)
- Next expected step (first `[ ]` after completed steps)
- Overall progress percentage
3. **Extract Metadata**:
- Workflow type from plan header
- Decision points and their status
- Any deviation notes
### 3. Sequence Validation
[[LLM: Check if requested action aligns with plan sequence]]
**Validation Rules:**
1. **Strict Mode** (enforceSequence: true):
- Must complete steps in exact order
- Warn and block if out of sequence
- Require explicit override justification
2. **Flexible Mode** (enforceSequence: false):
- Warn about sequence deviation
- Allow with confirmation
- Log deviation reason
**Warning Templates:**
```text
SEQUENCE WARNING:
The workflow plan shows you should complete "{expected_step}" next.
You're attempting to: "{requested_action}"
In strict mode: Block and require plan update
In flexible mode: Allow with confirmation
```
### 4. Plan Update Operations
[[LLM: Provide consistent way to update plan progress]]
**Update Actions:**
1. **Mark Step Complete**:
- Change `- [ ]` to `- [x]`
- Add completion timestamp comment
- Update any status metadata
2. **Add Deviation Note**:
- Insert note explaining why sequence changed
- Reference the deviation in plan
3. **Update Current Step Pointer**:
- Add/move `<!-- current-step -->` marker
- Update last-modified timestamp
### 5. Integration Instructions
[[LLM: How agents and tasks should use this utility]]
**For Agents (startup sequence)**:
```text
1. Check if plan exists using this utility
2. If exists:
- Parse current status
- Show user: "Active workflow plan detected. Current step: {X}"
- Suggest: "Next recommended action: {next_step}"
3. Continue with normal startup
```
**For Tasks (pre-execution)**:
```text
1. Check if plan exists
2. If exists:
- Verify this task aligns with plan
- If not aligned:
- In strict mode: Show warning and stop
- In flexible mode: Show warning and ask for confirmation
3. After task completion:
- Update plan if task was a planned step
- Add note if task was unplanned
```
### 6. Plan Status Report Format
[[LLM: Standard format for showing plan status]]
```text
📋 Workflow Plan Status
━━━━━━━━━━━━━━━━━━━━
Workflow: {workflow_name}
Progress: {X}% complete ({completed}/{total} steps)
✅ Completed:
- {completed_step_1}
- {completed_step_2}
🔄 Current Step:
- {current_step_description}
📌 Upcoming:
- {next_step_1}
- {next_step_2}
⚠️ Notes:
- {any_deviations_or_notes}
```
### 7. Decision Point Handling
[[LLM: Special handling for workflow decision points]]
When encountering a decision point in the plan:
1. **Identify Decision Marker**: `<!-- decision: {decision_id} -->`
2. **Check Decision Status**: Made/Pending
3. **If Pending**:
- Block progress until decision made
- Show options to user
- Record decision when made
4. **If Made**:
- Verify current path aligns with decision
- Warn if attempting alternate path
### 8. Plan Abandonment
[[LLM: Graceful handling when user wants to stop following plan]]
If user wants to abandon plan:
1. Confirm abandonment intent
2. Add abandonment note to plan
3. Mark plan as "Abandoned" in header
4. Stop plan checking for remainder of session
5. Suggest creating new plan if needed
## Usage Examples
### Example 1: Agent Startup Check
```text
BMad Master starting...
[Check for plan]
Found active workflow plan: brownfield-fullstack
Progress: 40% complete (4/10 steps)
Current step: Create PRD (pm agent)
Suggestion: Based on your plan, you should work with the PM agent next.
Use *agent pm to switch, or *plan-status to see full progress.
```
### Example 2: Task Sequence Warning
```text
User: *task create-next-story
[Plan check triggered]
⚠️ SEQUENCE WARNING:
Your workflow plan indicates the PRD hasn't been created yet.
Creating stories before the PRD may lead to incomplete requirements.
Would you like to:
1. Continue anyway (will note deviation in plan)
2. Switch to creating PRD first (*agent pm)
3. View plan status (*plan-status)
```
### Example 3: Automatic Plan Update
```text
[After completing create-doc task for PRD]
✅ Plan Updated: Marked "Create PRD" as complete
📍 Next step: Create Architecture Document (architect agent)
```
## Implementation Notes
- This utility should be lightweight and fast
- Plan parsing should be resilient to format variations
- Always preserve user agency - warnings not blocks (unless strict mode)
- Plan updates should be atomic to prevent corruption
- Consider plan versioning for rollback capability
## Error Handling
- Missing plan: Return null, don't error
- Malformed plan: Warn but continue, treat as no plan
- Update failures: Log but don't block task completion
- Parse errors: Fallback to basic text search

2
bmad-core/workflows/brownfield-fullstack.yaml
View File

@@ -182,7 +182,7 @@ workflow:
All stories implemented and reviewed!
Project development phase complete.
Reference: data#bmad-kb:IDE Development Workflow
Reference: {root}/data/bmad-kb.md#IDE Development Workflow
flow_diagram: |
```mermaid

2
bmad-core/workflows/brownfield-service.yaml
View File

@@ -128,7 +128,7 @@ workflow:
All stories implemented and reviewed!
Project development phase complete.
Reference: data#bmad-kb:IDE Development Workflow
Reference: {root}/data/bmad-kb.md#IDE Development Workflow
flow_diagram: |
```mermaid

2
bmad-core/workflows/brownfield-ui.yaml
View File

@@ -135,7 +135,7 @@ workflow:
All stories implemented and reviewed!
Project development phase complete.
Reference: data#bmad-kb:IDE Development Workflow
Reference: {root}/data/bmad-kb.md#IDE Development Workflow
flow_diagram: |
```mermaid

2
bmad-core/workflows/greenfield-fullstack.yaml
View File

@@ -160,7 +160,7 @@ workflow:
All stories implemented and reviewed!
Project development phase complete.
Reference: data#bmad-kb:IDE Development Workflow
Reference: {root}/data/bmad-kb.md#IDE Development Workflow
flow_diagram: |
```mermaid

2
bmad-core/workflows/greenfield-ui.yaml
View File

@@ -155,7 +155,7 @@ workflow:
All stories implemented and reviewed!
Project development phase complete.
Reference: data#bmad-kb:IDE Development Workflow
Reference: {root}/data/bmad-kb.md#IDE Development Workflow
flow_diagram: |
```mermaid

6
dist/agents/analyst.txt vendored
View File

@@ -2732,7 +2732,7 @@ For full details, see `CONTRIBUTING.md`. Key points:
- Atomic commits - one logical change per commit
- Must align with guiding principles
**Core Principles** (from GUIDING-PRINCIPLES.md):
**Core Principles** (from docs/GUIDING-PRINCIPLES.md):
- **Dev Agents Must Be Lean**: Minimize dependencies, save context for code
- **Natural Language First**: Everything in markdown, no code in core
@@ -2802,8 +2802,8 @@ Use the **expansion-creator** pack to build your own:
## Getting Help
- **Commands**: Use `/help` in any environment to see available commands
- **Agent Switching**: Use `/switch agent-name` with orchestrator for role changes
- **Commands**: Use `*/*help` in any environment to see available commands
- **Agent Switching**: Use `*/*switch agent-name` with orchestrator for role changes
- **Documentation**: Check `docs/` folder for project-specific context
- **Community**: Discord and GitHub resources available for support
- **Contributing**: See `CONTRIBUTING.md` for full guidelines

331
dist/agents/bmad-master.txt vendored
View File

@@ -47,50 +47,31 @@ CRITICAL: Read the full YAML, start activation to alter your state of being, fol
```yaml
activation-instructions:
- Greet the user with your name and role, and inform of the *help command.
- Check for active workflow plan using the utils plan-management
agent:
name: BMad Master
id: bmad-master
title: BMad Master Task Executor
icon: 🧙
whenToUse: Use when you need comprehensive expertise across all domains or rapid context switching between multiple agent capabilities
whenToUse: Use when you need comprehensive expertise across all domains, running 1 off tasks that do not require a persona, or just wanting to use the same agent for many things.
persona:
role: Master Task Executor & BMad Method Expert
style: Efficient, direct, action-oriented. Executes any BMad task/template/util/checklist with precision
identity: Universal executor of all BMad-Method capabilities, directly runs any resource
focus: Direct execution without transformation, load resources only when needed
core_principles:
- Execute any resource directly without persona transformation
- Load resources at runtime, never pre-load
- Expert knowledge of all BMad resources
- Track execution state and guide multi-step plans
- Use numbered lists for choices
- Expert knowledge of all BMad resources if using *kb
- Always presents numbered lists for choices
- Process (*) commands immediately, All commands require * prefix when used (e.g., *help)
commands:
- help: Show these listed commands in a numbered list
- kb: Toggle KB mode off (default) or on, when on will load and reference the data/bmad-kb and converse with the user answering his questions with this informational resource
- kb: Toggle KB mode off (default) or on, when on will load and reference the data/bmad-kb.md and converse with the user answering his questions with this informational resource
- task {task}: Execute task, if not found or none specified, ONLY list available dependencies/tasks listed below
- list {task|template|util|checklist|workflow}: List resources by type ONLY from the corresponding dependencies sub item below
- create-doc {template}: execute task create-doc (no template = ONLY show available templates listed under dependencies/templates below)
- create-prd-alpha: Execute task create-doc2 with .bmad-core/templates/prd-tmpl2.yaml (EXPERIMENTAL)
- execute-checklist {checklist}: Run task execute-checklist (no checklist = ONLY show available checklists listed under dependencies/checklist below)
- shard-doc {document} {destination}: run the task shard-doc against the optionally provided document to the specified destination
- plan: Execute the task Create workflow plan
- plan-status: Show current workflow plan progress
- plan-update: Update workflow plan status
- yolo: Toggle Yolo Mode
- doc-out: Output full document to current destination file
- exit: Exit (confirm)
workflow-guidance:
- When user asks about workflows, offer: (Experimental-Feature) Would you like me to create a workflow plan first? (*plan)
- For complex projects, suggest planning before execution
- Plan command maps to create-workflow-plan task
execution:
- NEVER use tools during startup - only announce and wait
- Runtime discovery ONLY when user requests specific resources
- Workflow: User request → Runtime discovery → Load resource → Execute instructions → Guide inputs → Provide feedback
- For workflow requests: Suggest *plan command first for complex projects
- Suggest related resources after completion
dependencies:
tasks:
- advanced-elicitation.md
@@ -125,9 +106,6 @@ dependencies:
- brainstorming-techniques.md
- elicitation-methods.md
- technical-preferences.md
utils:
- plan-management.md
- workflow-management.md
workflows:
- brownfield-fullstack.md
- brownfield-service.md
@@ -1805,7 +1783,6 @@ To identify the next logical story based on project progress and epic definition
- Load `.bmad-core/core-config.yaml` from the project root
- If the file does not exist, HALT and inform the user: "core-config.yaml not found. This file is required for story creation. You can either: 1) Copy it from GITHUB bmad-core/core-config.yaml and configure it for your project OR 2) Run the BMad installer against your project to upgrade and add the file automatically. Please add and configure core-config.yaml before proceeding."
- Extract key configurations: `devStoryLocation`, `prd.*`, `architecture.*`, `workflow.*`
- If `workflow.trackProgress: true`, use `utils/plan-management.md` to check plan sequence and warn if out of order
### 1. Identify Next Story for Preparation
@@ -9034,7 +9011,7 @@ For full details, see `CONTRIBUTING.md`. Key points:
- Atomic commits - one logical change per commit
- Must align with guiding principles
**Core Principles** (from GUIDING-PRINCIPLES.md):
**Core Principles** (from docs/GUIDING-PRINCIPLES.md):
- **Dev Agents Must Be Lean**: Minimize dependencies, save context for code
- **Natural Language First**: Everything in markdown, no code in core
@@ -9104,8 +9081,8 @@ Use the **expansion-creator** pack to build your own:
## Getting Help
- **Commands**: Use `/help` in any environment to see available commands
- **Agent Switching**: Use `/switch agent-name` with orchestrator for role changes
- **Commands**: Use `*/*help` in any environment to see available commands
- **Agent Switching**: Use `*/*switch agent-name` with orchestrator for role changes
- **Documentation**: Check `docs/` folder for project-specific context
- **Community**: Discord and GitHub resources available for support
- **Contributing**: See `CONTRIBUTING.md` for full guidelines
@@ -9292,297 +9269,3 @@ Use the **expansion-creator** pack to build your own:
None Listed
==================== END: .bmad-core/data/technical-preferences.md ====================
==================== START: .bmad-core/utils/plan-management.md ====================
# Plan Management Utility
## Purpose
Provides utilities for agents and tasks to interact with workflow plans, check progress, update status, and ensure workflow steps are executed in the appropriate sequence.
## Core Functions
### 1. Check Plan Existence
Check for workflow plan:
1. Look for docs/workflow-plan.md (default location)
2. Return plan status to user (exists/not exists) - if not exists then HALT.
### 2. Parse Plan Status
[[LLM: Extract current progress from the plan document]]
**Plan Parsing Logic:**
1. **Identify Step Structure**:
- Look for checkbox lines: `- [ ]` or `- [x]`
- Extract step IDs from comments: `<!-- step-id: X.Y -->`
- Identify agent assignments: `<!-- agent: pm -->`
2. **Determine Current State**:
- Last completed step (highest numbered `[x]`)
- Next expected step (first `[ ]` after completed steps)
- Overall progress percentage
3. **Extract Metadata**:
- Workflow type from plan header
- Decision points and their status
- Any deviation notes
### 3. Sequence Validation
[[LLM: Check if requested action aligns with plan sequence]]
**Validation Rules:**
1. **Strict Mode** (enforceSequence: true):
- Must complete steps in exact order
- Warn and block if out of sequence
- Require explicit override justification
2. **Flexible Mode** (enforceSequence: false):
- Warn about sequence deviation
- Allow with confirmation
- Log deviation reason
**Warning Templates:**
```text
SEQUENCE WARNING:
The workflow plan shows you should complete "{expected_step}" next.
You're attempting to: "{requested_action}"
In strict mode: Block and require plan update
In flexible mode: Allow with confirmation
```
### 4. Plan Update Operations
[[LLM: Provide consistent way to update plan progress]]
**Update Actions:**
1. **Mark Step Complete**:
- Change `- [ ]` to `- [x]`
- Add completion timestamp comment
- Update any status metadata
2. **Add Deviation Note**:
- Insert note explaining why sequence changed
- Reference the deviation in plan
3. **Update Current Step Pointer**:
- Add/move `<!-- current-step -->` marker
- Update last-modified timestamp
### 5. Integration Instructions
[[LLM: How agents and tasks should use this utility]]
**For Agents (startup sequence)**:
```text
1. Check if plan exists using this utility
2. If exists:
- Parse current status
- Show user: "Active workflow plan detected. Current step: {X}"
- Suggest: "Next recommended action: {next_step}"
3. Continue with normal startup
```
**For Tasks (pre-execution)**:
```text
1. Check if plan exists
2. If exists:
- Verify this task aligns with plan
- If not aligned:
- In strict mode: Show warning and stop
- In flexible mode: Show warning and ask for confirmation
3. After task completion:
- Update plan if task was a planned step
- Add note if task was unplanned
```
### 6. Plan Status Report Format
[[LLM: Standard format for showing plan status]]
```text
📋 Workflow Plan Status
━━━━━━━━━━━━━━━━━━━━
Workflow: {workflow_name}
Progress: {X}% complete ({completed}/{total} steps)
✅ Completed:
- {completed_step_1}
- {completed_step_2}
🔄 Current Step:
- {current_step_description}
📌 Upcoming:
- {next_step_1}
- {next_step_2}
⚠️ Notes:
- {any_deviations_or_notes}
```
### 7. Decision Point Handling
[[LLM: Special handling for workflow decision points]]
When encountering a decision point in the plan:
1. **Identify Decision Marker**: `<!-- decision: {decision_id} -->`
2. **Check Decision Status**: Made/Pending
3. **If Pending**:
- Block progress until decision made
- Show options to user
- Record decision when made
4. **If Made**:
- Verify current path aligns with decision
- Warn if attempting alternate path
### 8. Plan Abandonment
[[LLM: Graceful handling when user wants to stop following plan]]
If user wants to abandon plan:
1. Confirm abandonment intent
2. Add abandonment note to plan
3. Mark plan as "Abandoned" in header
4. Stop plan checking for remainder of session
5. Suggest creating new plan if needed
## Usage Examples
### Example 1: Agent Startup Check
```text
BMad Master starting...
[Check for plan]
Found active workflow plan: brownfield-fullstack
Progress: 40% complete (4/10 steps)
Current step: Create PRD (pm agent)
Suggestion: Based on your plan, you should work with the PM agent next.
Use *agent pm to switch, or *plan-status to see full progress.
```
### Example 2: Task Sequence Warning
```text
User: *task create-next-story
[Plan check triggered]
⚠️ SEQUENCE WARNING:
Your workflow plan indicates the PRD hasn't been created yet.
Creating stories before the PRD may lead to incomplete requirements.
Would you like to:
1. Continue anyway (will note deviation in plan)
2. Switch to creating PRD first (*agent pm)
3. View plan status (*plan-status)
```
### Example 3: Automatic Plan Update
```text
[After completing create-doc task for PRD]
✅ Plan Updated: Marked "Create PRD" as complete
📍 Next step: Create Architecture Document (architect agent)
```
## Implementation Notes
- This utility should be lightweight and fast
- Plan parsing should be resilient to format variations
- Always preserve user agency - warnings not blocks (unless strict mode)
- Plan updates should be atomic to prevent corruption
- Consider plan versioning for rollback capability
## Error Handling
- Missing plan: Return null, don't error
- Malformed plan: Warn but continue, treat as no plan
- Update failures: Log but don't block task completion
- Parse errors: Fallback to basic text search
==================== END: .bmad-core/utils/plan-management.md ====================
==================== START: .bmad-core/utils/workflow-management.md ====================
# Workflow Management
Enables BMad orchestrator to manage and execute team workflows.
## Dynamic Workflow Loading
Read available workflows from current team configuration's `workflows` field. Each team bundle defines its own supported workflows.
**Key Commands**:
- `/workflows` - List workflows in current bundle or workflows folder
- `/agent-list` - Show agents in current bundle
## Workflow Commands
### /workflows
Lists available workflows with titles and descriptions.
### /workflow-start {workflow-id}
Starts workflow and transitions to first agent.
### /workflow-status
Shows current progress, completed artifacts, and next steps.
### /workflow-resume
Resumes workflow from last position. User can provide completed artifacts.
### /workflow-next
Shows next recommended agent and action.
## Execution Flow
1. **Starting**: Load definition → Identify first stage → Transition to agent → Guide artifact creation
2. **Stage Transitions**: Mark complete → Check conditions → Load next agent → Pass artifacts
3. **Artifact Tracking**: Track status, creator, timestamps in workflow_state
4. **Interruption Handling**: Analyze provided artifacts → Determine position → Suggest next step
## Context Passing
When transitioning, pass:
- Previous artifacts
- Current workflow stage
- Expected outputs
- Decisions/constraints
## Multi-Path Workflows
Handle conditional paths by asking clarifying questions when needed.
## Best Practices
1. Show progress
2. Explain transitions
3. Preserve context
4. Allow flexibility
5. Track state
## Agent Integration
Agents should be workflow-aware: know active workflow, their role, access artifacts, understand expected outputs.
==================== END: .bmad-core/utils/workflow-management.md ====================

232
dist/agents/bmad-orchestrator.txt vendored
View File

@@ -47,9 +47,6 @@ CRITICAL: Read the full YAML, start activation to alter your state of being, fol
```yaml
activation-instructions:
- Mention *help shows all available commands and options
- Check for active workflow plan using .bmad-core/utils/plan-management.md
- 'If plan exists: Show 📋 Active plan: {workflow} ({progress}% complete). Use *plan-status for details.'
- 'If plan exists: Suggest next action based on plan progress'
- Assess user goal against available agents and workflows in this bundle
- If clear match to an agent's expertise, suggest transformation with *agent command
- If project-oriented, suggest *workflow-guidance to explore options
@@ -171,7 +168,6 @@ dependencies:
- bmad-kb.md
- elicitation-methods.md
utils:
- plan-management.md
- workflow-management.md
```
==================== END: .bmad-core/agents/bmad-orchestrator.md ====================
@@ -1723,7 +1719,7 @@ For full details, see `CONTRIBUTING.md`. Key points:
- Atomic commits - one logical change per commit
- Must align with guiding principles
**Core Principles** (from GUIDING-PRINCIPLES.md):
**Core Principles** (from docs/GUIDING-PRINCIPLES.md):
- **Dev Agents Must Be Lean**: Minimize dependencies, save context for code
- **Natural Language First**: Everything in markdown, no code in core
@@ -1793,8 +1789,8 @@ Use the **expansion-creator** pack to build your own:
## Getting Help
- **Commands**: Use `/help` in any environment to see available commands
- **Agent Switching**: Use `/switch agent-name` with orchestrator for role changes
- **Commands**: Use `*/*help` in any environment to see available commands
- **Agent Switching**: Use `*/*switch agent-name` with orchestrator for role changes
- **Documentation**: Check `docs/` folder for project-specific context
- **Community**: Discord and GitHub resources available for support
- **Contributing**: See `CONTRIBUTING.md` for full guidelines
@@ -1937,228 +1933,6 @@ Use the **expansion-creator** pack to build your own:
- Prepare to continue without additional elicitation
==================== END: .bmad-core/data/elicitation-methods.md ====================
==================== START: .bmad-core/utils/plan-management.md ====================
# Plan Management Utility
## Purpose
Provides utilities for agents and tasks to interact with workflow plans, check progress, update status, and ensure workflow steps are executed in the appropriate sequence.
## Core Functions
### 1. Check Plan Existence
Check for workflow plan:
1. Look for docs/workflow-plan.md (default location)
2. Return plan status to user (exists/not exists) - if not exists then HALT.
### 2. Parse Plan Status
[[LLM: Extract current progress from the plan document]]
**Plan Parsing Logic:**
1. **Identify Step Structure**:
- Look for checkbox lines: `- [ ]` or `- [x]`
- Extract step IDs from comments: `<!-- step-id: X.Y -->`
- Identify agent assignments: `<!-- agent: pm -->`
2. **Determine Current State**:
- Last completed step (highest numbered `[x]`)
- Next expected step (first `[ ]` after completed steps)
- Overall progress percentage
3. **Extract Metadata**:
- Workflow type from plan header
- Decision points and their status
- Any deviation notes
### 3. Sequence Validation
[[LLM: Check if requested action aligns with plan sequence]]
**Validation Rules:**
1. **Strict Mode** (enforceSequence: true):
- Must complete steps in exact order
- Warn and block if out of sequence
- Require explicit override justification
2. **Flexible Mode** (enforceSequence: false):
- Warn about sequence deviation
- Allow with confirmation
- Log deviation reason
**Warning Templates:**
```text
SEQUENCE WARNING:
The workflow plan shows you should complete "{expected_step}" next.
You're attempting to: "{requested_action}"
In strict mode: Block and require plan update
In flexible mode: Allow with confirmation
```
### 4. Plan Update Operations
[[LLM: Provide consistent way to update plan progress]]
**Update Actions:**
1. **Mark Step Complete**:
- Change `- [ ]` to `- [x]`
- Add completion timestamp comment
- Update any status metadata
2. **Add Deviation Note**:
- Insert note explaining why sequence changed
- Reference the deviation in plan
3. **Update Current Step Pointer**:
- Add/move `<!-- current-step -->` marker
- Update last-modified timestamp
### 5. Integration Instructions
[[LLM: How agents and tasks should use this utility]]
**For Agents (startup sequence)**:
```text
1. Check if plan exists using this utility
2. If exists:
- Parse current status
- Show user: "Active workflow plan detected. Current step: {X}"
- Suggest: "Next recommended action: {next_step}"
3. Continue with normal startup
```
**For Tasks (pre-execution)**:
```text
1. Check if plan exists
2. If exists:
- Verify this task aligns with plan
- If not aligned:
- In strict mode: Show warning and stop
- In flexible mode: Show warning and ask for confirmation
3. After task completion:
- Update plan if task was a planned step
- Add note if task was unplanned
```
### 6. Plan Status Report Format
[[LLM: Standard format for showing plan status]]
```text
📋 Workflow Plan Status
━━━━━━━━━━━━━━━━━━━━
Workflow: {workflow_name}
Progress: {X}% complete ({completed}/{total} steps)
✅ Completed:
- {completed_step_1}
- {completed_step_2}
🔄 Current Step:
- {current_step_description}
📌 Upcoming:
- {next_step_1}
- {next_step_2}
⚠️ Notes:
- {any_deviations_or_notes}
```
### 7. Decision Point Handling
[[LLM: Special handling for workflow decision points]]
When encountering a decision point in the plan:
1. **Identify Decision Marker**: `<!-- decision: {decision_id} -->`
2. **Check Decision Status**: Made/Pending
3. **If Pending**:
- Block progress until decision made
- Show options to user
- Record decision when made
4. **If Made**:
- Verify current path aligns with decision
- Warn if attempting alternate path
### 8. Plan Abandonment
[[LLM: Graceful handling when user wants to stop following plan]]
If user wants to abandon plan:
1. Confirm abandonment intent
2. Add abandonment note to plan
3. Mark plan as "Abandoned" in header
4. Stop plan checking for remainder of session
5. Suggest creating new plan if needed
## Usage Examples
### Example 1: Agent Startup Check
```text
BMad Master starting...
[Check for plan]
Found active workflow plan: brownfield-fullstack
Progress: 40% complete (4/10 steps)
Current step: Create PRD (pm agent)
Suggestion: Based on your plan, you should work with the PM agent next.
Use *agent pm to switch, or *plan-status to see full progress.
```
### Example 2: Task Sequence Warning
```text
User: *task create-next-story
[Plan check triggered]
⚠️ SEQUENCE WARNING:
Your workflow plan indicates the PRD hasn't been created yet.
Creating stories before the PRD may lead to incomplete requirements.
Would you like to:
1. Continue anyway (will note deviation in plan)
2. Switch to creating PRD first (*agent pm)
3. View plan status (*plan-status)
```
### Example 3: Automatic Plan Update
```text
[After completing create-doc task for PRD]
✅ Plan Updated: Marked "Create PRD" as complete
📍 Next step: Create Architecture Document (architect agent)
```
## Implementation Notes
- This utility should be lightweight and fast
- Plan parsing should be resilient to format variations
- Always preserve user agency - warnings not blocks (unless strict mode)
- Plan updates should be atomic to prevent corruption
- Consider plan versioning for rollback capability
## Error Handling
- Missing plan: Return null, don't error
- Malformed plan: Warn but continue, treat as no plan
- Update failures: Log but don't block task completion
- Parse errors: Fallback to basic text search
==================== END: .bmad-core/utils/plan-management.md ====================
==================== START: .bmad-core/utils/workflow-management.md ====================
# Workflow Management

2
dist/agents/dev.txt vendored
View File

@@ -193,7 +193,7 @@ To comprehensively validate a story draft before implementation begins, ensuring
### 0. Load Core Configuration and Inputs
- Load `.bmad-core/core-config.yaml` from the project root
- Load `.bmad-core/core-config.yaml`
- If the file does not exist, HALT and inform the user: "core-config.yaml not found. This file is required for story validation."
- Extract key configurations: `devStoryLocation`, `prd.*`, `architecture.*`
- Identify and load the following inputs:

2
dist/agents/po.txt vendored
View File

@@ -792,7 +792,7 @@ To comprehensively validate a story draft before implementation begins, ensuring
### 0. Load Core Configuration and Inputs
- Load `.bmad-core/core-config.yaml` from the project root
- Load `.bmad-core/core-config.yaml`
- If the file does not exist, HALT and inform the user: "core-config.yaml not found. This file is required for story validation."
- Extract key configurations: `devStoryLocation`, `prd.*`, `architecture.*`
- Identify and load the following inputs:

1
dist/agents/sm.txt vendored
View File

@@ -98,7 +98,6 @@ To identify the next logical story based on project progress and epic definition
- Load `.bmad-core/core-config.yaml` from the project root
- If the file does not exist, HALT and inform the user: "core-config.yaml not found. This file is required for story creation. You can either: 1) Copy it from GITHUB bmad-core/core-config.yaml and configure it for your project OR 2) Run the BMad installer against your project to upgrade and add the file automatically. Please add and configure core-config.yaml before proceeding."
- Extract key configurations: `devStoryLocation`, `prd.*`, `architecture.*`, `workflow.*`
- If `workflow.trackProgress: true`, use `utils/plan-management.md` to check plan sequence and warn if out of order
### 1. Identify Next Story for Preparation

226
dist/expansion-packs/bmad-2d-phaser-game-dev/teams/phaser-2d-nodejs-game-team.txt vendored
View File

@@ -128,9 +128,6 @@ CRITICAL: Read the full YAML, start activation to alter your state of being, fol
```yaml
activation-instructions:
- Mention *help shows all available commands and options
- Check for active workflow plan using .bmad-2d-phaser-game-dev/utils/plan-management.md
- 'If plan exists: Show 📋 Active plan: {workflow} ({progress}% complete). Use *plan-status for details.'
- 'If plan exists: Suggest next action based on plan progress'
- Assess user goal against available agents and workflows in this bundle
- If clear match to an agent's expertise, suggest transformation with *agent command
- If project-oriented, suggest *workflow-guidance to explore options
@@ -252,7 +249,6 @@ dependencies:
- bmad-kb.md
- elicitation-methods.md
utils:
- plan-management.md
- workflow-management.md
```
==================== END: .bmad-2d-phaser-game-dev/agents/bmad-orchestrator.md ====================
@@ -3374,228 +3370,6 @@ The update is successful when:
- Prepare to continue without additional elicitation
==================== END: .bmad-2d-phaser-game-dev/data/elicitation-methods.md ====================
==================== START: .bmad-2d-phaser-game-dev/utils/plan-management.md ====================
# Plan Management Utility
## Purpose
Provides utilities for agents and tasks to interact with workflow plans, check progress, update status, and ensure workflow steps are executed in the appropriate sequence.
## Core Functions
### 1. Check Plan Existence
Check for workflow plan:
1. Look for docs/workflow-plan.md (default location)
2. Return plan status to user (exists/not exists) - if not exists then HALT.
### 2. Parse Plan Status
[[LLM: Extract current progress from the plan document]]
**Plan Parsing Logic:**
1. **Identify Step Structure**:
- Look for checkbox lines: `- [ ]` or `- [x]`
- Extract step IDs from comments: `<!-- step-id: X.Y -->`
- Identify agent assignments: `<!-- agent: pm -->`
2. **Determine Current State**:
- Last completed step (highest numbered `[x]`)
- Next expected step (first `[ ]` after completed steps)
- Overall progress percentage
3. **Extract Metadata**:
- Workflow type from plan header
- Decision points and their status
- Any deviation notes
### 3. Sequence Validation
[[LLM: Check if requested action aligns with plan sequence]]
**Validation Rules:**
1. **Strict Mode** (enforceSequence: true):
- Must complete steps in exact order
- Warn and block if out of sequence
- Require explicit override justification
2. **Flexible Mode** (enforceSequence: false):
- Warn about sequence deviation
- Allow with confirmation
- Log deviation reason
**Warning Templates:**
```text
SEQUENCE WARNING:
The workflow plan shows you should complete "{expected_step}" next.
You're attempting to: "{requested_action}"
In strict mode: Block and require plan update
In flexible mode: Allow with confirmation
```
### 4. Plan Update Operations
[[LLM: Provide consistent way to update plan progress]]
**Update Actions:**
1. **Mark Step Complete**:
- Change `- [ ]` to `- [x]`
- Add completion timestamp comment
- Update any status metadata
2. **Add Deviation Note**:
- Insert note explaining why sequence changed
- Reference the deviation in plan
3. **Update Current Step Pointer**:
- Add/move `<!-- current-step -->` marker
- Update last-modified timestamp
### 5. Integration Instructions
[[LLM: How agents and tasks should use this utility]]
**For Agents (startup sequence)**:
```text
1. Check if plan exists using this utility
2. If exists:
- Parse current status
- Show user: "Active workflow plan detected. Current step: {X}"
- Suggest: "Next recommended action: {next_step}"
3. Continue with normal startup
```
**For Tasks (pre-execution)**:
```text
1. Check if plan exists
2. If exists:
- Verify this task aligns with plan
- If not aligned:
- In strict mode: Show warning and stop
- In flexible mode: Show warning and ask for confirmation
3. After task completion:
- Update plan if task was a planned step
- Add note if task was unplanned
```
### 6. Plan Status Report Format
[[LLM: Standard format for showing plan status]]
```text
📋 Workflow Plan Status
━━━━━━━━━━━━━━━━━━━━
Workflow: {workflow_name}
Progress: {X}% complete ({completed}/{total} steps)
✅ Completed:
- {completed_step_1}
- {completed_step_2}
🔄 Current Step:
- {current_step_description}
📌 Upcoming:
- {next_step_1}
- {next_step_2}
⚠️ Notes:
- {any_deviations_or_notes}
```
### 7. Decision Point Handling
[[LLM: Special handling for workflow decision points]]
When encountering a decision point in the plan:
1. **Identify Decision Marker**: `<!-- decision: {decision_id} -->`
2. **Check Decision Status**: Made/Pending
3. **If Pending**:
- Block progress until decision made
- Show options to user
- Record decision when made
4. **If Made**:
- Verify current path aligns with decision
- Warn if attempting alternate path
### 8. Plan Abandonment
[[LLM: Graceful handling when user wants to stop following plan]]
If user wants to abandon plan:
1. Confirm abandonment intent
2. Add abandonment note to plan
3. Mark plan as "Abandoned" in header
4. Stop plan checking for remainder of session
5. Suggest creating new plan if needed
## Usage Examples
### Example 1: Agent Startup Check
```text
BMad Master starting...
[Check for plan]
Found active workflow plan: brownfield-fullstack
Progress: 40% complete (4/10 steps)
Current step: Create PRD (pm agent)
Suggestion: Based on your plan, you should work with the PM agent next.
Use *agent pm to switch, or *plan-status to see full progress.
```
### Example 2: Task Sequence Warning
```text
User: *task create-next-story
[Plan check triggered]
⚠️ SEQUENCE WARNING:
Your workflow plan indicates the PRD hasn't been created yet.
Creating stories before the PRD may lead to incomplete requirements.
Would you like to:
1. Continue anyway (will note deviation in plan)
2. Switch to creating PRD first (*agent pm)
3. View plan status (*plan-status)
```
### Example 3: Automatic Plan Update
```text
[After completing create-doc task for PRD]
✅ Plan Updated: Marked "Create PRD" as complete
📍 Next step: Create Architecture Document (architect agent)
```
## Implementation Notes
- This utility should be lightweight and fast
- Plan parsing should be resilient to format variations
- Always preserve user agency - warnings not blocks (unless strict mode)
- Plan updates should be atomic to prevent corruption
- Consider plan versioning for rollback capability
## Error Handling
- Missing plan: Return null, don't error
- Malformed plan: Warn but continue, treat as no plan
- Update failures: Log but don't block task completion
- Parse errors: Fallback to basic text search
==================== END: .bmad-2d-phaser-game-dev/utils/plan-management.md ====================
==================== START: .bmad-2d-phaser-game-dev/utils/workflow-management.md ====================
# Workflow Management

245
dist/teams/team-all.txt vendored
View File

@@ -64,9 +64,6 @@ CRITICAL: Read the full YAML, start activation to alter your state of being, fol
```yaml
activation-instructions:
- Mention *help shows all available commands and options
- Check for active workflow plan using .bmad-core/utils/plan-management.md
- 'If plan exists: Show 📋 Active plan: {workflow} ({progress}% complete). Use *plan-status for details.'
- 'If plan exists: Suggest next action based on plan progress'
- Assess user goal against available agents and workflows in this bundle
- If clear match to an agent's expertise, suggest transformation with *agent command
- If project-oriented, suggest *workflow-guidance to explore options
@@ -188,7 +185,6 @@ dependencies:
- bmad-kb.md
- elicitation-methods.md
utils:
- plan-management.md
- workflow-management.md
```
==================== END: .bmad-core/agents/bmad-orchestrator.md ====================
@@ -2188,7 +2184,7 @@ For full details, see `CONTRIBUTING.md`. Key points:
- Atomic commits - one logical change per commit
- Must align with guiding principles
**Core Principles** (from GUIDING-PRINCIPLES.md):
**Core Principles** (from docs/GUIDING-PRINCIPLES.md):
- **Dev Agents Must Be Lean**: Minimize dependencies, save context for code
- **Natural Language First**: Everything in markdown, no code in core
@@ -2258,8 +2254,8 @@ Use the **expansion-creator** pack to build your own:
## Getting Help
- **Commands**: Use `/help` in any environment to see available commands
- **Agent Switching**: Use `/switch agent-name` with orchestrator for role changes
- **Commands**: Use `*/*help` in any environment to see available commands
- **Agent Switching**: Use `*/*switch agent-name` with orchestrator for role changes
- **Documentation**: Check `docs/` folder for project-specific context
- **Community**: Discord and GitHub resources available for support
- **Contributing**: See `CONTRIBUTING.md` for full guidelines
@@ -2402,228 +2398,6 @@ Use the **expansion-creator** pack to build your own:
- Prepare to continue without additional elicitation
==================== END: .bmad-core/data/elicitation-methods.md ====================
==================== START: .bmad-core/utils/plan-management.md ====================
# Plan Management Utility
## Purpose
Provides utilities for agents and tasks to interact with workflow plans, check progress, update status, and ensure workflow steps are executed in the appropriate sequence.
## Core Functions
### 1. Check Plan Existence
Check for workflow plan:
1. Look for docs/workflow-plan.md (default location)
2. Return plan status to user (exists/not exists) - if not exists then HALT.
### 2. Parse Plan Status
[[LLM: Extract current progress from the plan document]]
**Plan Parsing Logic:**
1. **Identify Step Structure**:
- Look for checkbox lines: `- [ ]` or `- [x]`
- Extract step IDs from comments: `<!-- step-id: X.Y -->`
- Identify agent assignments: `<!-- agent: pm -->`
2. **Determine Current State**:
- Last completed step (highest numbered `[x]`)
- Next expected step (first `[ ]` after completed steps)
- Overall progress percentage
3. **Extract Metadata**:
- Workflow type from plan header
- Decision points and their status
- Any deviation notes
### 3. Sequence Validation
[[LLM: Check if requested action aligns with plan sequence]]
**Validation Rules:**
1. **Strict Mode** (enforceSequence: true):
- Must complete steps in exact order
- Warn and block if out of sequence
- Require explicit override justification
2. **Flexible Mode** (enforceSequence: false):
- Warn about sequence deviation
- Allow with confirmation
- Log deviation reason
**Warning Templates:**
```text
SEQUENCE WARNING:
The workflow plan shows you should complete "{expected_step}" next.
You're attempting to: "{requested_action}"
In strict mode: Block and require plan update
In flexible mode: Allow with confirmation
```
### 4. Plan Update Operations
[[LLM: Provide consistent way to update plan progress]]
**Update Actions:**
1. **Mark Step Complete**:
- Change `- [ ]` to `- [x]`
- Add completion timestamp comment
- Update any status metadata
2. **Add Deviation Note**:
- Insert note explaining why sequence changed
- Reference the deviation in plan
3. **Update Current Step Pointer**:
- Add/move `<!-- current-step -->` marker
- Update last-modified timestamp
### 5. Integration Instructions
[[LLM: How agents and tasks should use this utility]]
**For Agents (startup sequence)**:
```text
1. Check if plan exists using this utility
2. If exists:
- Parse current status
- Show user: "Active workflow plan detected. Current step: {X}"
- Suggest: "Next recommended action: {next_step}"
3. Continue with normal startup
```
**For Tasks (pre-execution)**:
```text
1. Check if plan exists
2. If exists:
- Verify this task aligns with plan
- If not aligned:
- In strict mode: Show warning and stop
- In flexible mode: Show warning and ask for confirmation
3. After task completion:
- Update plan if task was a planned step
- Add note if task was unplanned
```
### 6. Plan Status Report Format
[[LLM: Standard format for showing plan status]]
```text
📋 Workflow Plan Status
━━━━━━━━━━━━━━━━━━━━
Workflow: {workflow_name}
Progress: {X}% complete ({completed}/{total} steps)
✅ Completed:
- {completed_step_1}
- {completed_step_2}
🔄 Current Step:
- {current_step_description}
📌 Upcoming:
- {next_step_1}
- {next_step_2}
⚠️ Notes:
- {any_deviations_or_notes}
```
### 7. Decision Point Handling
[[LLM: Special handling for workflow decision points]]
When encountering a decision point in the plan:
1. **Identify Decision Marker**: `<!-- decision: {decision_id} -->`
2. **Check Decision Status**: Made/Pending
3. **If Pending**:
- Block progress until decision made
- Show options to user
- Record decision when made
4. **If Made**:
- Verify current path aligns with decision
- Warn if attempting alternate path
### 8. Plan Abandonment
[[LLM: Graceful handling when user wants to stop following plan]]
If user wants to abandon plan:
1. Confirm abandonment intent
2. Add abandonment note to plan
3. Mark plan as "Abandoned" in header
4. Stop plan checking for remainder of session
5. Suggest creating new plan if needed
## Usage Examples
### Example 1: Agent Startup Check
```text
BMad Master starting...
[Check for plan]
Found active workflow plan: brownfield-fullstack
Progress: 40% complete (4/10 steps)
Current step: Create PRD (pm agent)
Suggestion: Based on your plan, you should work with the PM agent next.
Use *agent pm to switch, or *plan-status to see full progress.
```
### Example 2: Task Sequence Warning
```text
User: *task create-next-story
[Plan check triggered]
⚠️ SEQUENCE WARNING:
Your workflow plan indicates the PRD hasn't been created yet.
Creating stories before the PRD may lead to incomplete requirements.
Would you like to:
1. Continue anyway (will note deviation in plan)
2. Switch to creating PRD first (*agent pm)
3. View plan status (*plan-status)
```
### Example 3: Automatic Plan Update
```text
[After completing create-doc task for PRD]
✅ Plan Updated: Marked "Create PRD" as complete
📍 Next step: Create Architecture Document (architect agent)
```
## Implementation Notes
- This utility should be lightweight and fast
- Plan parsing should be resilient to format variations
- Always preserve user agency - warnings not blocks (unless strict mode)
- Plan updates should be atomic to prevent corruption
- Consider plan versioning for rollback capability
## Error Handling
- Missing plan: Return null, don't error
- Malformed plan: Warn but continue, treat as no plan
- Update failures: Log but don't block task completion
- Parse errors: Fallback to basic text search
==================== END: .bmad-core/utils/plan-management.md ====================
==================== START: .bmad-core/utils/workflow-management.md ====================
# Workflow Management
@@ -7140,7 +6914,7 @@ To comprehensively validate a story draft before implementation begins, ensuring
### 0. Load Core Configuration and Inputs
- Load `.bmad-core/core-config.yaml` from the project root
- Load `.bmad-core/core-config.yaml`
- If the file does not exist, HALT and inform the user: "core-config.yaml not found. This file is required for story validation."
- Extract key configurations: `devStoryLocation`, `prd.*`, `architecture.*`
- Identify and load the following inputs:
@@ -9750,7 +9524,6 @@ To identify the next logical story based on project progress and epic definition
- Load `.bmad-core/core-config.yaml` from the project root
- If the file does not exist, HALT and inform the user: "core-config.yaml not found. This file is required for story creation. You can either: 1) Copy it from GITHUB bmad-core/core-config.yaml and configure it for your project OR 2) Run the BMad installer against your project to upgrade and add the file automatically. Please add and configure core-config.yaml before proceeding."
- Extract key configurations: `devStoryLocation`, `prd.*`, `architecture.*`, `workflow.*`
- If `workflow.trackProgress: true`, use `utils/plan-management.md` to check plan sequence and warn if out of order
### 1. Identify Next Story for Preparation
@@ -10603,7 +10376,7 @@ workflow:
All stories implemented and reviewed!
Project development phase complete.
Reference: data#bmad-kb:IDE Development Workflow
Reference: .bmad-core/data/bmad-kb.md#IDE Development Workflow
flow_diagram: |
```mermaid
@@ -10849,7 +10622,7 @@ workflow:
All stories implemented and reviewed!
Project development phase complete.
Reference: data#bmad-kb:IDE Development Workflow
Reference: .bmad-core/data/bmad-kb.md#IDE Development Workflow
flow_diagram: |
```mermaid
@@ -11046,7 +10819,7 @@ workflow:
All stories implemented and reviewed!
Project development phase complete.
Reference: data#bmad-kb:IDE Development Workflow
Reference: .bmad-core/data/bmad-kb.md#IDE Development Workflow
flow_diagram: |
```mermaid
@@ -11271,7 +11044,7 @@ workflow:
All stories implemented and reviewed!
Project development phase complete.
Reference: data#bmad-kb:IDE Development Workflow
Reference: .bmad-core/data/bmad-kb.md#IDE Development Workflow
flow_diagram: |
```mermaid
@@ -11718,7 +11491,7 @@ workflow:
All stories implemented and reviewed!
Project development phase complete.
Reference: data#bmad-kb:IDE Development Workflow
Reference: .bmad-core/data/bmad-kb.md#IDE Development Workflow
flow_diagram: |
```mermaid

244
dist/teams/team-fullstack.txt vendored
View File

@@ -68,9 +68,6 @@ CRITICAL: Read the full YAML, start activation to alter your state of being, fol
```yaml
activation-instructions:
- Mention *help shows all available commands and options
- Check for active workflow plan using .bmad-core/utils/plan-management.md
- 'If plan exists: Show 📋 Active plan: {workflow} ({progress}% complete). Use *plan-status for details.'
- 'If plan exists: Suggest next action based on plan progress'
- Assess user goal against available agents and workflows in this bundle
- If clear match to an agent's expertise, suggest transformation with *agent command
- If project-oriented, suggest *workflow-guidance to explore options
@@ -192,7 +189,6 @@ dependencies:
- bmad-kb.md
- elicitation-methods.md
utils:
- plan-management.md
- workflow-management.md
```
==================== END: .bmad-core/agents/bmad-orchestrator.md ====================
@@ -2046,7 +2042,7 @@ For full details, see `CONTRIBUTING.md`. Key points:
- Atomic commits - one logical change per commit
- Must align with guiding principles
**Core Principles** (from GUIDING-PRINCIPLES.md):
**Core Principles** (from docs/GUIDING-PRINCIPLES.md):
- **Dev Agents Must Be Lean**: Minimize dependencies, save context for code
- **Natural Language First**: Everything in markdown, no code in core
@@ -2116,8 +2112,8 @@ Use the **expansion-creator** pack to build your own:
## Getting Help
- **Commands**: Use `/help` in any environment to see available commands
- **Agent Switching**: Use `/switch agent-name` with orchestrator for role changes
- **Commands**: Use `*/*help` in any environment to see available commands
- **Agent Switching**: Use `*/*switch agent-name` with orchestrator for role changes
- **Documentation**: Check `docs/` folder for project-specific context
- **Community**: Discord and GitHub resources available for support
- **Contributing**: See `CONTRIBUTING.md` for full guidelines
@@ -2260,228 +2256,6 @@ Use the **expansion-creator** pack to build your own:
- Prepare to continue without additional elicitation
==================== END: .bmad-core/data/elicitation-methods.md ====================
==================== START: .bmad-core/utils/plan-management.md ====================
# Plan Management Utility
## Purpose
Provides utilities for agents and tasks to interact with workflow plans, check progress, update status, and ensure workflow steps are executed in the appropriate sequence.
## Core Functions
### 1. Check Plan Existence
Check for workflow plan:
1. Look for docs/workflow-plan.md (default location)
2. Return plan status to user (exists/not exists) - if not exists then HALT.
### 2. Parse Plan Status
[[LLM: Extract current progress from the plan document]]
**Plan Parsing Logic:**
1. **Identify Step Structure**:
- Look for checkbox lines: `- [ ]` or `- [x]`
- Extract step IDs from comments: `<!-- step-id: X.Y -->`
- Identify agent assignments: `<!-- agent: pm -->`
2. **Determine Current State**:
- Last completed step (highest numbered `[x]`)
- Next expected step (first `[ ]` after completed steps)
- Overall progress percentage
3. **Extract Metadata**:
- Workflow type from plan header
- Decision points and their status
- Any deviation notes
### 3. Sequence Validation
[[LLM: Check if requested action aligns with plan sequence]]
**Validation Rules:**
1. **Strict Mode** (enforceSequence: true):
- Must complete steps in exact order
- Warn and block if out of sequence
- Require explicit override justification
2. **Flexible Mode** (enforceSequence: false):
- Warn about sequence deviation
- Allow with confirmation
- Log deviation reason
**Warning Templates:**
```text
SEQUENCE WARNING:
The workflow plan shows you should complete "{expected_step}" next.
You're attempting to: "{requested_action}"
In strict mode: Block and require plan update
In flexible mode: Allow with confirmation
```
### 4. Plan Update Operations
[[LLM: Provide consistent way to update plan progress]]
**Update Actions:**
1. **Mark Step Complete**:
- Change `- [ ]` to `- [x]`
- Add completion timestamp comment
- Update any status metadata
2. **Add Deviation Note**:
- Insert note explaining why sequence changed
- Reference the deviation in plan
3. **Update Current Step Pointer**:
- Add/move `<!-- current-step -->` marker
- Update last-modified timestamp
### 5. Integration Instructions
[[LLM: How agents and tasks should use this utility]]
**For Agents (startup sequence)**:
```text
1. Check if plan exists using this utility
2. If exists:
- Parse current status
- Show user: "Active workflow plan detected. Current step: {X}"
- Suggest: "Next recommended action: {next_step}"
3. Continue with normal startup
```
**For Tasks (pre-execution)**:
```text
1. Check if plan exists
2. If exists:
- Verify this task aligns with plan
- If not aligned:
- In strict mode: Show warning and stop
- In flexible mode: Show warning and ask for confirmation
3. After task completion:
- Update plan if task was a planned step
- Add note if task was unplanned
```
### 6. Plan Status Report Format
[[LLM: Standard format for showing plan status]]
```text
📋 Workflow Plan Status
━━━━━━━━━━━━━━━━━━━━
Workflow: {workflow_name}
Progress: {X}% complete ({completed}/{total} steps)
✅ Completed:
- {completed_step_1}
- {completed_step_2}
🔄 Current Step:
- {current_step_description}
📌 Upcoming:
- {next_step_1}
- {next_step_2}
⚠️ Notes:
- {any_deviations_or_notes}
```
### 7. Decision Point Handling
[[LLM: Special handling for workflow decision points]]
When encountering a decision point in the plan:
1. **Identify Decision Marker**: `<!-- decision: {decision_id} -->`
2. **Check Decision Status**: Made/Pending
3. **If Pending**:
- Block progress until decision made
- Show options to user
- Record decision when made
4. **If Made**:
- Verify current path aligns with decision
- Warn if attempting alternate path
### 8. Plan Abandonment
[[LLM: Graceful handling when user wants to stop following plan]]
If user wants to abandon plan:
1. Confirm abandonment intent
2. Add abandonment note to plan
3. Mark plan as "Abandoned" in header
4. Stop plan checking for remainder of session
5. Suggest creating new plan if needed
## Usage Examples
### Example 1: Agent Startup Check
```text
BMad Master starting...
[Check for plan]
Found active workflow plan: brownfield-fullstack
Progress: 40% complete (4/10 steps)
Current step: Create PRD (pm agent)
Suggestion: Based on your plan, you should work with the PM agent next.
Use *agent pm to switch, or *plan-status to see full progress.
```
### Example 2: Task Sequence Warning
```text
User: *task create-next-story
[Plan check triggered]
⚠️ SEQUENCE WARNING:
Your workflow plan indicates the PRD hasn't been created yet.
Creating stories before the PRD may lead to incomplete requirements.
Would you like to:
1. Continue anyway (will note deviation in plan)
2. Switch to creating PRD first (*agent pm)
3. View plan status (*plan-status)
```
### Example 3: Automatic Plan Update
```text
[After completing create-doc task for PRD]
✅ Plan Updated: Marked "Create PRD" as complete
📍 Next step: Create Architecture Document (architect agent)
```
## Implementation Notes
- This utility should be lightweight and fast
- Plan parsing should be resilient to format variations
- Always preserve user agency - warnings not blocks (unless strict mode)
- Plan updates should be atomic to prevent corruption
- Consider plan versioning for rollback capability
## Error Handling
- Missing plan: Return null, don't error
- Malformed plan: Warn but continue, treat as no plan
- Update failures: Log but don't block task completion
- Parse errors: Fallback to basic text search
==================== END: .bmad-core/utils/plan-management.md ====================
==================== START: .bmad-core/utils/workflow-management.md ====================
# Workflow Management
@@ -9038,7 +8812,7 @@ To comprehensively validate a story draft before implementation begins, ensuring
### 0. Load Core Configuration and Inputs
- Load `.bmad-core/core-config.yaml` from the project root
- Load `.bmad-core/core-config.yaml`
- If the file does not exist, HALT and inform the user: "core-config.yaml not found. This file is required for story validation."
- Extract key configurations: `devStoryLocation`, `prd.*`, `architecture.*`
- Identify and load the following inputs:
@@ -9933,7 +9707,7 @@ workflow:
All stories implemented and reviewed!
Project development phase complete.
Reference: data#bmad-kb:IDE Development Workflow
Reference: .bmad-core/data/bmad-kb.md#IDE Development Workflow
flow_diagram: |
```mermaid
@@ -10179,7 +9953,7 @@ workflow:
All stories implemented and reviewed!
Project development phase complete.
Reference: data#bmad-kb:IDE Development Workflow
Reference: .bmad-core/data/bmad-kb.md#IDE Development Workflow
flow_diagram: |
```mermaid
@@ -10376,7 +10150,7 @@ workflow:
All stories implemented and reviewed!
Project development phase complete.
Reference: data#bmad-kb:IDE Development Workflow
Reference: .bmad-core/data/bmad-kb.md#IDE Development Workflow
flow_diagram: |
```mermaid
@@ -10601,7 +10375,7 @@ workflow:
All stories implemented and reviewed!
Project development phase complete.
Reference: data#bmad-kb:IDE Development Workflow
Reference: .bmad-core/data/bmad-kb.md#IDE Development Workflow
flow_diagram: |
```mermaid
@@ -11048,7 +10822,7 @@ workflow:
All stories implemented and reviewed!
Project development phase complete.
Reference: data#bmad-kb:IDE Development Workflow
Reference: .bmad-core/data/bmad-kb.md#IDE Development Workflow
flow_diagram: |
```mermaid

235
dist/teams/team-ide-minimal.txt vendored
View File

@@ -60,9 +60,6 @@ CRITICAL: Read the full YAML, start activation to alter your state of being, fol
```yaml
activation-instructions:
- Mention *help shows all available commands and options
- Check for active workflow plan using .bmad-core/utils/plan-management.md
- 'If plan exists: Show 📋 Active plan: {workflow} ({progress}% complete). Use *plan-status for details.'
- 'If plan exists: Suggest next action based on plan progress'
- Assess user goal against available agents and workflows in this bundle
- If clear match to an agent's expertise, suggest transformation with *agent command
- If project-oriented, suggest *workflow-guidance to explore options
@@ -184,7 +181,6 @@ dependencies:
- bmad-kb.md
- elicitation-methods.md
utils:
- plan-management.md
- workflow-management.md
```
==================== END: .bmad-core/agents/bmad-orchestrator.md ====================
@@ -1945,7 +1941,7 @@ For full details, see `CONTRIBUTING.md`. Key points:
- Atomic commits - one logical change per commit
- Must align with guiding principles
**Core Principles** (from GUIDING-PRINCIPLES.md):
**Core Principles** (from docs/GUIDING-PRINCIPLES.md):
- **Dev Agents Must Be Lean**: Minimize dependencies, save context for code
- **Natural Language First**: Everything in markdown, no code in core
@@ -2015,8 +2011,8 @@ Use the **expansion-creator** pack to build your own:
## Getting Help
- **Commands**: Use `/help` in any environment to see available commands
- **Agent Switching**: Use `/switch agent-name` with orchestrator for role changes
- **Commands**: Use `*/*help` in any environment to see available commands
- **Agent Switching**: Use `*/*switch agent-name` with orchestrator for role changes
- **Documentation**: Check `docs/` folder for project-specific context
- **Community**: Discord and GitHub resources available for support
- **Contributing**: See `CONTRIBUTING.md` for full guidelines
@@ -2159,228 +2155,6 @@ Use the **expansion-creator** pack to build your own:
- Prepare to continue without additional elicitation
==================== END: .bmad-core/data/elicitation-methods.md ====================
==================== START: .bmad-core/utils/plan-management.md ====================
# Plan Management Utility
## Purpose
Provides utilities for agents and tasks to interact with workflow plans, check progress, update status, and ensure workflow steps are executed in the appropriate sequence.
## Core Functions
### 1. Check Plan Existence
Check for workflow plan:
1. Look for docs/workflow-plan.md (default location)
2. Return plan status to user (exists/not exists) - if not exists then HALT.
### 2. Parse Plan Status
[[LLM: Extract current progress from the plan document]]
**Plan Parsing Logic:**
1. **Identify Step Structure**:
- Look for checkbox lines: `- [ ]` or `- [x]`
- Extract step IDs from comments: `<!-- step-id: X.Y -->`
- Identify agent assignments: `<!-- agent: pm -->`
2. **Determine Current State**:
- Last completed step (highest numbered `[x]`)
- Next expected step (first `[ ]` after completed steps)
- Overall progress percentage
3. **Extract Metadata**:
- Workflow type from plan header
- Decision points and their status
- Any deviation notes
### 3. Sequence Validation
[[LLM: Check if requested action aligns with plan sequence]]
**Validation Rules:**
1. **Strict Mode** (enforceSequence: true):
- Must complete steps in exact order
- Warn and block if out of sequence
- Require explicit override justification
2. **Flexible Mode** (enforceSequence: false):
- Warn about sequence deviation
- Allow with confirmation
- Log deviation reason
**Warning Templates:**
```text
SEQUENCE WARNING:
The workflow plan shows you should complete "{expected_step}" next.
You're attempting to: "{requested_action}"
In strict mode: Block and require plan update
In flexible mode: Allow with confirmation
```
### 4. Plan Update Operations
[[LLM: Provide consistent way to update plan progress]]
**Update Actions:**
1. **Mark Step Complete**:
- Change `- [ ]` to `- [x]`
- Add completion timestamp comment
- Update any status metadata
2. **Add Deviation Note**:
- Insert note explaining why sequence changed
- Reference the deviation in plan
3. **Update Current Step Pointer**:
- Add/move `<!-- current-step -->` marker
- Update last-modified timestamp
### 5. Integration Instructions
[[LLM: How agents and tasks should use this utility]]
**For Agents (startup sequence)**:
```text
1. Check if plan exists using this utility
2. If exists:
- Parse current status
- Show user: "Active workflow plan detected. Current step: {X}"
- Suggest: "Next recommended action: {next_step}"
3. Continue with normal startup
```
**For Tasks (pre-execution)**:
```text
1. Check if plan exists
2. If exists:
- Verify this task aligns with plan
- If not aligned:
- In strict mode: Show warning and stop
- In flexible mode: Show warning and ask for confirmation
3. After task completion:
- Update plan if task was a planned step
- Add note if task was unplanned
```
### 6. Plan Status Report Format
[[LLM: Standard format for showing plan status]]
```text
📋 Workflow Plan Status
━━━━━━━━━━━━━━━━━━━━
Workflow: {workflow_name}
Progress: {X}% complete ({completed}/{total} steps)
✅ Completed:
- {completed_step_1}
- {completed_step_2}
🔄 Current Step:
- {current_step_description}
📌 Upcoming:
- {next_step_1}
- {next_step_2}
⚠️ Notes:
- {any_deviations_or_notes}
```
### 7. Decision Point Handling
[[LLM: Special handling for workflow decision points]]
When encountering a decision point in the plan:
1. **Identify Decision Marker**: `<!-- decision: {decision_id} -->`
2. **Check Decision Status**: Made/Pending
3. **If Pending**:
- Block progress until decision made
- Show options to user
- Record decision when made
4. **If Made**:
- Verify current path aligns with decision
- Warn if attempting alternate path
### 8. Plan Abandonment
[[LLM: Graceful handling when user wants to stop following plan]]
If user wants to abandon plan:
1. Confirm abandonment intent
2. Add abandonment note to plan
3. Mark plan as "Abandoned" in header
4. Stop plan checking for remainder of session
5. Suggest creating new plan if needed
## Usage Examples
### Example 1: Agent Startup Check
```text
BMad Master starting...
[Check for plan]
Found active workflow plan: brownfield-fullstack
Progress: 40% complete (4/10 steps)
Current step: Create PRD (pm agent)
Suggestion: Based on your plan, you should work with the PM agent next.
Use *agent pm to switch, or *plan-status to see full progress.
```
### Example 2: Task Sequence Warning
```text
User: *task create-next-story
[Plan check triggered]
⚠️ SEQUENCE WARNING:
Your workflow plan indicates the PRD hasn't been created yet.
Creating stories before the PRD may lead to incomplete requirements.
Would you like to:
1. Continue anyway (will note deviation in plan)
2. Switch to creating PRD first (*agent pm)
3. View plan status (*plan-status)
```
### Example 3: Automatic Plan Update
```text
[After completing create-doc task for PRD]
✅ Plan Updated: Marked "Create PRD" as complete
📍 Next step: Create Architecture Document (architect agent)
```
## Implementation Notes
- This utility should be lightweight and fast
- Plan parsing should be resilient to format variations
- Always preserve user agency - warnings not blocks (unless strict mode)
- Plan updates should be atomic to prevent corruption
- Consider plan versioning for rollback capability
## Error Handling
- Missing plan: Return null, don't error
- Malformed plan: Warn but continue, treat as no plan
- Update failures: Log but don't block task completion
- Parse errors: Fallback to basic text search
==================== END: .bmad-core/utils/plan-management.md ====================
==================== START: .bmad-core/utils/workflow-management.md ====================
# Workflow Management
@@ -3143,7 +2917,7 @@ To comprehensively validate a story draft before implementation begins, ensuring
### 0. Load Core Configuration and Inputs
- Load `.bmad-core/core-config.yaml` from the project root
- Load `.bmad-core/core-config.yaml`
- If the file does not exist, HALT and inform the user: "core-config.yaml not found. This file is required for story validation."
- Extract key configurations: `devStoryLocation`, `prd.*`, `architecture.*`
- Identify and load the following inputs:
@@ -4052,7 +3826,6 @@ To identify the next logical story based on project progress and epic definition
- Load `.bmad-core/core-config.yaml` from the project root
- If the file does not exist, HALT and inform the user: "core-config.yaml not found. This file is required for story creation. You can either: 1) Copy it from GITHUB bmad-core/core-config.yaml and configure it for your project OR 2) Run the BMad installer against your project to upgrade and add the file automatically. Please add and configure core-config.yaml before proceeding."
- Extract key configurations: `devStoryLocation`, `prd.*`, `architecture.*`, `workflow.*`
- If `workflow.trackProgress: true`, use `utils/plan-management.md` to check plan sequence and warn if out of order
### 1. Identify Next Story for Preparation

236
dist/teams/team-no-ui.txt vendored
View File

@@ -63,9 +63,6 @@ CRITICAL: Read the full YAML, start activation to alter your state of being, fol
```yaml
activation-instructions:
- Mention *help shows all available commands and options
- Check for active workflow plan using .bmad-core/utils/plan-management.md
- 'If plan exists: Show 📋 Active plan: {workflow} ({progress}% complete). Use *plan-status for details.'
- 'If plan exists: Suggest next action based on plan progress'
- Assess user goal against available agents and workflows in this bundle
- If clear match to an agent's expertise, suggest transformation with *agent command
- If project-oriented, suggest *workflow-guidance to explore options
@@ -187,7 +184,6 @@ dependencies:
- bmad-kb.md
- elicitation-methods.md
utils:
- plan-management.md
- workflow-management.md
```
==================== END: .bmad-core/agents/bmad-orchestrator.md ====================
@@ -1988,7 +1984,7 @@ For full details, see `CONTRIBUTING.md`. Key points:
- Atomic commits - one logical change per commit
- Must align with guiding principles
**Core Principles** (from GUIDING-PRINCIPLES.md):
**Core Principles** (from docs/GUIDING-PRINCIPLES.md):
- **Dev Agents Must Be Lean**: Minimize dependencies, save context for code
- **Natural Language First**: Everything in markdown, no code in core
@@ -2058,8 +2054,8 @@ Use the **expansion-creator** pack to build your own:
## Getting Help
- **Commands**: Use `/help` in any environment to see available commands
- **Agent Switching**: Use `/switch agent-name` with orchestrator for role changes
- **Commands**: Use `*/*help` in any environment to see available commands
- **Agent Switching**: Use `*/*switch agent-name` with orchestrator for role changes
- **Documentation**: Check `docs/` folder for project-specific context
- **Community**: Discord and GitHub resources available for support
- **Contributing**: See `CONTRIBUTING.md` for full guidelines
@@ -2202,228 +2198,6 @@ Use the **expansion-creator** pack to build your own:
- Prepare to continue without additional elicitation
==================== END: .bmad-core/data/elicitation-methods.md ====================
==================== START: .bmad-core/utils/plan-management.md ====================
# Plan Management Utility
## Purpose
Provides utilities for agents and tasks to interact with workflow plans, check progress, update status, and ensure workflow steps are executed in the appropriate sequence.
## Core Functions
### 1. Check Plan Existence
Check for workflow plan:
1. Look for docs/workflow-plan.md (default location)
2. Return plan status to user (exists/not exists) - if not exists then HALT.
### 2. Parse Plan Status
[[LLM: Extract current progress from the plan document]]
**Plan Parsing Logic:**
1. **Identify Step Structure**:
- Look for checkbox lines: `- [ ]` or `- [x]`
- Extract step IDs from comments: `<!-- step-id: X.Y -->`
- Identify agent assignments: `<!-- agent: pm -->`
2. **Determine Current State**:
- Last completed step (highest numbered `[x]`)
- Next expected step (first `[ ]` after completed steps)
- Overall progress percentage
3. **Extract Metadata**:
- Workflow type from plan header
- Decision points and their status
- Any deviation notes
### 3. Sequence Validation
[[LLM: Check if requested action aligns with plan sequence]]
**Validation Rules:**
1. **Strict Mode** (enforceSequence: true):
- Must complete steps in exact order
- Warn and block if out of sequence
- Require explicit override justification
2. **Flexible Mode** (enforceSequence: false):
- Warn about sequence deviation
- Allow with confirmation
- Log deviation reason
**Warning Templates:**
```text
SEQUENCE WARNING:
The workflow plan shows you should complete "{expected_step}" next.
You're attempting to: "{requested_action}"
In strict mode: Block and require plan update
In flexible mode: Allow with confirmation
```
### 4. Plan Update Operations
[[LLM: Provide consistent way to update plan progress]]
**Update Actions:**
1. **Mark Step Complete**:
- Change `- [ ]` to `- [x]`
- Add completion timestamp comment
- Update any status metadata
2. **Add Deviation Note**:
- Insert note explaining why sequence changed
- Reference the deviation in plan
3. **Update Current Step Pointer**:
- Add/move `<!-- current-step -->` marker
- Update last-modified timestamp
### 5. Integration Instructions
[[LLM: How agents and tasks should use this utility]]
**For Agents (startup sequence)**:
```text
1. Check if plan exists using this utility
2. If exists:
- Parse current status
- Show user: "Active workflow plan detected. Current step: {X}"
- Suggest: "Next recommended action: {next_step}"
3. Continue with normal startup
```
**For Tasks (pre-execution)**:
```text
1. Check if plan exists
2. If exists:
- Verify this task aligns with plan
- If not aligned:
- In strict mode: Show warning and stop
- In flexible mode: Show warning and ask for confirmation
3. After task completion:
- Update plan if task was a planned step
- Add note if task was unplanned
```
### 6. Plan Status Report Format
[[LLM: Standard format for showing plan status]]
```text
📋 Workflow Plan Status
━━━━━━━━━━━━━━━━━━━━
Workflow: {workflow_name}
Progress: {X}% complete ({completed}/{total} steps)
✅ Completed:
- {completed_step_1}
- {completed_step_2}
🔄 Current Step:
- {current_step_description}
📌 Upcoming:
- {next_step_1}
- {next_step_2}
⚠️ Notes:
- {any_deviations_or_notes}
```
### 7. Decision Point Handling
[[LLM: Special handling for workflow decision points]]
When encountering a decision point in the plan:
1. **Identify Decision Marker**: `<!-- decision: {decision_id} -->`
2. **Check Decision Status**: Made/Pending
3. **If Pending**:
- Block progress until decision made
- Show options to user
- Record decision when made
4. **If Made**:
- Verify current path aligns with decision
- Warn if attempting alternate path
### 8. Plan Abandonment
[[LLM: Graceful handling when user wants to stop following plan]]
If user wants to abandon plan:
1. Confirm abandonment intent
2. Add abandonment note to plan
3. Mark plan as "Abandoned" in header
4. Stop plan checking for remainder of session
5. Suggest creating new plan if needed
## Usage Examples
### Example 1: Agent Startup Check
```text
BMad Master starting...
[Check for plan]
Found active workflow plan: brownfield-fullstack
Progress: 40% complete (4/10 steps)
Current step: Create PRD (pm agent)
Suggestion: Based on your plan, you should work with the PM agent next.
Use *agent pm to switch, or *plan-status to see full progress.
```
### Example 2: Task Sequence Warning
```text
User: *task create-next-story
[Plan check triggered]
⚠️ SEQUENCE WARNING:
Your workflow plan indicates the PRD hasn't been created yet.
Creating stories before the PRD may lead to incomplete requirements.
Would you like to:
1. Continue anyway (will note deviation in plan)
2. Switch to creating PRD first (*agent pm)
3. View plan status (*plan-status)
```
### Example 3: Automatic Plan Update
```text
[After completing create-doc task for PRD]
✅ Plan Updated: Marked "Create PRD" as complete
📍 Next step: Create Architecture Document (architect agent)
```
## Implementation Notes
- This utility should be lightweight and fast
- Plan parsing should be resilient to format variations
- Always preserve user agency - warnings not blocks (unless strict mode)
- Plan updates should be atomic to prevent corruption
- Consider plan versioning for rollback capability
## Error Handling
- Missing plan: Return null, don't error
- Malformed plan: Warn but continue, treat as no plan
- Update failures: Log but don't block task completion
- Parse errors: Fallback to basic text search
==================== END: .bmad-core/utils/plan-management.md ====================
==================== START: .bmad-core/utils/workflow-management.md ====================
# Workflow Management
@@ -8574,7 +8348,7 @@ To comprehensively validate a story draft before implementation begins, ensuring
### 0. Load Core Configuration and Inputs
- Load `.bmad-core/core-config.yaml` from the project root
- Load `.bmad-core/core-config.yaml`
- If the file does not exist, HALT and inform the user: "core-config.yaml not found. This file is required for story validation."
- Extract key configurations: `devStoryLocation`, `prd.*`, `architecture.*`
- Identify and load the following inputs:
@@ -9624,7 +9398,7 @@ workflow:
All stories implemented and reviewed!
Project development phase complete.
Reference: data#bmad-kb:IDE Development Workflow
Reference: .bmad-core/data/bmad-kb.md#IDE Development Workflow
flow_diagram: |
```mermaid

5
expansion-packs/bmad-2d-phaser-game-dev/agents/game-designer.md
View File

@@ -3,9 +3,8 @@
CRITICAL: Read the full YAML, start activation to alter your state of being, follow startup section instructions, stay in this being until told to exit this mode:
```yaml
root: .bmad-2d-phaser-game-dev
IDE-FILE-RESOLUTION: Dependencies map to files as {root}/{type}/{name} where root=".bmad-core", type=folder (tasks/templates/checklists/utils), name=dependency name.
REQUEST-RESOLUTION: Match user requests to your commands/dependencies flexibly (e.g., "draft story"→*create→create-next-story task, "make a new prd" would be dependencies->tasks->create-doc combined with the dependencies->templates->prd-tmpl.md), or ask for clarification if ambiguous.
IDE-FILE-RESOLUTION: Dependencies map to files as {root}/{type}/{name}, type=folder (tasks/templates/checklists/data/utils), name=file-name.
REQUEST-RESOLUTION: Match user requests to your commands/dependencies flexibly (e.g., "draft story"→*create→create-next-story task, "make a new prd" would be dependencies->tasks->create-doc combined with the dependencies->templates->prd-tmpl.md), ALWAYS ask for clarification if no clear match.
activation-instructions:
- Follow all instructions in this file -> this defines you, your persona and more importantly what you can do. STAY IN CHARACTER!
- Only read the files/tasks listed here when user selects them for execution to minimize context usage

5
expansion-packs/bmad-2d-phaser-game-dev/agents/game-developer.md
View File

@@ -3,9 +3,8 @@
CRITICAL: Read the full YAML, start activation to alter your state of being, follow startup section instructions, stay in this being until told to exit this mode:
```yaml
root: .bmad-2d-phaser-game-dev
IDE-FILE-RESOLUTION: Dependencies map to files as {root}/{type}/{name} where root=".bmad-core", type=folder (tasks/templates/checklists/utils), name=dependency name.
REQUEST-RESOLUTION: Match user requests to your commands/dependencies flexibly (e.g., "draft story"→*create→create-next-story task, "make a new prd" would be dependencies->tasks->create-doc combined with the dependencies->templates->prd-tmpl.md), or ask for clarification if ambiguous.
IDE-FILE-RESOLUTION: Dependencies map to files as {root}/{type}/{name}, type=folder (tasks/templates/checklists/data/utils), name=file-name.
REQUEST-RESOLUTION: Match user requests to your commands/dependencies flexibly (e.g., "draft story"→*create→create-next-story task, "make a new prd" would be dependencies->tasks->create-doc combined with the dependencies->templates->prd-tmpl.md), ALWAYS ask for clarification if no clear match.
activation-instructions:
- Follow all instructions in this file -> this defines you, your persona and more importantly what you can do. STAY IN CHARACTER!
- Only read the files/tasks listed here when user selects them for execution to minimize context usage

5
expansion-packs/bmad-2d-phaser-game-dev/agents/game-sm.md
View File

@@ -3,9 +3,8 @@
CRITICAL: Read the full YAML, start activation to alter your state of being, follow startup section instructions, stay in this being until told to exit this mode:
```yaml
root: .bmad-2d-phaser-game-dev
IDE-FILE-RESOLUTION: Dependencies map to files as {root}/{type}/{name} where root=".bmad-core", type=folder (tasks/templates/checklists/utils), name=dependency name.
REQUEST-RESOLUTION: Match user requests to your commands/dependencies flexibly (e.g., "draft story"→*create→create-next-story task, "make a new prd" would be dependencies->tasks->create-doc combined with the dependencies->templates->prd-tmpl.md), or ask for clarification if ambiguous.
IDE-FILE-RESOLUTION: Dependencies map to files as {root}/{type}/{name}, type=folder (tasks/templates/checklists/data/utils), name=file-name.
REQUEST-RESOLUTION: Match user requests to your commands/dependencies flexibly (e.g., "draft story"→*create→create-next-story task, "make a new prd" would be dependencies->tasks->create-doc combined with the dependencies->templates->prd-tmpl.md), ALWAYS ask for clarification if no clear match.
activation-instructions:
- Follow all instructions in this file -> this defines you, your persona and more importantly what you can do. STAY IN CHARACTER!
- Only read the files/tasks listed here when user selects them for execution to minimize context usage

5
expansion-packs/bmad-creator-tools/agents/bmad-the-creator.md
View File

@@ -3,9 +3,8 @@
CRITICAL: Read the full YAML, start activation to alter your state of being, follow startup section instructions, stay in this being until told to exit this mode:
```yaml
root: .bmad-creator-tools
IDE-FILE-RESOLUTION: Dependencies map to files as {root}/{type}/{name} where root=".bmad-core", type=folder (tasks/templates/checklists/utils), name=dependency name.
REQUEST-RESOLUTION: Match user requests to your commands/dependencies flexibly (e.g., "draft story"→*create→create-next-story task, "make a new prd" would be dependencies->tasks->create-doc combined with the dependencies->templates->prd-tmpl.md), or ask for clarification if ambiguous.
IDE-FILE-RESOLUTION: Dependencies map to files as {root}/{type}/{name}, type=folder (tasks/templates/checklists/data/utils), name=file-name.
REQUEST-RESOLUTION: Match user requests to your commands/dependencies flexibly (e.g., "draft story"→*create→create-next-story task, "make a new prd" would be dependencies->tasks->create-doc combined with the dependencies->templates->prd-tmpl.md), ALWAYS ask for clarification if no clear match.
activation-instructions:
- Follow all instructions in this file -> this defines you, your persona and more importantly what you can do. STAY IN CHARACTER!
- Only read the files/tasks listed here when user selects them for execution to minimize context usage

5
expansion-packs/bmad-infrastructure-devops/agents/infra-devops-platform.md
View File

@@ -3,9 +3,8 @@
CRITICAL: Read the full YAML, start activation to alter your state of being, follow startup section instructions, stay in this being until told to exit this mode:
```yaml
root: .bmad-infrastructure-devops
IDE-FILE-RESOLUTION: Dependencies map to files as {root}/{type}/{name} where root=".bmad-core", type=folder (tasks/templates/checklists/utils), name=dependency name.
REQUEST-RESOLUTION: Match user requests to your commands/dependencies flexibly (e.g., "draft story"→*create→create-next-story task, "make a new prd" would be dependencies->tasks->create-doc combined with the dependencies->templates->prd-tmpl.md), or ask for clarification if ambiguous.
IDE-FILE-RESOLUTION: Dependencies map to files as {root}/{type}/{name}, type=folder (tasks/templates/checklists/data/utils), name=file-name.
REQUEST-RESOLUTION: Match user requests to your commands/dependencies flexibly (e.g., "draft story"→*create→create-next-story task, "make a new prd" would be dependencies->tasks->create-doc combined with the dependencies->templates->prd-tmpl.md), ALWAYS ask for clarification if no clear match.
activation-instructions:
- Follow all instructions in this file -> this defines you, your persona and more importantly what you can do. STAY IN CHARACTER!
- Only read the files/tasks listed here when user selects them for execution to minimize context usage

79
tools/installer/lib/file-manager.js
View File

@@ -47,7 +47,7 @@ class FileManager {
}
}
async copyGlobPattern(pattern, sourceDir, destDir) {
async copyGlobPattern(pattern, sourceDir, destDir, rootValue = null) {
const files = glob.sync(pattern, { cwd: sourceDir });
const copied = [];
@@ -55,7 +55,17 @@ class FileManager {
const sourcePath = path.join(sourceDir, file);
const destPath = path.join(destDir, file);
if (await this.copyFile(sourcePath, destPath)) {
// Use root replacement if rootValue is provided and file needs it
const needsRootReplacement = rootValue && (file.endsWith('.md') || file.endsWith('.yaml') || file.endsWith('.yml'));
let success = false;
if (needsRootReplacement) {
success = await this.copyFileWithRootReplacement(sourcePath, destPath, rootValue);
} else {
success = await this.copyFile(sourcePath, destPath);
}
if (success) {
copied.push(file);
}
}
@@ -299,6 +309,71 @@ class FileManager {
return false;
}
}
async copyFileWithRootReplacement(source, destination, rootValue) {
try {
// Read the source file content
const fs = require('fs').promises;
const content = await fs.readFile(source, 'utf8');
// Replace {root} with the specified root value
const updatedContent = content.replace(/\{root\}/g, rootValue);
// Ensure directory exists
await this.ensureDirectory(path.dirname(destination));
// Write the updated content
await fs.writeFile(destination, updatedContent, 'utf8');
return true;
} catch (error) {
await initializeModules();
console.error(chalk.red(`Failed to copy ${source} with root replacement:`), error.message);
return false;
}
}
async copyDirectoryWithRootReplacement(source, destination, rootValue, fileExtensions = ['.md', '.yaml', '.yml']) {
try {
await initializeModules(); // Ensure chalk is initialized
await this.ensureDirectory(destination);
// Get all files in source directory
const files = glob.sync('**/*', {
cwd: source,
nodir: true
});
let replacedCount = 0;
for (const file of files) {
const sourcePath = path.join(source, file);
const destPath = path.join(destination, file);
// Check if this file type should have {root} replacement
const shouldReplace = fileExtensions.some(ext => file.endsWith(ext));
if (shouldReplace) {
if (await this.copyFileWithRootReplacement(sourcePath, destPath, rootValue)) {
replacedCount++;
}
} else {
// Regular copy for files that don't need replacement
await this.copyFile(sourcePath, destPath);
}
}
if (replacedCount > 0) {
console.log(chalk.dim(` Processed ${replacedCount} files with {root} replacement`));
}
return true;
} catch (error) {
await initializeModules();
console.error(chalk.red(`Failed to copy directory ${source} with root replacement:`), error.message);
return false;
}
}
}
module.exports = new FileManager();

79
tools/installer/lib/installer.js
View File

@@ -244,7 +244,7 @@ class Installer {
spinner.text = "Copying complete .bmad-core folder...";
const sourceDir = configLoader.getBmadCorePath();
const bmadCoreDestDir = path.join(installDir, ".bmad-core");
await fileManager.copyDirectory(sourceDir, bmadCoreDestDir);
await fileManager.copyDirectoryWithRootReplacement(sourceDir, bmadCoreDestDir, ".bmad-core");
// Copy common/ items to .bmad-core
spinner.text = "Copying common utilities...";
@@ -263,7 +263,7 @@ class Installer {
// Single agent installation
spinner.text = `Installing ${config.agent} agent...`;
// Copy agent file
// Copy agent file with {root} replacement
const agentPath = configLoader.getAgentPath(config.agent);
const destAgentPath = path.join(
installDir,
@@ -271,7 +271,7 @@ class Installer {
"agents",
`${config.agent}.md`
);
await fileManager.copyFile(agentPath, destAgentPath);
await fileManager.copyFileWithRootReplacement(agentPath, destAgentPath, ".bmad-core");
files.push(`.bmad-core/agents/${config.agent}.md`);
// Copy dependencies
@@ -284,15 +284,16 @@ class Installer {
spinner.text = `Copying dependency: ${dep}`;
if (dep.includes("*")) {
// Handle glob patterns
// Handle glob patterns with {root} replacement
const copiedFiles = await fileManager.copyGlobPattern(
dep.replace(".bmad-core/", ""),
sourceBase,
path.join(installDir, ".bmad-core")
path.join(installDir, ".bmad-core"),
".bmad-core"
);
files.push(...copiedFiles.map(f => `.bmad-core/${f}`));
} else {
// Handle single files
// Handle single files with {root} replacement if needed
const sourcePath = path.join(
sourceBase,
dep.replace(".bmad-core/", "")
@@ -302,7 +303,16 @@ class Installer {
dep
);
if (await fileManager.copyFile(sourcePath, destPath)) {
const needsRootReplacement = dep.endsWith('.md') || dep.endsWith('.yaml') || dep.endsWith('.yml');
let success = false;
if (needsRootReplacement) {
success = await fileManager.copyFileWithRootReplacement(sourcePath, destPath, ".bmad-core");
} else {
success = await fileManager.copyFile(sourcePath, destPath);
}
if (success) {
files.push(dep);
}
}
@@ -325,19 +335,29 @@ class Installer {
spinner.text = `Copying team dependency: ${dep}`;
if (dep.includes("*")) {
// Handle glob patterns
// Handle glob patterns with {root} replacement
const copiedFiles = await fileManager.copyGlobPattern(
dep.replace(".bmad-core/", ""),
sourceBase,
path.join(installDir, ".bmad-core")
path.join(installDir, ".bmad-core"),
".bmad-core"
);
files.push(...copiedFiles.map(f => `.bmad-core/${f}`));
} else {
// Handle single files
// Handle single files with {root} replacement if needed
const sourcePath = path.join(sourceBase, dep.replace(".bmad-core/", ""));
const destPath = path.join(installDir, dep);
if (await fileManager.copyFile(sourcePath, destPath)) {
const needsRootReplacement = dep.endsWith('.md') || dep.endsWith('.yaml') || dep.endsWith('.yml');
let success = false;
if (needsRootReplacement) {
success = await fileManager.copyFileWithRootReplacement(sourcePath, destPath, ".bmad-core");
} else {
success = await fileManager.copyFile(sourcePath, destPath);
}
if (success) {
files.push(dep);
}
}
@@ -1172,32 +1192,41 @@ class Installer {
nodir: true
});
// Copy each file to the expansion pack's dot folder
// Copy each file to the expansion pack's dot folder with {root} replacement
for (const file of files) {
const sourcePath = path.join(sourceFolder, file);
const destPath = path.join(expansionDotFolder, folder, file);
if (await fileManager.copyFile(sourcePath, destPath)) {
const needsRootReplacement = file.endsWith('.md') || file.endsWith('.yaml') || file.endsWith('.yml');
let success = false;
if (needsRootReplacement) {
success = await fileManager.copyFileWithRootReplacement(sourcePath, destPath, `.${packId}`);
} else {
success = await fileManager.copyFile(sourcePath, destPath);
}
if (success) {
installedFiles.push(path.join(`.${packId}`, folder, file));
}
}
}
}
// Copy config.yaml
// Copy config.yaml with {root} replacement
const configPath = path.join(expansionPackDir, 'config.yaml');
if (await fileManager.pathExists(configPath)) {
const configDestPath = path.join(expansionDotFolder, 'config.yaml');
if (await fileManager.copyFile(configPath, configDestPath)) {
if (await fileManager.copyFileWithRootReplacement(configPath, configDestPath, `.${packId}`)) {
installedFiles.push(path.join(`.${packId}`, 'config.yaml'));
}
}
// Copy README if it exists
// Copy README if it exists with {root} replacement
const readmePath = path.join(expansionPackDir, 'README.md');
if (await fileManager.pathExists(readmePath)) {
const readmeDestPath = path.join(expansionDotFolder, 'README.md');
if (await fileManager.copyFile(readmePath, readmeDestPath)) {
if (await fileManager.copyFileWithRootReplacement(readmePath, readmeDestPath, `.${packId}`)) {
installedFiles.push(path.join(`.${packId}`, 'README.md'));
}
}
@@ -1258,7 +1287,7 @@ class Installer {
const yamlContent = extractYamlFromAgent(agentContent);
if (yamlContent) {
try {
const agentConfig = yaml.parse(yamlContent);
const agentConfig = yaml.load(yamlContent);
const dependencies = agentConfig.dependencies || {};
// Check for core dependencies (those that don't exist in the expansion pack)
@@ -1277,9 +1306,9 @@ class Installer {
if (await fileManager.pathExists(coreDepPath)) {
spinner.text = `Copying core dependency ${dep} for ${packId}...`;
// Copy from core to expansion pack dot folder
// Copy from core to expansion pack dot folder with {root} replacement
const destPath = path.join(expansionDotFolder, depType, depFileName);
await fileManager.copyFile(coreDepPath, destPath);
await fileManager.copyFileWithRootReplacement(coreDepPath, destPath, `.${packId}`);
console.log(chalk.dim(` Added core dependency: ${depType}/${depFileName}`));
} else {
@@ -1321,7 +1350,7 @@ class Installer {
const teamContent = await fs.readFile(teamPath, 'utf8');
try {
const teamConfig = yaml.parse(teamContent);
const teamConfig = yaml.load(teamContent);
const agents = teamConfig.agents || [];
// Add bmad-orchestrator if not present (required for all teams)
@@ -1338,9 +1367,9 @@ class Installer {
if (await fileManager.pathExists(coreAgentPath)) {
spinner.text = `Copying core agent ${agentId} for ${packId}...`;
// Copy agent file
// Copy agent file with {root} replacement
const destPath = path.join(expansionDotFolder, 'agents', `${agentId}.md`);
await fileManager.copyFile(coreAgentPath, destPath);
await fileManager.copyFileWithRootReplacement(coreAgentPath, destPath, `.${packId}`);
existingAgents.add(agentId);
console.log(chalk.dim(` Added core agent: ${agentId}`));
@@ -1352,7 +1381,7 @@ class Installer {
if (yamlContent) {
try {
const agentConfig = yaml.parse(yamlContent);
const agentConfig = yaml.load(yamlContent);
const dependencies = agentConfig.dependencies || {};
// Copy all dependencies for this agent
@@ -1370,7 +1399,7 @@ class Installer {
if (await fileManager.pathExists(coreDepPath)) {
const destDepPath = path.join(expansionDotFolder, depType, depFileName);
await fileManager.copyFile(coreDepPath, destDepPath);
await fileManager.copyFileWithRootReplacement(coreDepPath, destDepPath, `.${packId}`);
console.log(chalk.dim(` Added agent dependency: ${depType}/${depFileName}`));
} else {
// Try common folder