agentvibes 2.5.0 → 2.7.0

package/.bmad/core/workflows/party-mode/instructions.md

@@ -0,0 +1,202 @@
+# Party Mode - Multi-Agent Discussion Instructions
+
+<critical>The workflow execution engine is governed by: {project_root}/.bmad/core/tasks/workflow.xml</critical>
+<critical>This workflow orchestrates group discussions between all installed BMAD agents</critical>
+
+<workflow>
+
+<step n="1" goal="Load Agent Manifest and Configurations">
+  <action>Load the agent manifest CSV from {{agent_manifest}}</action>
+  <action>Parse CSV to extract all agent entries with their condensed information:</action>
+    - name (agent identifier)
+    - displayName (agent's persona name)
+    - title (formal position)
+    - icon (visual identifier)
+    - role (capabilities summary)
+    - identity (background/expertise)
+    - communicationStyle (how they communicate)
+    - principles (decision-making philosophy)
+    - module (source module)
+    - path (file location)
+
+<action>Build complete agent roster with merged personalities</action>
+<action>Store agent data for use in conversation orchestration</action>
+</step>
+
+<step n="2" goal="Initialize Party Mode">
+  <action>Announce party mode activation with enthusiasm</action>
+  <action>List all participating agents with their merged information:</action>
+  <format>
+    🎉 PARTY MODE ACTIVATED! 🎉
+    All agents are here for a group discussion!
+
+    Participating agents:
+    [For each agent in roster:]
+    - [Agent Name] ([Title]): [Role from merged data]
+
+    [Total count] agents ready to collaborate!
+
+    What would you like to discuss with the team?
+
+  </format>
+  <action>Wait for user to provide initial topic or question</action>
+</step>
+
+<step n="3" goal="Orchestrate Multi-Agent Discussion" repeat="until-exit">
+  <action>For each user message or topic:</action>
+
+  <substep n="3a" goal="Determine Relevant Agents">
+    <action>Analyze the user's message/question</action>
+    <action>Identify which agents would naturally respond based on:</action>
+      - Their role and capabilities (from merged data)
+      - Their stated principles
+      - Their memories/context if relevant
+      - Their collaboration patterns
+    <action>Select 2-3 most relevant agents for this response</action>
+    <note>If user addresses specific agent by name, prioritize that agent</note>
+  </substep>
+
+  <substep n="3b" goal="Generate In-Character Responses">
+    <action>For each selected agent, generate authentic response:</action>
+    <action>Use the agent's merged personality data:</action>
+      - Apply their communicationStyle exactly
+      - Reflect their principles in reasoning
+      - Draw from their identity and role for expertise
+      - Maintain their unique voice and perspective
+
+    <action>Enable natural cross-talk between agents:</action>
+      - Agents can reference each other by name
+      - Agents can build on previous points
+      - Agents can respectfully disagree or offer alternatives
+      - Agents can ask follow-up questions to each other
+
+  </substep>
+
+  <substep n="3c" goal="Handle Questions and Interactions">
+    <check if="an agent asks the user a direct question">
+      <action>Clearly highlight the question</action>
+      <action>End that round of responses</action>
+      <action>Display: "[Agent Name]: [Their question]"</action>
+      <action>Display: "[Awaiting user response...]"</action>
+      <action>WAIT for user input before continuing</action>
+    </check>
+
+    <check if="agents ask each other questions">
+      <action>Allow natural back-and-forth in the same response round</action>
+      <action>Maintain conversational flow</action>
+    </check>
+
+    <check if="discussion becomes circular or repetitive">
+      <action>The BMad Master will summarize</action>
+      <action>Redirect to new aspects or ask for user guidance</action>
+    </check>
+
+  </substep>
+
+  <substep n="3d" goal="Format and Present Responses">
+    <action>For each agent response, output text THEN trigger their voice:</action>
+
+    <procedure>
+      1. Output the agent's text in format: [Icon Emoji] [Agent Name]: [dialogue]
+      2. If AgentVibes party mode is enabled, immediately trigger TTS with agent's voice:
+         - Use Bash tool: `.claude/hooks/bmad-speak.sh "[Agent Name]" "[dialogue]"`
+         - This speaks the dialogue with the agent's unique voice
+         - Run in background (&) to not block next agent
+      3. Repeat for each agent in the response
+    </procedure>
+
+    <format>
+      [Icon Emoji] [Agent Name]: [Their response in their voice/style]
+
+      [Icon Emoji] [Another Agent]: [Their response, potentially referencing the first]
+
+      [Icon Emoji] [Third Agent if selected]: [Their contribution]
+    </format>
+    <example>
+      🏗️ [Winston]: I recommend using microservices for better scalability.
+      [Bash: .claude/hooks/bmad-speak.sh "Winston" "I recommend using microservices for better scalability."]
+
+      📋 [John]: But a monolith would get us to market faster for MVP.
+      [Bash: .claude/hooks/bmad-speak.sh "John" "But a monolith would get us to market faster for MVP."]
+    </example>
+
+    <action>Maintain spacing between agents for readability</action>
+    <action>Preserve each agent's unique voice throughout</action>
+    <action>Always include the agent's icon emoji from the manifest before their name</action>
+    <action>Trigger TTS for each agent immediately after outputting their text</action>
+
+  </substep>
+
+  <substep n="3e" goal="Check for Exit Conditions">
+    <check if="user message contains any {{exit_triggers}}">
+      <action>Have agents provide brief farewells in character</action>
+      <action>Thank user for the discussion</action>
+      <goto step="4">Exit party mode</goto>
+    </check>
+
+    <check if="user seems done or conversation naturally concludes">
+      <ask>Would you like to continue the discussion or end party mode?</ask>
+      <check if="user indicates end">
+        <goto step="4">Exit party mode</goto>
+      </check>
+    </check>
+
+  </substep>
+</step>
+
+<step n="4" goal="Exit Party Mode">
+  <action>Have 2-3 agents provide characteristic farewells to the user, and 1-2 to each other</action>
+  <format>
+    [Agent 1]: [Brief farewell in their style]
+
+    [Agent 2]: [Their goodbye]
+
+    🎊 Party Mode ended. Thanks for the great discussion!
+
+  </format>
+  <action>Exit workflow</action>
+</step>
+
+</workflow>
+
+## Role-Playing Guidelines
+
+<guidelines>
+  <guideline>Keep all responses strictly in-character based on merged personality data</guideline>
+  <guideline>Use each agent's documented communication style consistently</guideline>
+  <guideline>Reference agent memories and context when relevant</guideline>
+  <guideline>Allow natural disagreements and different perspectives</guideline>
+  <guideline>Maintain professional discourse while being engaging</guideline>
+  <guideline>Let agents reference each other naturally by name or role</guideline>
+  <guideline>Include personality-driven quirks and occasional humor</guideline>
+  <guideline>Respect each agent's expertise boundaries</guideline>
+</guidelines>
+
+## Question Handling Protocol
+
+<question-protocol>
+  <direct-to-user>
+    When agent asks user a specific question (e.g., "What's your budget?"):
+    - End that round immediately after the question
+    - Clearly highlight the questioning agent and their question
+    - Wait for user response before any agent continues
+  </direct-to-user>
+
+  <rhetorical>
+    Agents can ask rhetorical or thinking-aloud questions without pausing
+  </rhetorical>
+
+  <inter-agent>
+    Agents can question each other and respond naturally within same round
+  </inter-agent>
+</question-protocol>
+
+## Moderation Notes
+
+<moderation>
+  <note>If discussion becomes circular, have bmad-master summarize and redirect</note>
+  <note>If user asks for specific agent, let that agent take primary lead</note>
+  <note>Balance fun and productivity based on conversation tone</note>
+  <note>Ensure all agents stay true to their merged personalities</note>
+  <note>Exit gracefully when user indicates completion</note>
+</moderation>

package/.bmad/core/workflows/party-mode/workflow.yaml

@@ -0,0 +1,28 @@
+# Party Mode - Multi-Agent Group Discussion Workflow
+name: "party-mode"
+description: "Orchestrates group discussions between all installed BMAD agents, enabling natural multi-agent conversations"
+author: "BMad"
+
+# Critical data sources - manifest and config overrides
+agent_manifest: "{project-root}/.bmad/_cfg/agent-manifest.csv"
+date: system-generated
+
+# This is an interactive action workflow - no template output
+template: false
+instructions: "{project-root}/.bmad/core/workflows/party-mode/instructions.md"
+
+# Exit conditions
+exit_triggers:
+  - "*exit"
+
+standalone: true
+
+web_bundle:
+  name: "party-mode"
+  description: "Orchestrates group discussions between all installed BMAD agents, enabling natural multi-agent conversations"
+  author: "BMad"
+  instructions: ".bmad/core/workflows/party-mode/instructions.md"
+  agent_manifest: ".bmad/_cfg/agent-manifest.csv"
+  web_bundle_files:
+    - ".bmad/core/workflows/party-mode/instructions.md"
+    - ".bmad/_cfg/agent-manifest.csv"

package/.bmad/docs/claude-code-instructions.md

@@ -0,0 +1,25 @@
+# BMAD Method - Claude Code Instructions
+
+## Activating Agents
+
+BMAD agents are installed as slash commands in `.claude/commands/bmad/`.
+
+### How to Use
+
+1. **Type Slash Command**: Start with `/` to see available commands
+2. **Select Agent**: Type `/bmad-{agent-name}` (e.g., `/bmad-dev`)
+3. **Execute**: Press Enter to activate that agent persona
+
+### Examples
+
+```
+/bmad:bmm:agents:dev - Activate development agent
+/bmad:bmm:agents:architect - Activate architect agent
+/bmad:bmm:workflows:dev-story - Execute dev-story workflow
+```
+
+### Notes
+
+- Commands are autocompleted when you type `/`
+- Agent remains active for the conversation
+- Start a new conversation to switch agents

package/.claude/commands/agent-vibes-bmad-party.md

@@ -0,0 +1,117 @@
+---
+command: agent-vibes:bmad-party
+description: Control BMAD party mode voice integration (enable/disable/status)
+handler: bash .claude/hooks/bmad-party-manager.sh
+---
+
+Enable or disable BMAD party mode voice integration where each agent speaks with their unique voice during multi-agent conversations.
+
+## Usage
+
+- `/agent-vibes:bmad-party` - Show current status
+- `/agent-vibes:bmad-party status` - Show current status
+- `/agent-vibes:bmad-party enable` - Enable party mode voices
+- `/agent-vibes:bmad-party disable` - Disable party mode voices
+
+## What is Party Mode Voice Integration?
+
+When BMAD's party mode (`/bmad:core:workflows:party-mode`) is active, multiple agents collaborate on your questions. With this feature enabled, each agent speaks their responses with their unique assigned voice:
+
+- **Winston (Architect)** speaks with Michael's voice
+- **John (PM)** speaks with Jessica Anne Bogart's voice
+- **Amelia (Dev)** speaks with Matthew Schmitz's voice
+- And so on...
+
+## Auto-Enable Behavior
+
+**This feature is automatically enabled when:**
+1. BMAD v6 is installed (`.bmad/_cfg/agent-manifest.csv` exists)
+2. AgentVibes BMAD voice plugin is enabled
+
+**No manual configuration needed!** Just run party mode and each agent will speak with their voice.
+
+## How to Disable
+
+If you prefer party mode without voice switching:
+
+```bash
+/agent-vibes:bmad-party disable
+```
+
+This creates `.claude/plugins/bmad-party-mode-disabled.flag` to opt-out.
+
+## How It Works
+
+The integration detects agent responses in the format:
+
+```
+[Agent Name]: Their dialogue here
+```
+
+When detected, it:
+1. Extracts the agent's display name (e.g., "Winston", "John")
+2. Maps it to their agent ID using `.bmad/_cfg/agent-manifest.csv`
+3. Looks up their voice from `.claude/plugins/bmad-voices.md`
+4. Speaks their dialogue with that specific voice
+
+## Example
+
+**Before (silent text):**
+```
+[Winston]: I recommend microservices for scalability
+[John]: But monolith is faster to market for MVP
+[Amelia]: I can implement either approach
+```
+
+**After (with voices):**
+```
+[Winston speaks with Michael voice]: I recommend microservices for scalability
+[John speaks with Jessica Anne Bogart voice]: But monolith is faster to market for MVP
+[Amelia speaks with Matthew Schmitz voice]: I can implement either approach
+```
+
+## Voice Mappings
+
+See current agent-to-voice mappings:
+```bash
+/agent-vibes:bmad status
+```
+
+Edit voice assignments in:
+```
+.claude/plugins/bmad-voices.md
+```
+
+## Requirements
+
+- BMAD v6-alpha or later
+- AgentVibes with BMAD plugin enabled
+- Piper or ElevenLabs TTS provider configured
+
+## Troubleshooting
+
+**Party mode voices not working?**
+
+1. Check BMAD is installed: `ls .bmad/_cfg/agent-manifest.csv`
+2. Check voice plugin enabled: `ls .claude/plugins/bmad-voices-enabled.flag`
+3. Check party mode not disabled: `ls .claude/plugins/bmad-party-mode-disabled.flag`
+4. View status: `/agent-vibes:bmad-party status`
+
+**Wrong voices playing?**
+
+Check voice mappings: `/agent-vibes:bmad status`
+
+Edit mappings in: `.claude/plugins/bmad-voices.md`
+
+## Related Commands
+
+- `/bmad:core:workflows:party-mode` - Start BMAD party mode
+- `/agent-vibes:bmad` - Manage BMAD voice plugin
+- `/agent-vibes:switch` - Change your default voice
+- `/agent-vibes:provider` - Switch TTS provider
+
+---
+
+**Implementation:** Issue #33
+**Auto-enabled:** Yes (for BMAD users)
+**Opt-out:** Available via disable command

package/.claude/commands/bmad/bmm/agents/analyst.md

@@ -0,0 +1,14 @@
+---
+name: 'analyst'
+description: 'analyst agent'
+---
+
+You must fully embody this agent's persona and follow all activation instructions exactly as specified. NEVER break character until given an exit command.
+
+<agent-activation CRITICAL="TRUE">
+1. LOAD the FULL agent file from @.bmad/bmm/agents/analyst.md
+2. READ its entire contents - this contains the complete agent persona, menu, and instructions
+3. Execute ALL activation steps exactly as written in the agent file
+4. Follow the agent's persona and menu system precisely
+5. Stay in character throughout the session
+</agent-activation>

package/.claude/commands/bmad/bmm/agents/architect.md

@@ -0,0 +1,14 @@
+---
+name: 'architect'
+description: 'architect agent'
+---
+
+You must fully embody this agent's persona and follow all activation instructions exactly as specified. NEVER break character until given an exit command.
+
+<agent-activation CRITICAL="TRUE">
+1. LOAD the FULL agent file from @.bmad/bmm/agents/architect.md
+2. READ its entire contents - this contains the complete agent persona, menu, and instructions
+3. Execute ALL activation steps exactly as written in the agent file
+4. Follow the agent's persona and menu system precisely
+5. Stay in character throughout the session
+</agent-activation>

package/.claude/commands/bmad/bmm/agents/dev.md

@@ -0,0 +1,14 @@
+---
+name: 'dev'
+description: 'dev agent'
+---
+
+You must fully embody this agent's persona and follow all activation instructions exactly as specified. NEVER break character until given an exit command.
+
+<agent-activation CRITICAL="TRUE">
+1. LOAD the FULL agent file from @.bmad/bmm/agents/dev.md
+2. READ its entire contents - this contains the complete agent persona, menu, and instructions
+3. Execute ALL activation steps exactly as written in the agent file
+4. Follow the agent's persona and menu system precisely
+5. Stay in character throughout the session
+</agent-activation>

package/.claude/commands/bmad/bmm/agents/frame-expert.md

@@ -0,0 +1,14 @@
+---
+name: 'frame-expert'
+description: 'frame-expert agent'
+---
+
+You must fully embody this agent's persona and follow all activation instructions exactly as specified. NEVER break character until given an exit command.
+
+<agent-activation CRITICAL="TRUE">
+1. LOAD the FULL agent file from @.bmad/bmm/agents/frame-expert.md
+2. READ its entire contents - this contains the complete agent persona, menu, and instructions
+3. Execute ALL activation steps exactly as written in the agent file
+4. Follow the agent's persona and menu system precisely
+5. Stay in character throughout the session
+</agent-activation>

package/.claude/commands/bmad/bmm/agents/pm.md

@@ -0,0 +1,14 @@
+---
+name: 'pm'
+description: 'pm agent'
+---
+
+You must fully embody this agent's persona and follow all activation instructions exactly as specified. NEVER break character until given an exit command.
+
+<agent-activation CRITICAL="TRUE">
+1. LOAD the FULL agent file from @.bmad/bmm/agents/pm.md
+2. READ its entire contents - this contains the complete agent persona, menu, and instructions
+3. Execute ALL activation steps exactly as written in the agent file
+4. Follow the agent's persona and menu system precisely
+5. Stay in character throughout the session
+</agent-activation>

package/.claude/commands/bmad/bmm/agents/sm.md

@@ -0,0 +1,14 @@
+---
+name: 'sm'
+description: 'sm agent'
+---
+
+You must fully embody this agent's persona and follow all activation instructions exactly as specified. NEVER break character until given an exit command.
+
+<agent-activation CRITICAL="TRUE">
+1. LOAD the FULL agent file from @.bmad/bmm/agents/sm.md
+2. READ its entire contents - this contains the complete agent persona, menu, and instructions
+3. Execute ALL activation steps exactly as written in the agent file
+4. Follow the agent's persona and menu system precisely
+5. Stay in character throughout the session
+</agent-activation>

package/.claude/commands/bmad/bmm/agents/tea.md

@@ -0,0 +1,14 @@
+---
+name: 'tea'
+description: 'tea agent'
+---
+
+You must fully embody this agent's persona and follow all activation instructions exactly as specified. NEVER break character until given an exit command.
+
+<agent-activation CRITICAL="TRUE">
+1. LOAD the FULL agent file from @.bmad/bmm/agents/tea.md
+2. READ its entire contents - this contains the complete agent persona, menu, and instructions
+3. Execute ALL activation steps exactly as written in the agent file
+4. Follow the agent's persona and menu system precisely
+5. Stay in character throughout the session
+</agent-activation>

package/.claude/commands/bmad/bmm/agents/tech-writer.md

@@ -0,0 +1,14 @@
+---
+name: 'tech-writer'
+description: 'tech-writer agent'
+---
+
+You must fully embody this agent's persona and follow all activation instructions exactly as specified. NEVER break character until given an exit command.
+
+<agent-activation CRITICAL="TRUE">
+1. LOAD the FULL agent file from @.bmad/bmm/agents/tech-writer.md
+2. READ its entire contents - this contains the complete agent persona, menu, and instructions
+3. Execute ALL activation steps exactly as written in the agent file
+4. Follow the agent's persona and menu system precisely
+5. Stay in character throughout the session
+</agent-activation>

package/.claude/commands/bmad/bmm/agents/ux-designer.md

@@ -0,0 +1,14 @@
+---
+name: 'ux-designer'
+description: 'ux-designer agent'
+---
+
+You must fully embody this agent's persona and follow all activation instructions exactly as specified. NEVER break character until given an exit command.
+
+<agent-activation CRITICAL="TRUE">
+1. LOAD the FULL agent file from @.bmad/bmm/agents/ux-designer.md
+2. READ its entire contents - this contains the complete agent persona, menu, and instructions
+3. Execute ALL activation steps exactly as written in the agent file
+4. Follow the agent's persona and menu system precisely
+5. Stay in character throughout the session
+</agent-activation>

package/.claude/commands/bmad/bmm/workflows/architecture.md

@@ -0,0 +1,13 @@
+---
+description: 'Collaborative architectural decision facilitation for AI-agent consistency. Replaces template-driven architecture with intelligent, adaptive conversation that produces a decision-focused architecture document optimized for preventing agent conflicts.'
+---
+
+IT IS CRITICAL THAT YOU FOLLOW THESE STEPS - while staying in character as the current agent persona you may have loaded:
+
+<steps CRITICAL="TRUE">
+1. Always LOAD the FULL @.bmad/core/tasks/workflow.xml
+2. READ its entire contents - this is the CORE OS for EXECUTING the specific workflow-config @.bmad/bmm/workflows/3-solutioning/architecture/workflow.yaml
+3. Pass the yaml path .bmad/bmm/workflows/3-solutioning/architecture/workflow.yaml as 'workflow-config' parameter to the workflow.xml instructions
+4. Follow workflow.xml instructions EXACTLY as written to process and follow the specific workflow config and its instructions
+5. Save outputs after EACH section when generating any documents from templates
+</steps>

package/.claude/commands/bmad/bmm/workflows/brainstorm-project.md

@@ -0,0 +1,13 @@
+---
+description: 'Facilitate project brainstorming sessions by orchestrating the CIS brainstorming workflow with project-specific context and guidance.'
+---
+
+IT IS CRITICAL THAT YOU FOLLOW THESE STEPS - while staying in character as the current agent persona you may have loaded:
+
+<steps CRITICAL="TRUE">
+1. Always LOAD the FULL @.bmad/core/tasks/workflow.xml
+2. READ its entire contents - this is the CORE OS for EXECUTING the specific workflow-config @.bmad/bmm/workflows/1-analysis/brainstorm-project/workflow.yaml
+3. Pass the yaml path .bmad/bmm/workflows/1-analysis/brainstorm-project/workflow.yaml as 'workflow-config' parameter to the workflow.xml instructions
+4. Follow workflow.xml instructions EXACTLY as written to process and follow the specific workflow config and its instructions
+5. Save outputs after EACH section when generating any documents from templates
+</steps>

package/.claude/commands/bmad/bmm/workflows/code-review.md

@@ -0,0 +1,13 @@
+---
+description: 'Perform a Senior Developer code review on a completed story flagged Ready for Review, leveraging story-context, epic tech-spec, repo docs, MCP servers for latest best-practices, and web search as fallback. Appends structured review notes to the story.'
+---
+
+IT IS CRITICAL THAT YOU FOLLOW THESE STEPS - while staying in character as the current agent persona you may have loaded:
+
+<steps CRITICAL="TRUE">
+1. Always LOAD the FULL @.bmad/core/tasks/workflow.xml
+2. READ its entire contents - this is the CORE OS for EXECUTING the specific workflow-config @.bmad/bmm/workflows/4-implementation/code-review/workflow.yaml
+3. Pass the yaml path .bmad/bmm/workflows/4-implementation/code-review/workflow.yaml as 'workflow-config' parameter to the workflow.xml instructions
+4. Follow workflow.xml instructions EXACTLY as written to process and follow the specific workflow config and its instructions
+5. Save outputs after EACH section when generating any documents from templates
+</steps>

package/.claude/commands/bmad/bmm/workflows/correct-course.md

@@ -0,0 +1,13 @@
+---
+description: 'Navigate significant changes during sprint execution by analyzing impact, proposing solutions, and routing for implementation'
+---
+
+IT IS CRITICAL THAT YOU FOLLOW THESE STEPS - while staying in character as the current agent persona you may have loaded:
+
+<steps CRITICAL="TRUE">
+1. Always LOAD the FULL @.bmad/core/tasks/workflow.xml
+2. READ its entire contents - this is the CORE OS for EXECUTING the specific workflow-config @.bmad/bmm/workflows/4-implementation/correct-course/workflow.yaml
+3. Pass the yaml path .bmad/bmm/workflows/4-implementation/correct-course/workflow.yaml as 'workflow-config' parameter to the workflow.xml instructions
+4. Follow workflow.xml instructions EXACTLY as written to process and follow the specific workflow config and its instructions
+5. Save outputs after EACH section when generating any documents from templates
+</steps>

package/.claude/commands/bmad/bmm/workflows/create-dataflow.md

@@ -0,0 +1,13 @@
+---
+description: 'Create data flow diagrams (DFD) in Excalidraw format'
+---
+
+IT IS CRITICAL THAT YOU FOLLOW THESE STEPS - while staying in character as the current agent persona you may have loaded:
+
+<steps CRITICAL="TRUE">
+1. Always LOAD the FULL @.bmad/core/tasks/workflow.xml
+2. READ its entire contents - this is the CORE OS for EXECUTING the specific workflow-config @.bmad/bmm/workflows/frame-expert/create-dataflow/workflow.yaml
+3. Pass the yaml path .bmad/bmm/workflows/frame-expert/create-dataflow/workflow.yaml as 'workflow-config' parameter to the workflow.xml instructions
+4. Follow workflow.xml instructions EXACTLY as written to process and follow the specific workflow config and its instructions
+5. Save outputs after EACH section when generating any documents from templates
+</steps>

package/.claude/commands/bmad/bmm/workflows/create-diagram.md

@@ -0,0 +1,13 @@
+---
+description: 'Create system architecture diagrams, ERDs, UML diagrams, or general technical diagrams in Excalidraw format'
+---
+
+IT IS CRITICAL THAT YOU FOLLOW THESE STEPS - while staying in character as the current agent persona you may have loaded:
+
+<steps CRITICAL="TRUE">
+1. Always LOAD the FULL @.bmad/core/tasks/workflow.xml
+2. READ its entire contents - this is the CORE OS for EXECUTING the specific workflow-config @.bmad/bmm/workflows/frame-expert/create-diagram/workflow.yaml
+3. Pass the yaml path .bmad/bmm/workflows/frame-expert/create-diagram/workflow.yaml as 'workflow-config' parameter to the workflow.xml instructions
+4. Follow workflow.xml instructions EXACTLY as written to process and follow the specific workflow config and its instructions
+5. Save outputs after EACH section when generating any documents from templates
+</steps>

package/.claude/commands/bmad/bmm/workflows/create-epics-and-stories.md

@@ -0,0 +1,13 @@
+---
+description: 'Transform PRD requirements into bite-sized stories organized into deliverable functional epics. This workflow takes a Product Requirements Document (PRD) and breaks it down into epics and user stories that can be easily assigned to development teams. It ensures that all functional requirements are captured in a structured format, making it easier for teams to understand and implement the necessary features.'
+---
+
+IT IS CRITICAL THAT YOU FOLLOW THESE STEPS - while staying in character as the current agent persona you may have loaded:
+
+<steps CRITICAL="TRUE">
+1. Always LOAD the FULL @.bmad/core/tasks/workflow.xml
+2. READ its entire contents - this is the CORE OS for EXECUTING the specific workflow-config @.bmad/bmm/workflows/2-plan-workflows/create-epics-and-stories/workflow.yaml
+3. Pass the yaml path .bmad/bmm/workflows/2-plan-workflows/create-epics-and-stories/workflow.yaml as 'workflow-config' parameter to the workflow.xml instructions
+4. Follow workflow.xml instructions EXACTLY as written to process and follow the specific workflow config and its instructions
+5. Save outputs after EACH section when generating any documents from templates
+</steps>

package/.claude/commands/bmad/bmm/workflows/create-flowchart.md

@@ -0,0 +1,13 @@
+---
+description: 'Create a flowchart visualization in Excalidraw format for processes, pipelines, or logic flows'
+---
+
+IT IS CRITICAL THAT YOU FOLLOW THESE STEPS - while staying in character as the current agent persona you may have loaded:
+
+<steps CRITICAL="TRUE">
+1. Always LOAD the FULL @.bmad/core/tasks/workflow.xml
+2. READ its entire contents - this is the CORE OS for EXECUTING the specific workflow-config @.bmad/bmm/workflows/frame-expert/create-flowchart/workflow.yaml
+3. Pass the yaml path .bmad/bmm/workflows/frame-expert/create-flowchart/workflow.yaml as 'workflow-config' parameter to the workflow.xml instructions
+4. Follow workflow.xml instructions EXACTLY as written to process and follow the specific workflow config and its instructions
+5. Save outputs after EACH section when generating any documents from templates
+</steps>

package/.claude/commands/bmad/bmm/workflows/create-story.md

@@ -0,0 +1,13 @@
+---
+description: 'Create the next user story markdown from epics/PRD and architecture, using a standard template and saving to the stories folder'
+---
+
+IT IS CRITICAL THAT YOU FOLLOW THESE STEPS - while staying in character as the current agent persona you may have loaded:
+
+<steps CRITICAL="TRUE">
+1. Always LOAD the FULL @.bmad/core/tasks/workflow.xml
+2. READ its entire contents - this is the CORE OS for EXECUTING the specific workflow-config @.bmad/bmm/workflows/4-implementation/create-story/workflow.yaml
+3. Pass the yaml path .bmad/bmm/workflows/4-implementation/create-story/workflow.yaml as 'workflow-config' parameter to the workflow.xml instructions
+4. Follow workflow.xml instructions EXACTLY as written to process and follow the specific workflow config and its instructions
+5. Save outputs after EACH section when generating any documents from templates
+</steps>