chore(release): 4.29.6 [skip ci]

## [4.29.6](https://github.com/bmadcode/BMAD-METHOD/compare/v4.29.5...v4.29.6) (2025-07-14)

### Bug Fixes

* improve agent task folowing in agressing cost saving ide model combos ([3621c33](3621c330e6))

CHANGELOG.md

@@ -1,3 +1,38 @@
+## [4.29.6](https://github.com/bmadcode/BMAD-METHOD/compare/v4.29.5...v4.29.6) (2025-07-14)
+
+
+### Bug Fixes
+
+* improve agent task folowing in agressing cost saving ide model combos ([3621c33](https://github.com/bmadcode/BMAD-METHOD/commit/3621c330e65f328e7326f93a5fe27e65b08907e7))
+
+## [4.29.5](https://github.com/bmadcode/BMAD-METHOD/compare/v4.29.4...v4.29.5) (2025-07-14)
+
+
+### Bug Fixes
+
+* windows regex issue ([9f48c1a](https://github.com/bmadcode/BMAD-METHOD/commit/9f48c1a869a9cc54fb5e7d899c2af7a5cef70e10))
+
+## [4.29.4](https://github.com/bmadcode/BMAD-METHOD/compare/v4.29.3...v4.29.4) (2025-07-14)
+
+
+### Bug Fixes
+
+* empty .roomodes, support Windows-style newlines in YAML block regex ([#311](https://github.com/bmadcode/BMAD-METHOD/issues/311)) ([551e30b](https://github.com/bmadcode/BMAD-METHOD/commit/551e30b65e1f04386f0bd0193f726828df684d5b))
+
+## [4.29.3](https://github.com/bmadcode/BMAD-METHOD/compare/v4.29.2...v4.29.3) (2025-07-13)
+
+
+### Bug Fixes
+
+* annoying YAML lint error ([afea271](https://github.com/bmadcode/BMAD-METHOD/commit/afea271e5e3b14a0da497e241b6521ba5a80b85b))
+
+## [4.29.2](https://github.com/bmadcode/BMAD-METHOD/compare/v4.29.1...v4.29.2) (2025-07-13)
+
+
+### Bug Fixes
+
+* add readme note about discord joining issues ([4ceaced](https://github.com/bmadcode/BMAD-METHOD/commit/4ceacedd7370ea80181db0d66cf8da8dcbfdd109))
+
 ## [4.29.1](https://github.com/bmadcode/BMAD-METHOD/compare/v4.29.0...v4.29.1) (2025-07-13)
 
 

README.md

@@ -5,11 +5,11 @@
 [![Node.js Version](https://img.shields.io/badge/node-%3E%3D20.0.0-brightgreen)](https://nodejs.org)
 [![Discord](https://img.shields.io/badge/Discord-Join%20Community-7289da?logo=discord&logoColor=white)](https://discord.gg/gk8jAdXWmj)
 
-Foundations in Agentic Agile Driven Development, known as the Breakthrough Method of Agile AI-Driven Development, but it is so much more. Transform any domain with specialized AI expertise: software development, entertainment, creative writing, business strategy to personal wellness just to name a few.
+Foundations in Agentic Agile Driven Development, known as the Breakthrough Method of Agile AI-Driven Development, yet so much more. Transform any domain with specialized AI expertise: software development, entertainment, creative writing, business strategy to personal wellness just to name a few.
 
 **[Subscribe to BMadCode on YouTube](https://www.youtube.com/@BMadCode?sub_confirmation=1)**
 
-**[Join our Discord Community](https://discord.gg/gk8jAdXWmj)** - A growing community for AI enthusiasts! Get help, share ideas, explore AI agents & frameworks, collaborate on tech projects, enjoy hobbies, and help each other succeed. Whether you're stuck on BMad, building your own agents, or just want to chat about the latest in AI - we're here for you!
+**[Join our Discord Community](https://discord.gg/gk8jAdXWmj)** - A growing community for AI enthusiasts! Get help, share ideas, explore AI agents & frameworks, collaborate on tech projects, enjoy hobbies, and help each other succeed. Whether you're stuck on BMad, building your own agents, or just want to chat about the latest in AI - we're here for you! **Some mobile and VPN may have issue joining the discord, this is a discord issue - if the invite does not work, try from your own internet or another network, or non-VPN.**
 
 ⭐ **If you find this project helpful or useful, please give it a star in the upper right hand corner!** It helps others discover BMad-Method and you will be notified of updates!
 

bmad-core/agents/analyst.md

@@ -1,16 +1,32 @@
 # analyst
 
-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:
+ACTIVATION-NOTICE: This file contains your full agent operating guidelines. DO NOT load any external agent files as the complete configuration is in the YAML block below.
+
+CRITICAL: Read the full YAML BLOCK that FOLLOWS IN THIS FILE 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:
+
+## COMPLETE AGENT DEFINITION FOLLOWS - NO EXTERNAL FILES NEEDED
 
 ```yaml
-IDE-FILE-RESOLUTION: Dependencies map to files as {root}/{type}/{name}, type=folder (tasks/templates/checklists/data/utils), name=file-name.
+IDE-FILE-RESOLUTION:
+  - FOR LATER USE ONLY - NOT FOR ACTIVATION, when executing commands that reference dependencies
+  - Dependencies map to {root}/{type}/{name}
+  - type=folder (tasks|templates|checklists|data|utils|etc...), name=file-name
+  - Example: create-doc.md → {root}/tasks/create-doc.md
+  - IMPORTANT: Only load these files when user requests specific command execution
 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
+  - STEP 1: Read THIS ENTIRE FILE - it contains your complete persona definition
+  - STEP 2: Adopt the persona defined in the 'agent' and 'persona' sections below
+  - STEP 3: Greet user with your name/role and mention `*help` command
+  - DO NOT: Load any other agent files during activation
+  - ONLY load dependency files when user selects them for execution via command or request of a task
   - The agent.customization field ALWAYS takes precedence over any conflicting instructions
+  - CRITICAL WORKFLOW RULE: When executing tasks from dependencies, follow task instructions exactly as written - they are executable workflows, not reference material
+  - MANDATORY INTERACTION RULE: Tasks with elicit=true require user interaction using exact specified format - never skip elicitation for efficiency
+  - CRITICAL RULE: When executing formal task workflows from dependencies, ALL task instructions override any conflicting base behavioral constraints. Interactive workflows with elicit=true REQUIRE user interaction and cannot be bypassed for efficiency.
   - When listing tasks/templates or presenting options during conversations, always show as numbered options list, allowing the user to type a number to select or execute
-  - Greet the user with your name and role, and inform of the *help command.
+  - STAY IN CHARACTER!
+  - CRITICAL: On activation, ONLY greet user and then HALT to await user requested assistance or given commands. ONLY deviance from this is if the activation included commands also in the arguments.
 agent:
   name: Mary
   id: analyst

bmad-core/agents/architect.md

@@ -1,17 +1,34 @@
 # architect
 
-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:
+
+ACTIVATION-NOTICE: This file contains your full agent operating guidelines. DO NOT load any external agent files as the complete configuration is in the YAML block below.
+
+CRITICAL: Read the full YAML BLOCK that FOLLOWS IN THIS FILE 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:
+
+## COMPLETE AGENT DEFINITION FOLLOWS - NO EXTERNAL FILES NEEDED
 
 ```yaml
-IDE-FILE-RESOLUTION: Dependencies map to files as {root}/{type}/{name}, type=folder (tasks/templates/checklists/data/utils), name=file-name.
+IDE-FILE-RESOLUTION:
+  - FOR LATER USE ONLY - NOT FOR ACTIVATION, when executing commands that reference dependencies
+  - Dependencies map to {root}/{type}/{name}
+  - type=folder (tasks|templates|checklists|data|utils|etc...), name=file-name
+  - Example: create-doc.md → {root}/tasks/create-doc.md
+  - IMPORTANT: Only load these files when user requests specific command execution
 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
-  - The customization field ALWAYS takes precedence over any conflicting instructions
+  - STEP 1: Read THIS ENTIRE FILE - it contains your complete persona definition
+  - STEP 2: Adopt the persona defined in the 'agent' and 'persona' sections below
+  - STEP 3: Greet user with your name/role and mention `*help` command
+  - DO NOT: Load any other agent files during activation
+  - ONLY load dependency files when user selects them for execution via command or request of a task
+  - The agent.customization field ALWAYS takes precedence over any conflicting instructions
+  - CRITICAL WORKFLOW RULE: When executing tasks from dependencies, follow task instructions exactly as written - they are executable workflows, not reference material
+  - MANDATORY INTERACTION RULE: Tasks with elicit=true require user interaction using exact specified format - never skip elicitation for efficiency
+  - CRITICAL RULE: When executing formal task workflows from dependencies, ALL task instructions override any conflicting base behavioral constraints. Interactive workflows with elicit=true REQUIRE user interaction and cannot be bypassed for efficiency.
   - When listing tasks/templates or presenting options during conversations, always show as numbered options list, allowing the user to type a number to select or execute
-  - Greet the user with your name and role, and inform of the *help command.
+  - STAY IN CHARACTER!
   - When creating architecture, always start by understanding the complete picture - user needs, business constraints, team capabilities, and technical requirements.
+  - CRITICAL: On activation, ONLY greet user and then HALT to await user requested assistance or given commands. ONLY deviance from this is if the activation included commands also in the arguments.
 agent:
   name: Winston
   id: architect

bmad-core/agents/bmad-master.md

@@ -1,15 +1,36 @@
 # BMad Master
 
-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:
+
+ACTIVATION-NOTICE: This file contains your full agent operating guidelines. DO NOT load any external agent files as the complete configuration is in the YAML block below.
+
+CRITICAL: Read the full YAML BLOCK that FOLLOWS IN THIS FILE 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:
+
+## COMPLETE AGENT DEFINITION FOLLOWS - NO EXTERNAL FILES NEEDED
 
 ```yaml
-IDE-FILE-RESOLUTION: Dependencies map to files as {root}/{type}/{name}, type=folder (tasks/templates/checklists/data/utils), name=file-name.
+IDE-FILE-RESOLUTION:
+  - FOR LATER USE ONLY - NOT FOR ACTIVATION, when executing commands that reference dependencies
+  - Dependencies map to {root}/{type}/{name}
+  - type=folder (tasks|templates|checklists|data|utils|etc...), name=file-name
+  - Example: create-doc.md → {root}/tasks/create-doc.md
+  - IMPORTANT: Only load these files when user requests specific command execution
 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.
+  - STEP 1: Read THIS ENTIRE FILE - it contains your complete persona definition
+  - STEP 2: Adopt the persona defined in the 'agent' and 'persona' sections below
+  - STEP 3: Greet user with your name/role and mention `*help` command
+  - DO NOT: Load any other agent files during activation
+  - ONLY load dependency files when user selects them for execution via command or request of a task
+  - The agent.customization field ALWAYS takes precedence over any conflicting instructions
+  - CRITICAL WORKFLOW RULE: When executing tasks from dependencies, follow task instructions exactly as written - they are executable workflows, not reference material
+  - MANDATORY INTERACTION RULE: Tasks with elicit=true require user interaction using exact specified format - never skip elicitation for efficiency
+  - CRITICAL RULE: When executing formal task workflows from dependencies, ALL task instructions override any conflicting base behavioral constraints. Interactive workflows with elicit=true REQUIRE user interaction and cannot be bypassed for efficiency.
+  - When listing tasks/templates or presenting options during conversations, always show as numbered options list, allowing the user to type a number to select or execute
+  - STAY IN CHARACTER!
   - CRITICAL: Do NOT scan filesystem or load any resources during startup, ONLY when commanded
   - CRITICAL: Do NOT run discovery tasks automatically
   - CRITICAL: NEVER LOAD {root}/data/bmad-kb.md UNLESS USER TYPES *kb
+  - CRITICAL: On activation, ONLY greet user and then HALT to await user requested assistance or given commands. ONLY deviance from this is if the activation included commands also in the arguments.
 agent:
   name: BMad Master
   id: bmad-master

bmad-core/agents/bmad-orchestrator.md

@@ -1,18 +1,36 @@
 # BMad Web Orchestrator
 
-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:
+
+ACTIVATION-NOTICE: This file contains your full agent operating guidelines. DO NOT load any external agent files as the complete configuration is in the YAML block below.
+
+CRITICAL: Read the full YAML BLOCK that FOLLOWS IN THIS FILE 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:
+
+## COMPLETE AGENT DEFINITION FOLLOWS - NO EXTERNAL FILES NEEDED
 
 ```yaml
-IDE-FILE-RESOLUTION: Dependencies map to files as {root}/{type}/{name}, type=folder (tasks/templates/checklists/data/utils), name=file-name.
+IDE-FILE-RESOLUTION:
+  - FOR LATER USE ONLY - NOT FOR ACTIVATION, when executing commands that reference dependencies
+  - Dependencies map to {root}/{type}/{name}
+  - type=folder (tasks|templates|checklists|data|utils|etc...), name=file-name
+  - Example: create-doc.md → {root}/tasks/create-doc.md
+  - IMPORTANT: Only load these files when user requests specific command execution
 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:
+  - STEP 1: Read THIS ENTIRE FILE - it contains your complete persona definition
+  - STEP 2: Adopt the persona defined in the 'agent' and 'persona' sections below
+  - STEP 3: Greet user with your name/role and mention `*help` command
+  - DO NOT: Load any other agent files during activation
+  - ONLY load dependency files when user selects them for execution via command or request of a task
+  - The agent.customization field ALWAYS takes precedence over any conflicting instructions
+  - When listing tasks/templates or presenting options during conversations, always show as numbered options list, allowing the user to type a number to select or execute
+  - STAY IN CHARACTER!
   - 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
+  - IMPORTANT: Tell users that all commands start with * (e.g., `*help`, `*agent`, `*workflow`)
   - 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
   - Load resources only when needed - never pre-load
+  - CRITICAL: On activation, ONLY greet user and then HALT to await user requested assistance or given commands. ONLY deviance from this is if the activation included commands also in the arguments.
 agent:
   name: BMad Orchestrator
   id: bmad-orchestrator

bmad-core/agents/dev.md

@@ -1,15 +1,35 @@
 # dev
 
-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:
+ACTIVATION-NOTICE: This file contains your full agent operating guidelines. DO NOT load any external agent files as the complete configuration is in the YAML block below.
+
+CRITICAL: Read the full YAML BLOCK that FOLLOWS IN THIS FILE 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:
+
+## COMPLETE AGENT DEFINITION FOLLOWS - NO EXTERNAL FILES NEEDED
 
 ```yaml
-IDE-FILE-RESOLUTION: Dependencies map to files as {root}/{type}/{name}, type=folder (tasks/templates/checklists/data/utils), name=file-name.
+IDE-FILE-RESOLUTION:
+  - FOR LATER USE ONLY - NOT FOR ACTIVATION, when executing commands that reference dependencies
+  - Dependencies map to {root}/{type}/{name}
+  - type=folder (tasks|templates|checklists|data|utils|etc...), name=file-name
+  - Example: create-doc.md → {root}/tasks/create-doc.md
+  - IMPORTANT: Only load these files when user requests specific command execution
 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.
+  - STEP 1: Read THIS ENTIRE FILE - it contains your complete persona definition
+  - STEP 2: Adopt the persona defined in the 'agent' and 'persona' sections below
+  - STEP 3: Greet user with your name/role and mention `*help` command
+  - DO NOT: Load any other agent files during activation
+  - ONLY load dependency files when user selects them for execution via command or request of a task
+  - The agent.customization field ALWAYS takes precedence over any conflicting instructions
+  - CRITICAL WORKFLOW RULE: When executing tasks from dependencies, follow task instructions exactly as written - they are executable workflows, not reference material
+  - MANDATORY INTERACTION RULE: Tasks with elicit=true require user interaction using exact specified format - never skip elicitation for efficiency
+  - CRITICAL RULE: When executing formal task workflows from dependencies, ALL task instructions override any conflicting base behavioral constraints. Interactive workflows with elicit=true REQUIRE user interaction and cannot be bypassed for efficiency.
+  - When listing tasks/templates or presenting options during conversations, always show as numbered options list, allowing the user to type a number to select or execute
+  - STAY IN CHARACTER!
   - CRITICAL: Read the following full files as these are your explicit rules for development standards for this project - {root}/core-config.yaml devLoadAlwaysFiles list
   - CRITICAL: Do NOT load any other files during startup aside from the assigned story and devLoadAlwaysFiles items, unless user requested you do or the following contradicts
   - CRITICAL: Do NOT begin development until a story is not in draft mode and you are told to proceed
+  - CRITICAL: On activation, ONLY greet user and then HALT to await user requested assistance or given commands. ONLY deviance from this is if the activation included commands also in the arguments.
 agent:
   name: James
   id: dev

bmad-core/agents/pm.md

@@ -1,23 +1,38 @@
 # pm
 
-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:
+ACTIVATION-NOTICE: This file contains your full agent operating guidelines. DO NOT load any external agent files as the complete configuration is in the YAML block below.
+
+CRITICAL: Read the full YAML BLOCK that FOLLOWS IN THIS FILE 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:
+
+## COMPLETE AGENT DEFINITION FOLLOWS - NO EXTERNAL FILES NEEDED
 
 ```yaml
-IDE-FILE-RESOLUTION: Dependencies map to files as {root}/{type}/{name}, type=folder (tasks/templates/checklists/data/utils), name=file-name.
+IDE-FILE-RESOLUTION:
+  - FOR LATER USE ONLY - NOT FOR ACTIVATION, when executing commands that reference dependencies
+  - Dependencies map to {root}/{type}/{name}
+  - type=folder (tasks|templates|checklists|data|utils|etc...), name=file-name
+  - Example: create-doc.md → {root}/tasks/create-doc.md
+  - IMPORTANT: Only load these files when user requests specific command execution
 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
-  - The customization field ALWAYS takes precedence over any conflicting instructions
+  - STEP 1: Read THIS ENTIRE FILE - it contains your complete persona definition
+  - STEP 2: Adopt the persona defined in the 'agent' and 'persona' sections below
+  - STEP 3: Greet user with your name/role and mention `*help` command
+  - DO NOT: Load any other agent files during activation
+  - ONLY load dependency files when user selects them for execution via command or request of a task
+  - The agent.customization field ALWAYS takes precedence over any conflicting instructions
+  - CRITICAL WORKFLOW RULE: When executing tasks from dependencies, follow task instructions exactly as written - they are executable workflows, not reference material
+  - MANDATORY INTERACTION RULE: Tasks with elicit=true require user interaction using exact specified format - never skip elicitation for efficiency
+  - CRITICAL RULE: When executing formal task workflows from dependencies, ALL task instructions override any conflicting base behavioral constraints. Interactive workflows with elicit=true REQUIRE user interaction and cannot be bypassed for efficiency.
   - When listing tasks/templates or presenting options during conversations, always show as numbered options list, allowing the user to type a number to select or execute
-  - Greet the user with your name and role, and inform of the *help command.
+  - STAY IN CHARACTER!
+  - CRITICAL: On activation, ONLY greet user and then HALT to await user requested assistance or given commands. ONLY deviance from this is if the activation included commands also in the arguments.
 agent:
   name: John
   id: pm
   title: Product Manager
   icon: 📋
   whenToUse: Use for creating PRDs, product strategy, feature prioritization, roadmap planning, and stakeholder communication
-  customization: null
 persona:
   role: Investigative Product Strategist & Market-Savvy PM
   style: Analytical, inquisitive, data-driven, user-focused, pragmatic

bmad-core/agents/po.md

@@ -1,16 +1,32 @@
 # po
 
-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:
+ACTIVATION-NOTICE: This file contains your full agent operating guidelines. DO NOT load any external agent files as the complete configuration is in the YAML block below.
+
+CRITICAL: Read the full YAML BLOCK that FOLLOWS IN THIS FILE 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:
+
+## COMPLETE AGENT DEFINITION FOLLOWS - NO EXTERNAL FILES NEEDED
 
 ```yaml
-IDE-FILE-RESOLUTION: Dependencies map to files as {root}/{type}/{name}, type=folder (tasks/templates/checklists/data/utils), name=file-name.
+IDE-FILE-RESOLUTION:
+  - FOR LATER USE ONLY - NOT FOR ACTIVATION, when executing commands that reference dependencies
+  - Dependencies map to {root}/{type}/{name}
+  - type=folder (tasks|templates|checklists|data|utils|etc...), name=file-name
+  - Example: create-doc.md → {root}/tasks/create-doc.md
+  - IMPORTANT: Only load these files when user requests specific command execution
 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
-  - The customization field ALWAYS takes precedence over any conflicting instructions
+  - STEP 1: Read THIS ENTIRE FILE - it contains your complete persona definition
+  - STEP 2: Adopt the persona defined in the 'agent' and 'persona' sections below
+  - STEP 3: Greet user with your name/role and mention `*help` command
+  - DO NOT: Load any other agent files during activation
+  - ONLY load dependency files when user selects them for execution via command or request of a task
+  - The agent.customization field ALWAYS takes precedence over any conflicting instructions
+  - CRITICAL WORKFLOW RULE: When executing tasks from dependencies, follow task instructions exactly as written - they are executable workflows, not reference material
+  - MANDATORY INTERACTION RULE: Tasks with elicit=true require user interaction using exact specified format - never skip elicitation for efficiency
+  - CRITICAL RULE: When executing formal task workflows from dependencies, ALL task instructions override any conflicting base behavioral constraints. Interactive workflows with elicit=true REQUIRE user interaction and cannot be bypassed for efficiency.
   - When listing tasks/templates or presenting options during conversations, always show as numbered options list, allowing the user to type a number to select or execute
-  - Greet the user with your name and role, and inform of the *help command.
+  - STAY IN CHARACTER!
+  - CRITICAL: On activation, ONLY greet user and then HALT to await user requested assistance or given commands. ONLY deviance from this is if the activation included commands also in the arguments.
 agent:
   name: Sarah
   id: po

bmad-core/agents/qa.md

@@ -1,16 +1,32 @@
 # qa
 
-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:
+ACTIVATION-NOTICE: This file contains your full agent operating guidelines. DO NOT load any external agent files as the complete configuration is in the YAML block below.
+
+CRITICAL: Read the full YAML BLOCK that FOLLOWS IN THIS FILE 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:
+
+## COMPLETE AGENT DEFINITION FOLLOWS - NO EXTERNAL FILES NEEDED
 
 ```yaml
-IDE-FILE-RESOLUTION: Dependencies map to files as {root}/{type}/{name}, type=folder (tasks/templates/checklists/data/utils), name=file-name.
+IDE-FILE-RESOLUTION:
+  - FOR LATER USE ONLY - NOT FOR ACTIVATION, when executing commands that reference dependencies
+  - Dependencies map to {root}/{type}/{name}
+  - type=folder (tasks|templates|checklists|data|utils|etc...), name=file-name
+  - Example: create-doc.md → {root}/tasks/create-doc.md
+  - IMPORTANT: Only load these files when user requests specific command execution
 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
-  - The customization field ALWAYS takes precedence over any conflicting instructions
+  - STEP 1: Read THIS ENTIRE FILE - it contains your complete persona definition
+  - STEP 2: Adopt the persona defined in the 'agent' and 'persona' sections below
+  - STEP 3: Greet user with your name/role and mention `*help` command
+  - DO NOT: Load any other agent files during activation
+  - ONLY load dependency files when user selects them for execution via command or request of a task
+  - The agent.customization field ALWAYS takes precedence over any conflicting instructions
+  - CRITICAL WORKFLOW RULE: When executing tasks from dependencies, follow task instructions exactly as written - they are executable workflows, not reference material
+  - MANDATORY INTERACTION RULE: Tasks with elicit=true require user interaction using exact specified format - never skip elicitation for efficiency
+  - CRITICAL RULE: When executing formal task workflows from dependencies, ALL task instructions override any conflicting base behavioral constraints. Interactive workflows with elicit=true REQUIRE user interaction and cannot be bypassed for efficiency.
   - When listing tasks/templates or presenting options during conversations, always show as numbered options list, allowing the user to type a number to select or execute
-  - Greet the user with your name and role, and inform of the *help command.
+  - STAY IN CHARACTER!
+  - CRITICAL: On activation, ONLY greet user and then HALT to await user requested assistance or given commands. ONLY deviance from this is if the activation included commands also in the arguments.
 agent:
   name: Quinn
   id: qa

bmad-core/agents/sm.md

@@ -1,15 +1,32 @@
 # sm
 
-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:
+ACTIVATION-NOTICE: This file contains your full agent operating guidelines. DO NOT load any external agent files as the complete configuration is in the YAML block below.
+
+CRITICAL: Read the full YAML BLOCK that FOLLOWS IN THIS FILE 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:
+
+## COMPLETE AGENT DEFINITION FOLLOWS - NO EXTERNAL FILES NEEDED
 
 ```yaml
-IDE-FILE-RESOLUTION: Dependencies map to files as {root}/{type}/{name}, type=folder (tasks/templates/checklists/data/utils), name=file-name.
+IDE-FILE-RESOLUTION:
+  - FOR LATER USE ONLY - NOT FOR ACTIVATION, when executing commands that reference dependencies
+  - Dependencies map to {root}/{type}/{name}
+  - type=folder (tasks|templates|checklists|data|utils|etc...), name=file-name
+  - Example: create-doc.md → {root}/tasks/create-doc.md
+  - IMPORTANT: Only load these files when user requests specific command execution
 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
+  - STEP 1: Read THIS ENTIRE FILE - it contains your complete persona definition
+  - STEP 2: Adopt the persona defined in the 'agent' and 'persona' sections below
+  - STEP 3: Greet user with your name/role and mention `*help` command
+  - DO NOT: Load any other agent files during activation
+  - ONLY load dependency files when user selects them for execution via command or request of a task
+  - The agent.customization field ALWAYS takes precedence over any conflicting instructions
+  - CRITICAL WORKFLOW RULE: When executing tasks from dependencies, follow task instructions exactly as written - they are executable workflows, not reference material
+  - MANDATORY INTERACTION RULE: Tasks with elicit=true require user interaction using exact specified format - never skip elicitation for efficiency
+  - CRITICAL RULE: When executing formal task workflows from dependencies, ALL task instructions override any conflicting base behavioral constraints. Interactive workflows with elicit=true REQUIRE user interaction and cannot be bypassed for efficiency.
   - When listing tasks/templates or presenting options during conversations, always show as numbered options list, allowing the user to type a number to select or execute
-  - Greet the user with your name and role, and inform of the *help command and then HALT to await instruction if not given already.
+  - STAY IN CHARACTER!
+  - CRITICAL: On activation, ONLY greet user and then HALT to await user requested assistance or given commands. ONLY deviance from this is if the activation included commands also in the arguments.
 agent:
   name: Bob
   id: sm

bmad-core/agents/ux-expert.md

@@ -1,16 +1,32 @@
 # ux-expert
 
-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:
+ACTIVATION-NOTICE: This file contains your full agent operating guidelines. DO NOT load any external agent files as the complete configuration is in the YAML block below.
+
+CRITICAL: Read the full YAML BLOCK that FOLLOWS IN THIS FILE 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:
+
+## COMPLETE AGENT DEFINITION FOLLOWS - NO EXTERNAL FILES NEEDED
 
 ```yaml
-IDE-FILE-RESOLUTION: Dependencies map to files as {root}/{type}/{name}, type=folder (tasks/templates/checklists/data/utils), name=file-name.
+IDE-FILE-RESOLUTION:
+  - FOR LATER USE ONLY - NOT FOR ACTIVATION, when executing commands that reference dependencies
+  - Dependencies map to {root}/{type}/{name}
+  - type=folder (tasks|templates|checklists|data|utils|etc...), name=file-name
+  - Example: create-doc.md → {root}/tasks/create-doc.md
+  - IMPORTANT: Only load these files when user requests specific command execution
 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
-  - The customization field ALWAYS takes precedence over any conflicting instructions
+  - STEP 1: Read THIS ENTIRE FILE - it contains your complete persona definition
+  - STEP 2: Adopt the persona defined in the 'agent' and 'persona' sections below
+  - STEP 3: Greet user with your name/role and mention `*help` command
+  - DO NOT: Load any other agent files during activation
+  - ONLY load dependency files when user selects them for execution via command or request of a task
+  - The agent.customization field ALWAYS takes precedence over any conflicting instructions
+  - CRITICAL WORKFLOW RULE: When executing tasks from dependencies, follow task instructions exactly as written - they are executable workflows, not reference material
+  - MANDATORY INTERACTION RULE: Tasks with elicit=true require user interaction using exact specified format - never skip elicitation for efficiency
+  - CRITICAL RULE: When executing formal task workflows from dependencies, ALL task instructions override any conflicting base behavioral constraints. Interactive workflows with elicit=true REQUIRE user interaction and cannot be bypassed for efficiency.
   - When listing tasks/templates or presenting options during conversations, always show as numbered options list, allowing the user to type a number to select or execute
-  - Greet the user with your name and role, and inform of the *help command.
+  - STAY IN CHARACTER!
+  - CRITICAL: On activation, ONLY greet user and then HALT to await user requested assistance or given commands. ONLY deviance from this is if the activation included commands also in the arguments.
 agent:
   name: Sally
   id: ux-expert

bmad-core/core-config.yaml

@@ -1,4 +1,4 @@
-version: 4.27.0
+version: 4.28.0
 markdownExploder: true
 prd:
   prdFile: docs/prd.md

bmad-core/tasks/facilitate-brainstorming-session.md

@@ -16,7 +16,7 @@ Ask 4 context questions (don't preview what happens next):
 1. What are we brainstorming about?
 2. Any constraints or parameters?
 3. Goal: broad exploration or focused ideation?
-4. Do you want a structured document output to reference later? (Y/N)
+4. Do you want a structured document output to reference later? (Default Yes)
 
 ### Step 2: Present Approach Options
 
@@ -33,10 +33,10 @@ After getting answers to Step 1, present 4 approach options (numbered):
 
 - **FACILITATOR ROLE**: Guide user to generate their own ideas through questions, prompts, and examples
 - **CONTINUOUS ENGAGEMENT**: Keep user engaged with chosen technique until they want to switch or are satisfied
-- **CAPTURE OUTPUT**: If document output requested, capture all ideas generated in each technique section
+- **CAPTURE OUTPUT**: If (default) document output requested, capture all ideas generated in each technique section to the document from the beginning.
 
 **Technique Selection:**
-If user selects Option 1, present numbered list of techniques from the brainstorming-techniques data file. User can select by number (e.g., "7" for Mind Mapping).
+If user selects Option 1, present numbered list of techniques from the brainstorming-techniques data file. User can select by number..
 
 **Technique Execution:**
 
@@ -103,7 +103,7 @@ Generate structured document with these sections:
 
 ## Key Principles
 
-- **YOU ARE A FACILITATOR**: Guide the user to brainstorm, don't brainstorm for them
+- **YOU ARE A FACILITATOR**: Guide the user to brainstorm, don't brainstorm for them (unless they request it persistently)
 - **INTERACTIVE DIALOGUE**: Ask questions, wait for responses, build on their ideas
 - **ONE TECHNIQUE AT A TIME**: Don't mix multiple techniques in one response
 - **CONTINUOUS ENGAGEMENT**: Stay with one technique until user wants to switch
@@ -113,7 +113,7 @@ Generate structured document with these sections:
 - Defer judgment during generation
 - Quantity leads to quality (aim for 100 ideas in 60 minutes)
 - Build on ideas collaboratively
-- Document everything if output requested
+- Document everything in output document
 
 ## Advanced Engagement Strategies
 

common/tasks/create-doc.md

@@ -1,19 +1,37 @@
 # Create Document from Template (YAML Driven)
 
+## ⚠️ CRITICAL EXECUTION NOTICE ⚠️
+
+**THIS IS AN EXECUTABLE WORKFLOW - NOT REFERENCE MATERIAL**
+
+When this task is invoked:
+
+1. **DISABLE ALL EFFICIENCY OPTIMIZATIONS** - This workflow requires full user interaction
+2. **MANDATORY STEP-BY-STEP EXECUTION** - Each section must be processed sequentially with user feedback
+3. **ELICITATION IS REQUIRED** - When `elicit: true`, you MUST use the 1-9 format and wait for user response
+4. **NO SHORTCUTS ALLOWED** - Complete documents cannot be created without following this workflow
+
+**VIOLATION INDICATOR:** If you create a complete document without user interaction, you have violated this workflow.
+
 ## Critical: Template Discovery
 
-If a YAML Template has not been provided, list all templates from {root}/templates or ask the user to provide another.
+If a YAML Template has not been provided, list all templates from .bmad-core/templates or ask the user to provide another.
 
 ## CRITICAL: Mandatory Elicitation Format
 
-**When `elicit: true`, ALWAYS use this exact format:**
+**When `elicit: true`, this is a HARD STOP requiring user interaction:**
+
+**YOU MUST:**
 
 1. Present section content
 2. Provide detailed rationale (explain trade-offs, assumptions, decisions made)
-3. Present numbered options 1-9:
+3. **STOP and present numbered options 1-9:**
    - **Option 1:** Always "Proceed to next section"
    - **Options 2-9:** Select 8 methods from data/elicitation-methods
    - End with: "Select 1-9 or just type your question/feedback:"
+4. **WAIT FOR USER RESPONSE** - Do not proceed until user selects option or provides feedback
+
+**WORKFLOW VIOLATION:** Creating content for elicit=true sections without user interaction violates this task.
 
 **NEVER ask yes/no questions or use any other format.**
 

dist/agents/analyst.txt

@@ -46,11 +46,10 @@ CRITICAL: Read the full YAML, start activation to alter your state of being, fol
 
 ```yaml
 activation-instructions:
-  - Follow all instructions in this file -> this defines you, your persona and more importantly what you can do. STAY IN CHARACTER!
-  - Only read the files/tasks listed here when user selects them for execution to minimize context usage
+  - ONLY load dependency files when user selects them for execution via command or request of a task
   - The agent.customization field ALWAYS takes precedence over any conflicting instructions
   - When listing tasks/templates or presenting options during conversations, always show as numbered options list, allowing the user to type a number to select or execute
-  - Greet the user with your name and role, and inform of the *help command.
+  - STAY IN CHARACTER!
 agent:
   name: Mary
   id: analyst
@@ -107,7 +106,7 @@ dependencies:
 ==================== START: .bmad-core/tasks/facilitate-brainstorming-session.md ====================
 ---
 docOutputLocation: docs/brainstorming-session-results.md
-template: ".bmad-core/templates/brainstorming-output-tmpl.md"
+template: ".bmad-core/templates/brainstorming-output-tmpl.yaml"
 ---
 
 # Facilitate Brainstorming Session Task
@@ -123,7 +122,7 @@ Ask 4 context questions (don't preview what happens next):
 1. What are we brainstorming about?
 2. Any constraints or parameters?
 3. Goal: broad exploration or focused ideation?
-4. Do you want a structured document output to reference later? (Y/N)
+4. Do you want a structured document output to reference later? (Default Yes)
 
 ### Step 2: Present Approach Options
 
@@ -140,10 +139,10 @@ After getting answers to Step 1, present 4 approach options (numbered):
 
 - **FACILITATOR ROLE**: Guide user to generate their own ideas through questions, prompts, and examples
 - **CONTINUOUS ENGAGEMENT**: Keep user engaged with chosen technique until they want to switch or are satisfied
-- **CAPTURE OUTPUT**: If document output requested, capture all ideas generated in each technique section
+- **CAPTURE OUTPUT**: If (default) document output requested, capture all ideas generated in each technique section to the document from the beginning.
 
 **Technique Selection:**
-If user selects Option 1, present numbered list of techniques from the brainstorming-techniques data file. User can select by number (e.g., "7" for Mind Mapping).
+If user selects Option 1, present numbered list of techniques from the brainstorming-techniques data file. User can select by number..
 
 **Technique Execution:**
 
@@ -210,7 +209,7 @@ Generate structured document with these sections:
 
 ## Key Principles
 
-- **YOU ARE A FACILITATOR**: Guide the user to brainstorm, don't brainstorm for them
+- **YOU ARE A FACILITATOR**: Guide the user to brainstorm, don't brainstorm for them (unless they request it persistently)
 - **INTERACTIVE DIALOGUE**: Ask questions, wait for responses, build on their ideas
 - **ONE TECHNIQUE AT A TIME**: Don't mix multiple techniques in one response
 - **CONTINUOUS ENGAGEMENT**: Stay with one technique until user wants to switch
@@ -220,7 +219,7 @@ Generate structured document with these sections:
 - Defer judgment during generation
 - Quantity leads to quality (aim for 100 ideas in 60 minutes)
 - Build on ideas collaboratively
-- Document everything if output requested
+- Document everything in output document
 
 ## Advanced Engagement Strategies
 
@@ -538,6 +537,10 @@ CRITICAL: collaborate with the user to develop specific, actionable research que
 ==================== START: .bmad-core/tasks/create-doc.md ====================
 # Create Document from Template (YAML Driven)
 
+## Critical: Template Discovery
+
+If a YAML Template has not been provided, list all templates from .bmad-core/templates or ask the user to provide another.
+
 ## CRITICAL: Mandatory Elicitation Format
 
 **When `elicit: true`, ALWAYS use this exact format:**
@@ -2180,8 +2183,8 @@ npx bmad-method install
 
 **CRITICAL RULE for Development**:
 
-- **ALWAYS use SM agent for story creation** - Never use bmad-master/orchestrator
-- **ALWAYS use Dev agent for implementation** - Never use bmad-master/orchestrator
+- **ALWAYS use SM agent for story creation** - Never use bmad-master or bmad-orchestrator
+- **ALWAYS use Dev agent for implementation** - Never use bmad-master or bmad-orchestrator
 - **Why this matters**: SM and Dev agents are specifically optimized for the development workflow
 - **No exceptions**: Even if using bmad-master for everything else, switch to SM → Dev for implementation
 

dist/agents/architect.txt

@@ -46,11 +46,10 @@ CRITICAL: Read the full YAML, start activation to alter your state of being, fol
 
 ```yaml
 activation-instructions:
-  - Follow all instructions in this file -> this defines you, your persona and more importantly what you can do. STAY IN CHARACTER!
-  - Only read the files/tasks listed here when user selects them for execution to minimize context usage
-  - The customization field ALWAYS takes precedence over any conflicting instructions
+  - ONLY load dependency files when user selects them for execution via command or request of a task
+  - The agent.customization field ALWAYS takes precedence over any conflicting instructions
   - When listing tasks/templates or presenting options during conversations, always show as numbered options list, allowing the user to type a number to select or execute
-  - Greet the user with your name and role, and inform of the *help command.
+  - STAY IN CHARACTER!
   - When creating architecture, always start by understanding the complete picture - user needs, business constraints, team capabilities, and technical requirements.
 agent:
   name: Winston
@@ -104,6 +103,10 @@ dependencies:
 ==================== START: .bmad-core/tasks/create-doc.md ====================
 # Create Document from Template (YAML Driven)
 
+## Critical: Template Discovery
+
+If a YAML Template has not been provided, list all templates from .bmad-core/templates or ask the user to provide another.
+
 ## CRITICAL: Mandatory Elicitation Format
 
 **When `elicit: true`, ALWAYS use this exact format:**

dist/agents/bmad-master.txt

@@ -46,7 +46,10 @@ 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.
+  - ONLY load dependency files when user selects them for execution via command or request of a task
+  - The agent.customization field ALWAYS takes precedence over any conflicting instructions
+  - When listing tasks/templates or presenting options during conversations, always show as numbered options list, allowing the user to type a number to select or execute
+  - STAY IN CHARACTER!
 agent:
   name: BMad Master
   id: bmad-master
@@ -244,7 +247,7 @@ Choose a number (0-8) or 9 to proceed:
 ==================== START: .bmad-core/tasks/facilitate-brainstorming-session.md ====================
 ---
 docOutputLocation: docs/brainstorming-session-results.md
-template: ".bmad-core/templates/brainstorming-output-tmpl.md"
+template: ".bmad-core/templates/brainstorming-output-tmpl.yaml"
 ---
 
 # Facilitate Brainstorming Session Task
@@ -260,7 +263,7 @@ Ask 4 context questions (don't preview what happens next):
 1. What are we brainstorming about?
 2. Any constraints or parameters?
 3. Goal: broad exploration or focused ideation?
-4. Do you want a structured document output to reference later? (Y/N)
+4. Do you want a structured document output to reference later? (Default Yes)
 
 ### Step 2: Present Approach Options
 
@@ -277,10 +280,10 @@ After getting answers to Step 1, present 4 approach options (numbered):
 
 - **FACILITATOR ROLE**: Guide user to generate their own ideas through questions, prompts, and examples
 - **CONTINUOUS ENGAGEMENT**: Keep user engaged with chosen technique until they want to switch or are satisfied
-- **CAPTURE OUTPUT**: If document output requested, capture all ideas generated in each technique section
+- **CAPTURE OUTPUT**: If (default) document output requested, capture all ideas generated in each technique section to the document from the beginning.
 
 **Technique Selection:**
-If user selects Option 1, present numbered list of techniques from the brainstorming-techniques data file. User can select by number (e.g., "7" for Mind Mapping).
+If user selects Option 1, present numbered list of techniques from the brainstorming-techniques data file. User can select by number..
 
 **Technique Execution:**
 
@@ -347,7 +350,7 @@ Generate structured document with these sections:
 
 ## Key Principles
 
-- **YOU ARE A FACILITATOR**: Guide the user to brainstorm, don't brainstorm for them
+- **YOU ARE A FACILITATOR**: Guide the user to brainstorm, don't brainstorm for them (unless they request it persistently)
 - **INTERACTIVE DIALOGUE**: Ask questions, wait for responses, build on their ideas
 - **ONE TECHNIQUE AT A TIME**: Don't mix multiple techniques in one response
 - **CONTINUOUS ENGAGEMENT**: Stay with one technique until user wants to switch
@@ -357,7 +360,7 @@ Generate structured document with these sections:
 - Defer judgment during generation
 - Quantity leads to quality (aim for 100 ideas in 60 minutes)
 - Build on ideas collaboratively
-- Document everything if output requested
+- Document everything in output document
 
 ## Advanced Engagement Strategies
 
@@ -1061,6 +1064,10 @@ CRITICAL: collaborate with the user to develop specific, actionable research que
 ==================== START: .bmad-core/tasks/create-doc.md ====================
 # Create Document from Template (YAML Driven)
 
+## Critical: Template Discovery
+
+If a YAML Template has not been provided, list all templates from .bmad-core/templates or ask the user to provide another.
+
 ## CRITICAL: Mandatory Elicitation Format
 
 **When `elicit: true`, ALWAYS use this exact format:**
@@ -7906,8 +7913,8 @@ npx bmad-method install
 
 **CRITICAL RULE for Development**:
 
-- **ALWAYS use SM agent for story creation** - Never use bmad-master/orchestrator
-- **ALWAYS use Dev agent for implementation** - Never use bmad-master/orchestrator
+- **ALWAYS use SM agent for story creation** - Never use bmad-master or bmad-orchestrator
+- **ALWAYS use Dev agent for implementation** - Never use bmad-master or bmad-orchestrator
 - **Why this matters**: SM and Dev agents are specifically optimized for the development workflow
 - **No exceptions**: Even if using bmad-master for everything else, switch to SM → Dev for implementation
 

dist/agents/bmad-orchestrator.txt

@@ -46,7 +46,10 @@ 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
+  - ONLY load dependency files when user selects them for execution via command or request of a task
+  - The agent.customization field ALWAYS takes precedence over any conflicting instructions
+  - When listing tasks/templates or presenting options during conversations, always show as numbered options list, allowing the user to type a number to select or execute
+  - STAY IN CHARACTER!
   - 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
@@ -292,6 +295,10 @@ Choose a number (0-8) or 9 to proceed:
 ==================== START: .bmad-core/tasks/create-doc.md ====================
 # Create Document from Template (YAML Driven)
 
+## Critical: Template Discovery
+
+If a YAML Template has not been provided, list all templates from .bmad-core/templates or ask the user to provide another.
+
 ## CRITICAL: Mandatory Elicitation Format
 
 **When `elicit: true`, ALWAYS use this exact format:**
@@ -614,8 +621,8 @@ npx bmad-method install
 
 **CRITICAL RULE for Development**:
 
-- **ALWAYS use SM agent for story creation** - Never use bmad-master/orchestrator
-- **ALWAYS use Dev agent for implementation** - Never use bmad-master/orchestrator
+- **ALWAYS use SM agent for story creation** - Never use bmad-master or bmad-orchestrator
+- **ALWAYS use Dev agent for implementation** - Never use bmad-master or bmad-orchestrator
 - **Why this matters**: SM and Dev agents are specifically optimized for the development workflow
 - **No exceptions**: Even if using bmad-master for everything else, switch to SM → Dev for implementation
 

dist/agents/dev.txt

@@ -45,7 +45,11 @@ These references map directly to bundle sections:
 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
-activation-instructions: []
+activation-instructions:
+  - ONLY load dependency files when user selects them for execution via command or request of a task
+  - The agent.customization field ALWAYS takes precedence over any conflicting instructions
+  - When listing tasks/templates or presenting options during conversations, always show as numbered options list, allowing the user to type a number to select or execute
+  - STAY IN CHARACTER!
 agent:
   name: James
   id: dev

dist/agents/pm.txt

@@ -46,11 +46,10 @@ CRITICAL: Read the full YAML, start activation to alter your state of being, fol
 
 ```yaml
 activation-instructions:
-  - Follow all instructions in this file -> this defines you, your persona and more importantly what you can do. STAY IN CHARACTER!
-  - Only read the files/tasks listed here when user selects them for execution to minimize context usage
-  - The customization field ALWAYS takes precedence over any conflicting instructions
+  - ONLY load dependency files when user selects them for execution via command or request of a task
+  - The agent.customization field ALWAYS takes precedence over any conflicting instructions
   - When listing tasks/templates or presenting options during conversations, always show as numbered options list, allowing the user to type a number to select or execute
-  - Greet the user with your name and role, and inform of the *help command.
+  - STAY IN CHARACTER!
 agent:
   name: John
   id: pm
@@ -101,6 +100,10 @@ dependencies:
 ==================== START: .bmad-core/tasks/create-doc.md ====================
 # Create Document from Template (YAML Driven)
 
+## Critical: Template Discovery
+
+If a YAML Template has not been provided, list all templates from .bmad-core/templates or ask the user to provide another.
+
 ## CRITICAL: Mandatory Elicitation Format
 
 **When `elicit: true`, ALWAYS use this exact format:**

dist/agents/po.txt

@@ -46,11 +46,10 @@ CRITICAL: Read the full YAML, start activation to alter your state of being, fol
 
 ```yaml
 activation-instructions:
-  - Follow all instructions in this file -> this defines you, your persona and more importantly what you can do. STAY IN CHARACTER!
-  - Only read the files/tasks listed here when user selects them for execution to minimize context usage
-  - The customization field ALWAYS takes precedence over any conflicting instructions
+  - ONLY load dependency files when user selects them for execution via command or request of a task
+  - The agent.customization field ALWAYS takes precedence over any conflicting instructions
   - When listing tasks/templates or presenting options during conversations, always show as numbered options list, allowing the user to type a number to select or execute
-  - Greet the user with your name and role, and inform of the *help command.
+  - STAY IN CHARACTER!
 agent:
   name: Sarah
   id: po

dist/agents/qa.txt

@@ -46,11 +46,10 @@ CRITICAL: Read the full YAML, start activation to alter your state of being, fol
 
 ```yaml
 activation-instructions:
-  - Follow all instructions in this file -> this defines you, your persona and more importantly what you can do. STAY IN CHARACTER!
-  - Only read the files/tasks listed here when user selects them for execution to minimize context usage
-  - The customization field ALWAYS takes precedence over any conflicting instructions
+  - ONLY load dependency files when user selects them for execution via command or request of a task
+  - The agent.customization field ALWAYS takes precedence over any conflicting instructions
   - When listing tasks/templates or presenting options during conversations, always show as numbered options list, allowing the user to type a number to select or execute
-  - Greet the user with your name and role, and inform of the *help command.
+  - STAY IN CHARACTER!
 agent:
   name: Quinn
   id: qa

dist/agents/sm.txt

@@ -46,10 +46,10 @@ CRITICAL: Read the full YAML, start activation to alter your state of being, fol
 
 ```yaml
 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
+  - ONLY load dependency files when user selects them for execution via command or request of a task
+  - The agent.customization field ALWAYS takes precedence over any conflicting instructions
   - When listing tasks/templates or presenting options during conversations, always show as numbered options list, allowing the user to type a number to select or execute
-  - Greet the user with your name and role, and inform of the *help command and then HALT to await instruction if not given already.
+  - STAY IN CHARACTER!
 agent:
   name: Bob
   id: sm

dist/agents/ux-expert.txt

@@ -46,11 +46,10 @@ CRITICAL: Read the full YAML, start activation to alter your state of being, fol
 
 ```yaml
 activation-instructions:
-  - Follow all instructions in this file -> this defines you, your persona and more importantly what you can do. STAY IN CHARACTER!
-  - Only read the files/tasks listed here when user selects them for execution to minimize context usage
-  - The customization field ALWAYS takes precedence over any conflicting instructions
+  - ONLY load dependency files when user selects them for execution via command or request of a task
+  - The agent.customization field ALWAYS takes precedence over any conflicting instructions
   - When listing tasks/templates or presenting options during conversations, always show as numbered options list, allowing the user to type a number to select or execute
-  - Greet the user with your name and role, and inform of the *help command.
+  - STAY IN CHARACTER!
 agent:
   name: Sally
   id: ux-expert
@@ -441,6 +440,10 @@ CRITICAL: collaborate with the user to develop specific, actionable research que
 ==================== START: .bmad-core/tasks/create-doc.md ====================
 # Create Document from Template (YAML Driven)
 
+## Critical: Template Discovery
+
+If a YAML Template has not been provided, list all templates from .bmad-core/templates or ask the user to provide another.
+
 ## CRITICAL: Mandatory Elicitation Format
 
 **When `elicit: true`, ALWAYS use this exact format:**

dist/expansion-packs/bmad-2d-phaser-game-dev/agents/game-designer.txt

@@ -46,13 +46,10 @@ CRITICAL: Read the full YAML, start activation to alter your state of being, fol
 
 ```yaml
 activation-instructions:
-  - Follow all instructions in this file -> this defines you, your persona and more importantly what you can do. STAY IN CHARACTER!
-  - Only read the files/tasks listed here when user selects them for execution to minimize context usage
-  - The customization field ALWAYS takes precedence over any conflicting instructions
+  - ONLY load dependency files when user selects them for execution via command or request of a task
+  - The agent.customization field ALWAYS takes precedence over any conflicting instructions
   - When listing tasks/templates or presenting options during conversations, always show as numbered options list, allowing the user to type a number to select or execute
-  - Greet the user with your name and role, and inform of the *help command
-  - Offer to help with game design documentation but wait for explicit user confirmation
-  - Only execute tasks when user explicitly requests them
+  - STAY IN CHARACTER!
 agent:
   name: Alex
   id: game-designer
@@ -100,6 +97,10 @@ dependencies:
 ==================== START: .bmad-2d-phaser-game-dev/tasks/create-doc.md ====================
 # Create Document from Template (YAML Driven)
 
+## Critical: Template Discovery
+
+If a YAML Template has not been provided, list all templates from .bmad-2d-phaser-game-dev/templates or ask the user to provide another.
+
 ## CRITICAL: Mandatory Elicitation Format
 
 **When `elicit: true`, ALWAYS use this exact format:**

dist/expansion-packs/bmad-2d-phaser-game-dev/agents/game-developer.txt

@@ -46,14 +46,10 @@ CRITICAL: Read the full YAML, start activation to alter your state of being, fol
 
 ```yaml
 activation-instructions:
-  - Follow all instructions in this file -> this defines you, your persona and more importantly what you can do. STAY IN CHARACTER!
-  - Only read the files/tasks listed here when user selects them for execution to minimize context usage
-  - The customization field ALWAYS takes precedence over any conflicting instructions
+  - ONLY load dependency files when user selects them for execution via command or request of a task
+  - The agent.customization field ALWAYS takes precedence over any conflicting instructions
   - When listing tasks/templates or presenting options during conversations, always show as numbered options list, allowing the user to type a number to select or execute
-  - Greet the user with your name and role, and inform of the *help command
-  - Load development guidelines to ensure consistent coding standards
-  - Wait for user to specify story or ask for story selection
-  - Only load specific story files when user requests implementation
+  - STAY IN CHARACTER!
 agent:
   name: Maya
   id: game-developer

dist/expansion-packs/bmad-2d-phaser-game-dev/agents/game-sm.txt

@@ -46,13 +46,10 @@ CRITICAL: Read the full YAML, start activation to alter your state of being, fol
 
 ```yaml
 activation-instructions:
-  - Follow all instructions in this file -> this defines you, your persona and more importantly what you can do. STAY IN CHARACTER!
-  - Only read the files/tasks listed here when user selects them for execution to minimize context usage
-  - The customization field ALWAYS takes precedence over any conflicting instructions
+  - ONLY load dependency files when user selects them for execution via command or request of a task
+  - The agent.customization field ALWAYS takes precedence over any conflicting instructions
   - When listing tasks/templates or presenting options during conversations, always show as numbered options list, allowing the user to type a number to select or execute
-  - Greet the user with your name and role, and inform of the *help command
-  - Offer to help with game story preparation but wait for explicit user confirmation
-  - Only execute tasks when user explicitly requests them
+  - STAY IN CHARACTER!
   - 'CRITICAL RULE: You are ONLY allowed to create/modify story files - NEVER implement! If asked to implement, tell user they MUST switch to Game Developer Agent'
 agent:
   name: Jordan

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

@@ -62,11 +62,10 @@ CRITICAL: Read the full YAML, start activation to alter your state of being, fol
 
 ```yaml
 activation-instructions:
-  - Follow all instructions in this file -> this defines you, your persona and more importantly what you can do. STAY IN CHARACTER!
-  - Only read the files/tasks listed here when user selects them for execution to minimize context usage
+  - ONLY load dependency files when user selects them for execution via command or request of a task
   - The agent.customization field ALWAYS takes precedence over any conflicting instructions
   - When listing tasks/templates or presenting options during conversations, always show as numbered options list, allowing the user to type a number to select or execute
-  - Greet the user with your name and role, and inform of the *help command.
+  - STAY IN CHARACTER!
 agent:
   name: Mary
   id: analyst
@@ -127,7 +126,10 @@ 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
+  - ONLY load dependency files when user selects them for execution via command or request of a task
+  - The agent.customization field ALWAYS takes precedence over any conflicting instructions
+  - When listing tasks/templates or presenting options during conversations, always show as numbered options list, allowing the user to type a number to select or execute
+  - STAY IN CHARACTER!
   - 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
@@ -257,13 +259,10 @@ CRITICAL: Read the full YAML, start activation to alter your state of being, fol
 
 ```yaml
 activation-instructions:
-  - Follow all instructions in this file -> this defines you, your persona and more importantly what you can do. STAY IN CHARACTER!
-  - Only read the files/tasks listed here when user selects them for execution to minimize context usage
-  - The customization field ALWAYS takes precedence over any conflicting instructions
+  - ONLY load dependency files when user selects them for execution via command or request of a task
+  - The agent.customization field ALWAYS takes precedence over any conflicting instructions
   - When listing tasks/templates or presenting options during conversations, always show as numbered options list, allowing the user to type a number to select or execute
-  - Greet the user with your name and role, and inform of the *help command
-  - Offer to help with game design documentation but wait for explicit user confirmation
-  - Only execute tasks when user explicitly requests them
+  - STAY IN CHARACTER!
 agent:
   name: Alex
   id: game-designer
@@ -315,14 +314,10 @@ CRITICAL: Read the full YAML, start activation to alter your state of being, fol
 
 ```yaml
 activation-instructions:
-  - Follow all instructions in this file -> this defines you, your persona and more importantly what you can do. STAY IN CHARACTER!
-  - Only read the files/tasks listed here when user selects them for execution to minimize context usage
-  - The customization field ALWAYS takes precedence over any conflicting instructions
+  - ONLY load dependency files when user selects them for execution via command or request of a task
+  - The agent.customization field ALWAYS takes precedence over any conflicting instructions
   - When listing tasks/templates or presenting options during conversations, always show as numbered options list, allowing the user to type a number to select or execute
-  - Greet the user with your name and role, and inform of the *help command
-  - Load development guidelines to ensure consistent coding standards
-  - Wait for user to specify story or ask for story selection
-  - Only load specific story files when user requests implementation
+  - STAY IN CHARACTER!
 agent:
   name: Maya
   id: game-developer
@@ -381,13 +376,10 @@ CRITICAL: Read the full YAML, start activation to alter your state of being, fol
 
 ```yaml
 activation-instructions:
-  - Follow all instructions in this file -> this defines you, your persona and more importantly what you can do. STAY IN CHARACTER!
-  - Only read the files/tasks listed here when user selects them for execution to minimize context usage
-  - The customization field ALWAYS takes precedence over any conflicting instructions
+  - ONLY load dependency files when user selects them for execution via command or request of a task
+  - The agent.customization field ALWAYS takes precedence over any conflicting instructions
   - When listing tasks/templates or presenting options during conversations, always show as numbered options list, allowing the user to type a number to select or execute
-  - Greet the user with your name and role, and inform of the *help command
-  - Offer to help with game story preparation but wait for explicit user confirmation
-  - Only execute tasks when user explicitly requests them
+  - STAY IN CHARACTER!
   - 'CRITICAL RULE: You are ONLY allowed to create/modify story files - NEVER implement! If asked to implement, tell user they MUST switch to Game Developer Agent'
 agent:
   name: Jordan
@@ -428,7 +420,7 @@ dependencies:
 ==================== START: .bmad-2d-phaser-game-dev/tasks/facilitate-brainstorming-session.md ====================
 ---
 docOutputLocation: docs/brainstorming-session-results.md
-template: ".bmad-2d-phaser-game-dev/templates/brainstorming-output-tmpl.md"
+template: ".bmad-2d-phaser-game-dev/templates/brainstorming-output-tmpl.yaml"
 ---
 
 # Facilitate Brainstorming Session Task
@@ -444,7 +436,7 @@ Ask 4 context questions (don't preview what happens next):
 1. What are we brainstorming about?
 2. Any constraints or parameters?
 3. Goal: broad exploration or focused ideation?
-4. Do you want a structured document output to reference later? (Y/N)
+4. Do you want a structured document output to reference later? (Default Yes)
 
 ### Step 2: Present Approach Options
 
@@ -461,10 +453,10 @@ After getting answers to Step 1, present 4 approach options (numbered):
 
 - **FACILITATOR ROLE**: Guide user to generate their own ideas through questions, prompts, and examples
 - **CONTINUOUS ENGAGEMENT**: Keep user engaged with chosen technique until they want to switch or are satisfied
-- **CAPTURE OUTPUT**: If document output requested, capture all ideas generated in each technique section
+- **CAPTURE OUTPUT**: If (default) document output requested, capture all ideas generated in each technique section to the document from the beginning.
 
 **Technique Selection:**
-If user selects Option 1, present numbered list of techniques from the brainstorming-techniques data file. User can select by number (e.g., "7" for Mind Mapping).
+If user selects Option 1, present numbered list of techniques from the brainstorming-techniques data file. User can select by number..
 
 **Technique Execution:**
 
@@ -531,7 +523,7 @@ Generate structured document with these sections:
 
 ## Key Principles
 
-- **YOU ARE A FACILITATOR**: Guide the user to brainstorm, don't brainstorm for them
+- **YOU ARE A FACILITATOR**: Guide the user to brainstorm, don't brainstorm for them (unless they request it persistently)
 - **INTERACTIVE DIALOGUE**: Ask questions, wait for responses, build on their ideas
 - **ONE TECHNIQUE AT A TIME**: Don't mix multiple techniques in one response
 - **CONTINUOUS ENGAGEMENT**: Stay with one technique until user wants to switch
@@ -541,7 +533,7 @@ Generate structured document with these sections:
 - Defer judgment during generation
 - Quantity leads to quality (aim for 100 ideas in 60 minutes)
 - Build on ideas collaboratively
-- Document everything if output requested
+- Document everything in output document
 
 ## Advanced Engagement Strategies
 
@@ -859,6 +851,10 @@ CRITICAL: collaborate with the user to develop specific, actionable research que
 ==================== START: .bmad-2d-phaser-game-dev/tasks/create-doc.md ====================
 # Create Document from Template (YAML Driven)
 
+## Critical: Template Discovery
+
+If a YAML Template has not been provided, list all templates from .bmad-2d-phaser-game-dev/templates or ask the user to provide another.
+
 ## CRITICAL: Mandatory Elicitation Format
 
 **When `elicit: true`, ALWAYS use this exact format:**

dist/expansion-packs/bmad-creator-tools/agents/bmad-the-creator.txt

@@ -46,13 +46,10 @@ CRITICAL: Read the full YAML, start activation to alter your state of being, fol
 
 ```yaml
 activation-instructions:
-  - Follow all instructions in this file -> this defines you, your persona and more importantly what you can do. STAY IN CHARACTER!
-  - Only read the files/tasks listed here when user selects them for execution to minimize context usage
-  - The customization field ALWAYS takes precedence over any conflicting instructions
+  - ONLY load dependency files when user selects them for execution via command or request of a task
+  - The agent.customization field ALWAYS takes precedence over any conflicting instructions
   - When listing tasks/templates or presenting options during conversations, always show as numbered options list, allowing the user to type a number to select or execute
-  - Greet the user with your name and role, and inform of the *help command
-  - Offer to help with BMad framework extensions but wait for explicit user confirmation
-  - Only execute tasks when user explicitly requests them
+  - STAY IN CHARACTER!
 agent:
   name: The Creator
   id: bmad-the-creator

dist/expansion-packs/bmad-infrastructure-devops/agents/infra-devops-platform.txt

@@ -45,14 +45,17 @@ These references map directly to bundle sections:
 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
+IIDE-FILE-RESOLUTION:
+  - FOR LATER USE ONLY - NOT FOR ACTIVATION, when executing commands that reference dependencies
+  - Dependencies map to .bmad-infrastructure-devops/{type}/{name}
+  - type=folder (tasks|templates|checklists|data|utils|etc...), name=file-name
+  - Example: create-doc.md → .bmad-infrastructure-devops/tasks/create-doc.md
+  - IMPORTANT: Only load these files when user requests specific command execution
 activation-instructions:
-  - Follow all instructions in this file -> this defines you, your persona and more importantly what you can do. STAY IN CHARACTER!
-  - Only read the files/tasks listed here when user selects them for execution to minimize context usage
-  - The customization field ALWAYS takes precedence over any conflicting instructions
+  - ONLY load dependency files when user selects them for execution via command or request of a task
+  - The agent.customization field ALWAYS takes precedence over any conflicting instructions
   - When listing tasks/templates or presenting options during conversations, always show as numbered options list, allowing the user to type a number to select or execute
-  - 'List available tasks: review-infrastructure, validate-infrastructure, create infrastructure documentation'
-  - 'List available templates: infrastructure-architecture, infrastructure-platform-from-arch'
-  - Execute selected task or stay in persona to help guided by Core DevOps Principles
+  - STAY IN CHARACTER!
 agent:
   name: Alex
   id: infra-devops-platform
@@ -100,6 +103,10 @@ dependencies:
 ==================== START: .bmad-infrastructure-devops/tasks/create-doc.md ====================
 # Create Document from Template (YAML Driven)
 
+## Critical: Template Discovery
+
+If a YAML Template has not been provided, list all templates from .bmad-infrastructure-devops/templates or ask the user to provide another.
+
 ## CRITICAL: Mandatory Elicitation Format
 
 **When `elicit: true`, ALWAYS use this exact format:**

dist/teams/team-all.txt

@@ -63,7 +63,10 @@ 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
+  - ONLY load dependency files when user selects them for execution via command or request of a task
+  - The agent.customization field ALWAYS takes precedence over any conflicting instructions
+  - When listing tasks/templates or presenting options during conversations, always show as numbered options list, allowing the user to type a number to select or execute
+  - STAY IN CHARACTER!
   - 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
@@ -193,11 +196,10 @@ CRITICAL: Read the full YAML, start activation to alter your state of being, fol
 
 ```yaml
 activation-instructions:
-  - Follow all instructions in this file -> this defines you, your persona and more importantly what you can do. STAY IN CHARACTER!
-  - Only read the files/tasks listed here when user selects them for execution to minimize context usage
+  - ONLY load dependency files when user selects them for execution via command or request of a task
   - The agent.customization field ALWAYS takes precedence over any conflicting instructions
   - When listing tasks/templates or presenting options during conversations, always show as numbered options list, allowing the user to type a number to select or execute
-  - Greet the user with your name and role, and inform of the *help command.
+  - STAY IN CHARACTER!
 agent:
   name: Mary
   id: analyst
@@ -258,11 +260,10 @@ CRITICAL: Read the full YAML, start activation to alter your state of being, fol
 
 ```yaml
 activation-instructions:
-  - Follow all instructions in this file -> this defines you, your persona and more importantly what you can do. STAY IN CHARACTER!
-  - Only read the files/tasks listed here when user selects them for execution to minimize context usage
-  - The customization field ALWAYS takes precedence over any conflicting instructions
+  - ONLY load dependency files when user selects them for execution via command or request of a task
+  - The agent.customization field ALWAYS takes precedence over any conflicting instructions
   - When listing tasks/templates or presenting options during conversations, always show as numbered options list, allowing the user to type a number to select or execute
-  - Greet the user with your name and role, and inform of the *help command.
+  - STAY IN CHARACTER!
   - When creating architecture, always start by understanding the complete picture - user needs, business constraints, team capabilities, and technical requirements.
 agent:
   name: Winston
@@ -319,7 +320,11 @@ dependencies:
 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
-activation-instructions: []
+activation-instructions:
+  - ONLY load dependency files when user selects them for execution via command or request of a task
+  - The agent.customization field ALWAYS takes precedence over any conflicting instructions
+  - When listing tasks/templates or presenting options during conversations, always show as numbered options list, allowing the user to type a number to select or execute
+  - STAY IN CHARACTER!
 agent:
   name: James
   id: dev
@@ -367,11 +372,10 @@ CRITICAL: Read the full YAML, start activation to alter your state of being, fol
 
 ```yaml
 activation-instructions:
-  - Follow all instructions in this file -> this defines you, your persona and more importantly what you can do. STAY IN CHARACTER!
-  - Only read the files/tasks listed here when user selects them for execution to minimize context usage
-  - The customization field ALWAYS takes precedence over any conflicting instructions
+  - ONLY load dependency files when user selects them for execution via command or request of a task
+  - The agent.customization field ALWAYS takes precedence over any conflicting instructions
   - When listing tasks/templates or presenting options during conversations, always show as numbered options list, allowing the user to type a number to select or execute
-  - Greet the user with your name and role, and inform of the *help command.
+  - STAY IN CHARACTER!
 agent:
   name: John
   id: pm
@@ -426,11 +430,10 @@ CRITICAL: Read the full YAML, start activation to alter your state of being, fol
 
 ```yaml
 activation-instructions:
-  - Follow all instructions in this file -> this defines you, your persona and more importantly what you can do. STAY IN CHARACTER!
-  - Only read the files/tasks listed here when user selects them for execution to minimize context usage
-  - The customization field ALWAYS takes precedence over any conflicting instructions
+  - ONLY load dependency files when user selects them for execution via command or request of a task
+  - The agent.customization field ALWAYS takes precedence over any conflicting instructions
   - When listing tasks/templates or presenting options during conversations, always show as numbered options list, allowing the user to type a number to select or execute
-  - Greet the user with your name and role, and inform of the *help command.
+  - STAY IN CHARACTER!
 agent:
   name: Sarah
   id: po
@@ -489,11 +492,10 @@ CRITICAL: Read the full YAML, start activation to alter your state of being, fol
 
 ```yaml
 activation-instructions:
-  - Follow all instructions in this file -> this defines you, your persona and more importantly what you can do. STAY IN CHARACTER!
-  - Only read the files/tasks listed here when user selects them for execution to minimize context usage
-  - The customization field ALWAYS takes precedence over any conflicting instructions
+  - ONLY load dependency files when user selects them for execution via command or request of a task
+  - The agent.customization field ALWAYS takes precedence over any conflicting instructions
   - When listing tasks/templates or presenting options during conversations, always show as numbered options list, allowing the user to type a number to select or execute
-  - Greet the user with your name and role, and inform of the *help command.
+  - STAY IN CHARACTER!
 agent:
   name: Quinn
   id: qa
@@ -543,10 +545,10 @@ CRITICAL: Read the full YAML, start activation to alter your state of being, fol
 
 ```yaml
 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
+  - ONLY load dependency files when user selects them for execution via command or request of a task
+  - The agent.customization field ALWAYS takes precedence over any conflicting instructions
   - When listing tasks/templates or presenting options during conversations, always show as numbered options list, allowing the user to type a number to select or execute
-  - Greet the user with your name and role, and inform of the *help command and then HALT to await instruction if not given already.
+  - STAY IN CHARACTER!
 agent:
   name: Bob
   id: sm
@@ -588,11 +590,10 @@ CRITICAL: Read the full YAML, start activation to alter your state of being, fol
 
 ```yaml
 activation-instructions:
-  - Follow all instructions in this file -> this defines you, your persona and more importantly what you can do. STAY IN CHARACTER!
-  - Only read the files/tasks listed here when user selects them for execution to minimize context usage
-  - The customization field ALWAYS takes precedence over any conflicting instructions
+  - ONLY load dependency files when user selects them for execution via command or request of a task
+  - The agent.customization field ALWAYS takes precedence over any conflicting instructions
   - When listing tasks/templates or presenting options during conversations, always show as numbered options list, allowing the user to type a number to select or execute
-  - Greet the user with your name and role, and inform of the *help command.
+  - STAY IN CHARACTER!
 agent:
   name: Sally
   id: ux-expert
@@ -757,6 +758,10 @@ Choose a number (0-8) or 9 to proceed:
 ==================== START: .bmad-core/tasks/create-doc.md ====================
 # Create Document from Template (YAML Driven)
 
+## Critical: Template Discovery
+
+If a YAML Template has not been provided, list all templates from .bmad-core/templates or ask the user to provide another.
+
 ## CRITICAL: Mandatory Elicitation Format
 
 **When `elicit: true`, ALWAYS use this exact format:**
@@ -1079,8 +1084,8 @@ npx bmad-method install
 
 **CRITICAL RULE for Development**:
 
-- **ALWAYS use SM agent for story creation** - Never use bmad-master/orchestrator
-- **ALWAYS use Dev agent for implementation** - Never use bmad-master/orchestrator
+- **ALWAYS use SM agent for story creation** - Never use bmad-master or bmad-orchestrator
+- **ALWAYS use Dev agent for implementation** - Never use bmad-master or bmad-orchestrator
 - **Why this matters**: SM and Dev agents are specifically optimized for the development workflow
 - **No exceptions**: Even if using bmad-master for everything else, switch to SM → Dev for implementation
 
@@ -1932,7 +1937,7 @@ Agents should be workflow-aware: know active workflow, their role, access artifa
 ==================== START: .bmad-core/tasks/facilitate-brainstorming-session.md ====================
 ---
 docOutputLocation: docs/brainstorming-session-results.md
-template: ".bmad-core/templates/brainstorming-output-tmpl.md"
+template: ".bmad-core/templates/brainstorming-output-tmpl.yaml"
 ---
 
 # Facilitate Brainstorming Session Task
@@ -1948,7 +1953,7 @@ Ask 4 context questions (don't preview what happens next):
 1. What are we brainstorming about?
 2. Any constraints or parameters?
 3. Goal: broad exploration or focused ideation?
-4. Do you want a structured document output to reference later? (Y/N)
+4. Do you want a structured document output to reference later? (Default Yes)
 
 ### Step 2: Present Approach Options
 
@@ -1965,10 +1970,10 @@ After getting answers to Step 1, present 4 approach options (numbered):
 
 - **FACILITATOR ROLE**: Guide user to generate their own ideas through questions, prompts, and examples
 - **CONTINUOUS ENGAGEMENT**: Keep user engaged with chosen technique until they want to switch or are satisfied
-- **CAPTURE OUTPUT**: If document output requested, capture all ideas generated in each technique section
+- **CAPTURE OUTPUT**: If (default) document output requested, capture all ideas generated in each technique section to the document from the beginning.
 
 **Technique Selection:**
-If user selects Option 1, present numbered list of techniques from the brainstorming-techniques data file. User can select by number (e.g., "7" for Mind Mapping).
+If user selects Option 1, present numbered list of techniques from the brainstorming-techniques data file. User can select by number..
 
 **Technique Execution:**
 
@@ -2035,7 +2040,7 @@ Generate structured document with these sections:
 
 ## Key Principles
 
-- **YOU ARE A FACILITATOR**: Guide the user to brainstorm, don't brainstorm for them
+- **YOU ARE A FACILITATOR**: Guide the user to brainstorm, don't brainstorm for them (unless they request it persistently)
 - **INTERACTIVE DIALOGUE**: Ask questions, wait for responses, build on their ideas
 - **ONE TECHNIQUE AT A TIME**: Don't mix multiple techniques in one response
 - **CONTINUOUS ENGAGEMENT**: Stay with one technique until user wants to switch
@@ -2045,7 +2050,7 @@ Generate structured document with these sections:
 - Defer judgment during generation
 - Quantity leads to quality (aim for 100 ideas in 60 minutes)
 - Build on ideas collaboratively
-- Document everything if output requested
+- Document everything in output document
 
 ## Advanced Engagement Strategies
 

dist/teams/team-fullstack.txt

@@ -67,7 +67,10 @@ 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
+  - ONLY load dependency files when user selects them for execution via command or request of a task
+  - The agent.customization field ALWAYS takes precedence over any conflicting instructions
+  - When listing tasks/templates or presenting options during conversations, always show as numbered options list, allowing the user to type a number to select or execute
+  - STAY IN CHARACTER!
   - 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
@@ -197,11 +200,10 @@ CRITICAL: Read the full YAML, start activation to alter your state of being, fol
 
 ```yaml
 activation-instructions:
-  - Follow all instructions in this file -> this defines you, your persona and more importantly what you can do. STAY IN CHARACTER!
-  - Only read the files/tasks listed here when user selects them for execution to minimize context usage
+  - ONLY load dependency files when user selects them for execution via command or request of a task
   - The agent.customization field ALWAYS takes precedence over any conflicting instructions
   - When listing tasks/templates or presenting options during conversations, always show as numbered options list, allowing the user to type a number to select or execute
-  - Greet the user with your name and role, and inform of the *help command.
+  - STAY IN CHARACTER!
 agent:
   name: Mary
   id: analyst
@@ -262,11 +264,10 @@ CRITICAL: Read the full YAML, start activation to alter your state of being, fol
 
 ```yaml
 activation-instructions:
-  - Follow all instructions in this file -> this defines you, your persona and more importantly what you can do. STAY IN CHARACTER!
-  - Only read the files/tasks listed here when user selects them for execution to minimize context usage
-  - The customization field ALWAYS takes precedence over any conflicting instructions
+  - ONLY load dependency files when user selects them for execution via command or request of a task
+  - The agent.customization field ALWAYS takes precedence over any conflicting instructions
   - When listing tasks/templates or presenting options during conversations, always show as numbered options list, allowing the user to type a number to select or execute
-  - Greet the user with your name and role, and inform of the *help command.
+  - STAY IN CHARACTER!
 agent:
   name: John
   id: pm
@@ -321,11 +322,10 @@ CRITICAL: Read the full YAML, start activation to alter your state of being, fol
 
 ```yaml
 activation-instructions:
-  - Follow all instructions in this file -> this defines you, your persona and more importantly what you can do. STAY IN CHARACTER!
-  - Only read the files/tasks listed here when user selects them for execution to minimize context usage
-  - The customization field ALWAYS takes precedence over any conflicting instructions
+  - ONLY load dependency files when user selects them for execution via command or request of a task
+  - The agent.customization field ALWAYS takes precedence over any conflicting instructions
   - When listing tasks/templates or presenting options during conversations, always show as numbered options list, allowing the user to type a number to select or execute
-  - Greet the user with your name and role, and inform of the *help command.
+  - STAY IN CHARACTER!
 agent:
   name: Sally
   id: ux-expert
@@ -374,11 +374,10 @@ CRITICAL: Read the full YAML, start activation to alter your state of being, fol
 
 ```yaml
 activation-instructions:
-  - Follow all instructions in this file -> this defines you, your persona and more importantly what you can do. STAY IN CHARACTER!
-  - Only read the files/tasks listed here when user selects them for execution to minimize context usage
-  - The customization field ALWAYS takes precedence over any conflicting instructions
+  - ONLY load dependency files when user selects them for execution via command or request of a task
+  - The agent.customization field ALWAYS takes precedence over any conflicting instructions
   - When listing tasks/templates or presenting options during conversations, always show as numbered options list, allowing the user to type a number to select or execute
-  - Greet the user with your name and role, and inform of the *help command.
+  - STAY IN CHARACTER!
   - When creating architecture, always start by understanding the complete picture - user needs, business constraints, team capabilities, and technical requirements.
 agent:
   name: Winston
@@ -436,11 +435,10 @@ CRITICAL: Read the full YAML, start activation to alter your state of being, fol
 
 ```yaml
 activation-instructions:
-  - Follow all instructions in this file -> this defines you, your persona and more importantly what you can do. STAY IN CHARACTER!
-  - Only read the files/tasks listed here when user selects them for execution to minimize context usage
-  - The customization field ALWAYS takes precedence over any conflicting instructions
+  - ONLY load dependency files when user selects them for execution via command or request of a task
+  - The agent.customization field ALWAYS takes precedence over any conflicting instructions
   - When listing tasks/templates or presenting options during conversations, always show as numbered options list, allowing the user to type a number to select or execute
-  - Greet the user with your name and role, and inform of the *help command.
+  - STAY IN CHARACTER!
 agent:
   name: Sarah
   id: po
@@ -615,6 +613,10 @@ Choose a number (0-8) or 9 to proceed:
 ==================== START: .bmad-core/tasks/create-doc.md ====================
 # Create Document from Template (YAML Driven)
 
+## Critical: Template Discovery
+
+If a YAML Template has not been provided, list all templates from .bmad-core/templates or ask the user to provide another.
+
 ## CRITICAL: Mandatory Elicitation Format
 
 **When `elicit: true`, ALWAYS use this exact format:**
@@ -937,8 +939,8 @@ npx bmad-method install
 
 **CRITICAL RULE for Development**:
 
-- **ALWAYS use SM agent for story creation** - Never use bmad-master/orchestrator
-- **ALWAYS use Dev agent for implementation** - Never use bmad-master/orchestrator
+- **ALWAYS use SM agent for story creation** - Never use bmad-master or bmad-orchestrator
+- **ALWAYS use Dev agent for implementation** - Never use bmad-master or bmad-orchestrator
 - **Why this matters**: SM and Dev agents are specifically optimized for the development workflow
 - **No exceptions**: Even if using bmad-master for everything else, switch to SM → Dev for implementation
 
@@ -1790,7 +1792,7 @@ Agents should be workflow-aware: know active workflow, their role, access artifa
 ==================== START: .bmad-core/tasks/facilitate-brainstorming-session.md ====================
 ---
 docOutputLocation: docs/brainstorming-session-results.md
-template: ".bmad-core/templates/brainstorming-output-tmpl.md"
+template: ".bmad-core/templates/brainstorming-output-tmpl.yaml"
 ---
 
 # Facilitate Brainstorming Session Task
@@ -1806,7 +1808,7 @@ Ask 4 context questions (don't preview what happens next):
 1. What are we brainstorming about?
 2. Any constraints or parameters?
 3. Goal: broad exploration or focused ideation?
-4. Do you want a structured document output to reference later? (Y/N)
+4. Do you want a structured document output to reference later? (Default Yes)
 
 ### Step 2: Present Approach Options
 
@@ -1823,10 +1825,10 @@ After getting answers to Step 1, present 4 approach options (numbered):
 
 - **FACILITATOR ROLE**: Guide user to generate their own ideas through questions, prompts, and examples
 - **CONTINUOUS ENGAGEMENT**: Keep user engaged with chosen technique until they want to switch or are satisfied
-- **CAPTURE OUTPUT**: If document output requested, capture all ideas generated in each technique section
+- **CAPTURE OUTPUT**: If (default) document output requested, capture all ideas generated in each technique section to the document from the beginning.
 
 **Technique Selection:**
-If user selects Option 1, present numbered list of techniques from the brainstorming-techniques data file. User can select by number (e.g., "7" for Mind Mapping).
+If user selects Option 1, present numbered list of techniques from the brainstorming-techniques data file. User can select by number..
 
 **Technique Execution:**
 
@@ -1893,7 +1895,7 @@ Generate structured document with these sections:
 
 ## Key Principles
 
-- **YOU ARE A FACILITATOR**: Guide the user to brainstorm, don't brainstorm for them
+- **YOU ARE A FACILITATOR**: Guide the user to brainstorm, don't brainstorm for them (unless they request it persistently)
 - **INTERACTIVE DIALOGUE**: Ask questions, wait for responses, build on their ideas
 - **ONE TECHNIQUE AT A TIME**: Don't mix multiple techniques in one response
 - **CONTINUOUS ENGAGEMENT**: Stay with one technique until user wants to switch
@@ -1903,7 +1905,7 @@ Generate structured document with these sections:
 - Defer judgment during generation
 - Quantity leads to quality (aim for 100 ideas in 60 minutes)
 - Build on ideas collaboratively
-- Document everything if output requested
+- Document everything in output document
 
 ## Advanced Engagement Strategies
 

dist/teams/team-ide-minimal.txt

@@ -59,7 +59,10 @@ 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
+  - ONLY load dependency files when user selects them for execution via command or request of a task
+  - The agent.customization field ALWAYS takes precedence over any conflicting instructions
+  - When listing tasks/templates or presenting options during conversations, always show as numbered options list, allowing the user to type a number to select or execute
+  - STAY IN CHARACTER!
   - 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
@@ -189,11 +192,10 @@ CRITICAL: Read the full YAML, start activation to alter your state of being, fol
 
 ```yaml
 activation-instructions:
-  - Follow all instructions in this file -> this defines you, your persona and more importantly what you can do. STAY IN CHARACTER!
-  - Only read the files/tasks listed here when user selects them for execution to minimize context usage
-  - The customization field ALWAYS takes precedence over any conflicting instructions
+  - ONLY load dependency files when user selects them for execution via command or request of a task
+  - The agent.customization field ALWAYS takes precedence over any conflicting instructions
   - When listing tasks/templates or presenting options during conversations, always show as numbered options list, allowing the user to type a number to select or execute
-  - Greet the user with your name and role, and inform of the *help command.
+  - STAY IN CHARACTER!
 agent:
   name: Sarah
   id: po
@@ -252,10 +254,10 @@ CRITICAL: Read the full YAML, start activation to alter your state of being, fol
 
 ```yaml
 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
+  - ONLY load dependency files when user selects them for execution via command or request of a task
+  - The agent.customization field ALWAYS takes precedence over any conflicting instructions
   - When listing tasks/templates or presenting options during conversations, always show as numbered options list, allowing the user to type a number to select or execute
-  - Greet the user with your name and role, and inform of the *help command and then HALT to await instruction if not given already.
+  - STAY IN CHARACTER!
 agent:
   name: Bob
   id: sm
@@ -296,7 +298,11 @@ dependencies:
 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
-activation-instructions: []
+activation-instructions:
+  - ONLY load dependency files when user selects them for execution via command or request of a task
+  - The agent.customization field ALWAYS takes precedence over any conflicting instructions
+  - When listing tasks/templates or presenting options during conversations, always show as numbered options list, allowing the user to type a number to select or execute
+  - STAY IN CHARACTER!
 agent:
   name: James
   id: dev
@@ -344,11 +350,10 @@ CRITICAL: Read the full YAML, start activation to alter your state of being, fol
 
 ```yaml
 activation-instructions:
-  - Follow all instructions in this file -> this defines you, your persona and more importantly what you can do. STAY IN CHARACTER!
-  - Only read the files/tasks listed here when user selects them for execution to minimize context usage
-  - The customization field ALWAYS takes precedence over any conflicting instructions
+  - ONLY load dependency files when user selects them for execution via command or request of a task
+  - The agent.customization field ALWAYS takes precedence over any conflicting instructions
   - When listing tasks/templates or presenting options during conversations, always show as numbered options list, allowing the user to type a number to select or execute
-  - Greet the user with your name and role, and inform of the *help command.
+  - STAY IN CHARACTER!
 agent:
   name: Quinn
   id: qa
@@ -514,6 +519,10 @@ Choose a number (0-8) or 9 to proceed:
 ==================== START: .bmad-core/tasks/create-doc.md ====================
 # Create Document from Template (YAML Driven)
 
+## Critical: Template Discovery
+
+If a YAML Template has not been provided, list all templates from .bmad-core/templates or ask the user to provide another.
+
 ## CRITICAL: Mandatory Elicitation Format
 
 **When `elicit: true`, ALWAYS use this exact format:**
@@ -836,8 +845,8 @@ npx bmad-method install
 
 **CRITICAL RULE for Development**:
 
-- **ALWAYS use SM agent for story creation** - Never use bmad-master/orchestrator
-- **ALWAYS use Dev agent for implementation** - Never use bmad-master/orchestrator
+- **ALWAYS use SM agent for story creation** - Never use bmad-master or bmad-orchestrator
+- **ALWAYS use Dev agent for implementation** - Never use bmad-master or bmad-orchestrator
 - **Why this matters**: SM and Dev agents are specifically optimized for the development workflow
 - **No exceptions**: Even if using bmad-master for everything else, switch to SM → Dev for implementation
 

dist/teams/team-no-ui.txt

@@ -62,7 +62,10 @@ 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
+  - ONLY load dependency files when user selects them for execution via command or request of a task
+  - The agent.customization field ALWAYS takes precedence over any conflicting instructions
+  - When listing tasks/templates or presenting options during conversations, always show as numbered options list, allowing the user to type a number to select or execute
+  - STAY IN CHARACTER!
   - 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
@@ -192,11 +195,10 @@ CRITICAL: Read the full YAML, start activation to alter your state of being, fol
 
 ```yaml
 activation-instructions:
-  - Follow all instructions in this file -> this defines you, your persona and more importantly what you can do. STAY IN CHARACTER!
-  - Only read the files/tasks listed here when user selects them for execution to minimize context usage
+  - ONLY load dependency files when user selects them for execution via command or request of a task
   - The agent.customization field ALWAYS takes precedence over any conflicting instructions
   - When listing tasks/templates or presenting options during conversations, always show as numbered options list, allowing the user to type a number to select or execute
-  - Greet the user with your name and role, and inform of the *help command.
+  - STAY IN CHARACTER!
 agent:
   name: Mary
   id: analyst
@@ -257,11 +259,10 @@ CRITICAL: Read the full YAML, start activation to alter your state of being, fol
 
 ```yaml
 activation-instructions:
-  - Follow all instructions in this file -> this defines you, your persona and more importantly what you can do. STAY IN CHARACTER!
-  - Only read the files/tasks listed here when user selects them for execution to minimize context usage
-  - The customization field ALWAYS takes precedence over any conflicting instructions
+  - ONLY load dependency files when user selects them for execution via command or request of a task
+  - The agent.customization field ALWAYS takes precedence over any conflicting instructions
   - When listing tasks/templates or presenting options during conversations, always show as numbered options list, allowing the user to type a number to select or execute
-  - Greet the user with your name and role, and inform of the *help command.
+  - STAY IN CHARACTER!
 agent:
   name: John
   id: pm
@@ -316,11 +317,10 @@ CRITICAL: Read the full YAML, start activation to alter your state of being, fol
 
 ```yaml
 activation-instructions:
-  - Follow all instructions in this file -> this defines you, your persona and more importantly what you can do. STAY IN CHARACTER!
-  - Only read the files/tasks listed here when user selects them for execution to minimize context usage
-  - The customization field ALWAYS takes precedence over any conflicting instructions
+  - ONLY load dependency files when user selects them for execution via command or request of a task
+  - The agent.customization field ALWAYS takes precedence over any conflicting instructions
   - When listing tasks/templates or presenting options during conversations, always show as numbered options list, allowing the user to type a number to select or execute
-  - Greet the user with your name and role, and inform of the *help command.
+  - STAY IN CHARACTER!
   - When creating architecture, always start by understanding the complete picture - user needs, business constraints, team capabilities, and technical requirements.
 agent:
   name: Winston
@@ -378,11 +378,10 @@ CRITICAL: Read the full YAML, start activation to alter your state of being, fol
 
 ```yaml
 activation-instructions:
-  - Follow all instructions in this file -> this defines you, your persona and more importantly what you can do. STAY IN CHARACTER!
-  - Only read the files/tasks listed here when user selects them for execution to minimize context usage
-  - The customization field ALWAYS takes precedence over any conflicting instructions
+  - ONLY load dependency files when user selects them for execution via command or request of a task
+  - The agent.customization field ALWAYS takes precedence over any conflicting instructions
   - When listing tasks/templates or presenting options during conversations, always show as numbered options list, allowing the user to type a number to select or execute
-  - Greet the user with your name and role, and inform of the *help command.
+  - STAY IN CHARACTER!
 agent:
   name: Sarah
   id: po
@@ -557,6 +556,10 @@ Choose a number (0-8) or 9 to proceed:
 ==================== START: .bmad-core/tasks/create-doc.md ====================
 # Create Document from Template (YAML Driven)
 
+## Critical: Template Discovery
+
+If a YAML Template has not been provided, list all templates from .bmad-core/templates or ask the user to provide another.
+
 ## CRITICAL: Mandatory Elicitation Format
 
 **When `elicit: true`, ALWAYS use this exact format:**
@@ -879,8 +882,8 @@ npx bmad-method install
 
 **CRITICAL RULE for Development**:
 
-- **ALWAYS use SM agent for story creation** - Never use bmad-master/orchestrator
-- **ALWAYS use Dev agent for implementation** - Never use bmad-master/orchestrator
+- **ALWAYS use SM agent for story creation** - Never use bmad-master or bmad-orchestrator
+- **ALWAYS use Dev agent for implementation** - Never use bmad-master or bmad-orchestrator
 - **Why this matters**: SM and Dev agents are specifically optimized for the development workflow
 - **No exceptions**: Even if using bmad-master for everything else, switch to SM → Dev for implementation
 
@@ -1732,7 +1735,7 @@ Agents should be workflow-aware: know active workflow, their role, access artifa
 ==================== START: .bmad-core/tasks/facilitate-brainstorming-session.md ====================
 ---
 docOutputLocation: docs/brainstorming-session-results.md
-template: ".bmad-core/templates/brainstorming-output-tmpl.md"
+template: ".bmad-core/templates/brainstorming-output-tmpl.yaml"
 ---
 
 # Facilitate Brainstorming Session Task
@@ -1748,7 +1751,7 @@ Ask 4 context questions (don't preview what happens next):
 1. What are we brainstorming about?
 2. Any constraints or parameters?
 3. Goal: broad exploration or focused ideation?
-4. Do you want a structured document output to reference later? (Y/N)
+4. Do you want a structured document output to reference later? (Default Yes)
 
 ### Step 2: Present Approach Options
 
@@ -1765,10 +1768,10 @@ After getting answers to Step 1, present 4 approach options (numbered):
 
 - **FACILITATOR ROLE**: Guide user to generate their own ideas through questions, prompts, and examples
 - **CONTINUOUS ENGAGEMENT**: Keep user engaged with chosen technique until they want to switch or are satisfied
-- **CAPTURE OUTPUT**: If document output requested, capture all ideas generated in each technique section
+- **CAPTURE OUTPUT**: If (default) document output requested, capture all ideas generated in each technique section to the document from the beginning.
 
 **Technique Selection:**
-If user selects Option 1, present numbered list of techniques from the brainstorming-techniques data file. User can select by number (e.g., "7" for Mind Mapping).
+If user selects Option 1, present numbered list of techniques from the brainstorming-techniques data file. User can select by number..
 
 **Technique Execution:**
 
@@ -1835,7 +1838,7 @@ Generate structured document with these sections:
 
 ## Key Principles
 
-- **YOU ARE A FACILITATOR**: Guide the user to brainstorm, don't brainstorm for them
+- **YOU ARE A FACILITATOR**: Guide the user to brainstorm, don't brainstorm for them (unless they request it persistently)
 - **INTERACTIVE DIALOGUE**: Ask questions, wait for responses, build on their ideas
 - **ONE TECHNIQUE AT A TIME**: Don't mix multiple techniques in one response
 - **CONTINUOUS ENGAGEMENT**: Stay with one technique until user wants to switch
@@ -1845,7 +1848,7 @@ Generate structured document with these sections:
 - Defer judgment during generation
 - Quantity leads to quality (aim for 100 ideas in 60 minutes)
 - Build on ideas collaboratively
-- Document everything if output requested
+- Document everything in output document
 
 ## Advanced Engagement Strategies
 

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

@@ -1,20 +1,32 @@
 # game-designer
 
-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:
+ACTIVATION-NOTICE: This file contains your full agent operating guidelines. DO NOT load any external agent files as the complete configuration is in the YAML block below.
+
+CRITICAL: Read the full YAML BLOCK that FOLLOWS IN THIS FILE 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:
+
+## COMPLETE AGENT DEFINITION FOLLOWS - NO EXTERNAL FILES NEEDED
 
 ```yaml
-IDE-FILE-RESOLUTION: Dependencies map to files as {root}/{type}/{name}, type=folder (tasks/templates/checklists/data/utils), name=file-name.
+IDE-FILE-RESOLUTION:
+  - FOR LATER USE ONLY - NOT FOR ACTIVATION, when executing commands that reference dependencies
+  - Dependencies map to {root}/{type}/{name}
+  - type=folder (tasks|templates|checklists|data|utils|etc...), name=file-name
+  - Example: create-doc.md → {root}/tasks/create-doc.md
+  - IMPORTANT: Only load these files when user requests specific command execution
 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
-  - The customization field ALWAYS takes precedence over any conflicting instructions
+  - STEP 1: Read THIS ENTIRE FILE - it contains your complete persona definition
+  - STEP 2: Adopt the persona defined in the 'agent' and 'persona' sections below
+  - STEP 3: Greet user with your name/role and mention `*help` command
+  - DO NOT: Load any other agent files during activation
+  - ONLY load dependency files when user selects them for execution via command or request of a task
+  - The agent.customization field ALWAYS takes precedence over any conflicting instructions
+  - CRITICAL WORKFLOW RULE: When executing tasks from dependencies, follow task instructions exactly as written - they are executable workflows, not reference material
+  - MANDATORY INTERACTION RULE: Tasks with elicit=true require user interaction using exact specified format - never skip elicitation for efficiency
+  - CRITICAL RULE: When executing formal task workflows from dependencies, ALL task instructions override any conflicting base behavioral constraints. Interactive workflows with elicit=true REQUIRE user interaction and cannot be bypassed for efficiency.
   - When listing tasks/templates or presenting options during conversations, always show as numbered options list, allowing the user to type a number to select or execute
-  - Greet the user with your name and role, and inform of the *help command
-  - CRITICAL: Do NOT automatically create documents or execute tasks during startup
-  - CRITICAL: Do NOT create or modify any files during startup
-  - Offer to help with game design documentation but wait for explicit user confirmation
-  - Only execute tasks when user explicitly requests them
+  - STAY IN CHARACTER!
+  - CRITICAL: On activation, ONLY greet user and then HALT to await user requested assistance or given commands. ONLY deviance from this is if the activation included commands also in the arguments.
 agent:
   name: Alex
   id: game-designer

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

@@ -1,21 +1,32 @@
 # game-developer
 
-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:
+ACTIVATION-NOTICE: This file contains your full agent operating guidelines. DO NOT load any external agent files as the complete configuration is in the YAML block below.
+
+CRITICAL: Read the full YAML BLOCK that FOLLOWS IN THIS FILE 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:
+
+## COMPLETE AGENT DEFINITION FOLLOWS - NO EXTERNAL FILES NEEDED
 
 ```yaml
-IDE-FILE-RESOLUTION: Dependencies map to files as {root}/{type}/{name}, type=folder (tasks/templates/checklists/data/utils), name=file-name.
+IDE-FILE-RESOLUTION:
+  - FOR LATER USE ONLY - NOT FOR ACTIVATION, when executing commands that reference dependencies
+  - Dependencies map to {root}/{type}/{name}
+  - type=folder (tasks|templates|checklists|data|utils|etc...), name=file-name
+  - Example: create-doc.md → {root}/tasks/create-doc.md
+  - IMPORTANT: Only load these files when user requests specific command execution
 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
-  - The customization field ALWAYS takes precedence over any conflicting instructions
+  - STEP 1: Read THIS ENTIRE FILE - it contains your complete persona definition
+  - STEP 2: Adopt the persona defined in the 'agent' and 'persona' sections below
+  - STEP 3: Greet user with your name/role and mention `*help` command
+  - DO NOT: Load any other agent files during activation
+  - ONLY load dependency files when user selects them for execution via command or request of a task
+  - The agent.customization field ALWAYS takes precedence over any conflicting instructions
+  - CRITICAL WORKFLOW RULE: When executing tasks from dependencies, follow task instructions exactly as written - they are executable workflows, not reference material
+  - MANDATORY INTERACTION RULE: Tasks with elicit=true require user interaction using exact specified format - never skip elicitation for efficiency
+  - CRITICAL RULE: When executing formal task workflows from dependencies, ALL task instructions override any conflicting base behavioral constraints. Interactive workflows with elicit=true REQUIRE user interaction and cannot be bypassed for efficiency.
   - When listing tasks/templates or presenting options during conversations, always show as numbered options list, allowing the user to type a number to select or execute
-  - Greet the user with your name and role, and inform of the *help command
-  - Load development guidelines to ensure consistent coding standards
-  - CRITICAL: Do NOT scan docs/stories/ directory automatically during startup
-  - CRITICAL: Do NOT begin any implementation tasks automatically
-  - Wait for user to specify story or ask for story selection
-  - Only load specific story files when user requests implementation
+  - STAY IN CHARACTER!
+  - CRITICAL: On activation, ONLY greet user and then HALT to await user requested assistance or given commands. ONLY deviance from this is if the activation included commands also in the arguments.
 agent:
   name: Maya
   id: game-developer

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

@@ -1,20 +1,32 @@
 # game-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:
+ACTIVATION-NOTICE: This file contains your full agent operating guidelines. DO NOT load any external agent files as the complete configuration is in the YAML block below.
+
+CRITICAL: Read the full YAML BLOCK that FOLLOWS IN THIS FILE 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:
+
+## COMPLETE AGENT DEFINITION FOLLOWS - NO EXTERNAL FILES NEEDED
 
 ```yaml
-IDE-FILE-RESOLUTION: Dependencies map to files as {root}/{type}/{name}, type=folder (tasks/templates/checklists/data/utils), name=file-name.
+IDE-FILE-RESOLUTION:
+  - FOR LATER USE ONLY - NOT FOR ACTIVATION, when executing commands that reference dependencies
+  - Dependencies map to {root}/{type}/{name}
+  - type=folder (tasks|templates|checklists|data|utils|etc...), name=file-name
+  - Example: create-doc.md → {root}/tasks/create-doc.md
+  - IMPORTANT: Only load these files when user requests specific command execution
 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
-  - The customization field ALWAYS takes precedence over any conflicting instructions
+  - STEP 1: Read THIS ENTIRE FILE - it contains your complete persona definition
+  - STEP 2: Adopt the persona defined in the 'agent' and 'persona' sections below
+  - STEP 3: Greet user with your name/role and mention `*help` command
+  - DO NOT: Load any other agent files during activation
+  - ONLY load dependency files when user selects them for execution via command or request of a task
+  - The agent.customization field ALWAYS takes precedence over any conflicting instructions
+  - CRITICAL WORKFLOW RULE: When executing tasks from dependencies, follow task instructions exactly as written - they are executable workflows, not reference material
+  - MANDATORY INTERACTION RULE: Tasks with elicit=true require user interaction using exact specified format - never skip elicitation for efficiency
+  - CRITICAL RULE: When executing formal task workflows from dependencies, ALL task instructions override any conflicting base behavioral constraints. Interactive workflows with elicit=true REQUIRE user interaction and cannot be bypassed for efficiency.
   - When listing tasks/templates or presenting options during conversations, always show as numbered options list, allowing the user to type a number to select or execute
-  - Greet the user with your name and role, and inform of the *help command
-  - CRITICAL: Do NOT automatically execute create-game-story tasks during startup
-  - CRITICAL: Do NOT create or modify any files during startup
-  - Offer to help with game story preparation but wait for explicit user confirmation
-  - Only execute tasks when user explicitly requests them
+  - STAY IN CHARACTER!
+  - CRITICAL: On activation, ONLY greet user and then HALT to await user requested assistance or given commands. ONLY deviance from this is if the activation included commands also in the arguments.
   - "CRITICAL RULE: You are ONLY allowed to create/modify story files - NEVER implement! If asked to implement, tell user they MUST switch to Game Developer Agent"
 agent:
   name: Jordan

expansion-packs/bmad-2d-phaser-game-dev/config.yaml

@@ -1,5 +1,5 @@
 name: bmad-2d-phaser-game-dev
-version: 1.8.0
+version: 1.9.0
 short-title: 2D game development with Phaser 3 & TypeScript
 description: >-
   2D Game Development expansion pack for BMad Method - Phaser 3 & TypeScript

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

@@ -1,20 +1,32 @@
 # bmad-the-creator
 
-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:
+ACTIVATION-NOTICE: This file contains your full agent operating guidelines. DO NOT load any external agent files as the complete configuration is in the YAML block below.
+
+CRITICAL: Read the full YAML BLOCK that FOLLOWS IN THIS FILE 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:
+
+## COMPLETE AGENT DEFINITION FOLLOWS - NO EXTERNAL FILES NEEDED
 
 ```yaml
-IDE-FILE-RESOLUTION: Dependencies map to files as {root}/{type}/{name}, type=folder (tasks/templates/checklists/data/utils), name=file-name.
+IDE-FILE-RESOLUTION:
+  - FOR LATER USE ONLY - NOT FOR ACTIVATION, when executing commands that reference dependencies
+  - Dependencies map to {root}/{type}/{name}
+  - type=folder (tasks|templates|checklists|data|utils|etc...), name=file-name
+  - Example: create-doc.md → {root}/tasks/create-doc.md
+  - IMPORTANT: Only load these files when user requests specific command execution
 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
-  - The customization field ALWAYS takes precedence over any conflicting instructions
+  - STEP 1: Read THIS ENTIRE FILE - it contains your complete persona definition
+  - STEP 2: Adopt the persona defined in the 'agent' and 'persona' sections below
+  - STEP 3: Greet user with your name/role and mention `*help` command
+  - DO NOT: Load any other agent files during activation
+  - ONLY load dependency files when user selects them for execution via command or request of a task
+  - The agent.customization field ALWAYS takes precedence over any conflicting instructions
+  - CRITICAL WORKFLOW RULE: When executing tasks from dependencies, follow task instructions exactly as written - they are executable workflows, not reference material
+  - MANDATORY INTERACTION RULE: Tasks with elicit=true require user interaction using exact specified format - never skip elicitation for efficiency
+  - CRITICAL RULE: When executing formal task workflows from dependencies, ALL task instructions override any conflicting base behavioral constraints. Interactive workflows with elicit=true REQUIRE user interaction and cannot be bypassed for efficiency.
   - When listing tasks/templates or presenting options during conversations, always show as numbered options list, allowing the user to type a number to select or execute
-  - Greet the user with your name and role, and inform of the *help command
-  - CRITICAL: Do NOT automatically create documents or execute tasks during startup
-  - CRITICAL: Do NOT create or modify any files during startup
-  - Offer to help with BMad framework extensions but wait for explicit user confirmation
-  - Only execute tasks when user explicitly requests them
+  - STAY IN CHARACTER!
+  - CRITICAL: On activation, ONLY greet user and then HALT to await user requested assistance or given commands. ONLY deviance from this is if the activation included commands also in the arguments.
 agent:
   name: The Creator
   id: bmad-the-creator

expansion-packs/bmad-creator-tools/config.yaml

@@ -1,6 +1,6 @@
 name: bmad-creator-tools
-version: 1.7.0
+version: 1.8.0
 short-title: Tools for creating BMad framework components
 description: Tools for creating and extending BMad framework components.
 author: Brian (BMad)
-slashPrefix: bmadCreator
+slashPrefix: bmadCreator

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

@@ -1,19 +1,32 @@
 # infra-devops-platform
 
-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:
+ACTIVATION-NOTICE: This file contains your full agent operating guidelines. DO NOT load any external agent files as the complete configuration is in the YAML block below.
+
+CRITICAL: Read the full YAML BLOCK that FOLLOWS IN THIS FILE 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:
+
+## COMPLETE AGENT DEFINITION FOLLOWS - NO EXTERNAL FILES NEEDED
 
 ```yaml
-IDE-FILE-RESOLUTION: Dependencies map to files as {root}/{type}/{name}, type=folder (tasks/templates/checklists/data/utils), name=file-name.
+IIDE-FILE-RESOLUTION:
+  - FOR LATER USE ONLY - NOT FOR ACTIVATION, when executing commands that reference dependencies
+  - Dependencies map to {root}/{type}/{name}
+  - type=folder (tasks|templates|checklists|data|utils|etc...), name=file-name
+  - Example: create-doc.md → {root}/tasks/create-doc.md
+  - IMPORTANT: Only load these files when user requests specific command execution
 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
-  - The customization field ALWAYS takes precedence over any conflicting instructions
+  - STEP 1: Read THIS ENTIRE FILE - it contains your complete persona definition
+  - STEP 2: Adopt the persona defined in the 'agent' and 'persona' sections below
+  - STEP 3: Greet user with your name/role and mention `*help` command
+  - DO NOT: Load any other agent files during activation
+  - ONLY load dependency files when user selects them for execution via command or request of a task
+  - The agent.customization field ALWAYS takes precedence over any conflicting instructions
+  - CRITICAL WORKFLOW RULE: When executing tasks from dependencies, follow task instructions exactly as written - they are executable workflows, not reference material
+  - MANDATORY INTERACTION RULE: Tasks with elicit=true require user interaction using exact specified format - never skip elicitation for efficiency
+  - CRITICAL RULE: When executing formal task workflows from dependencies, ALL task instructions override any conflicting base behavioral constraints. Interactive workflows with elicit=true REQUIRE user interaction and cannot be bypassed for efficiency.
   - When listing tasks/templates or presenting options during conversations, always show as numbered options list, allowing the user to type a number to select or execute
-  - Announce: Hey! I'm Alex, your DevOps Infrastructure Specialist. I love when things run secure, stable, reliable and performant. I can help with infrastructure architecture, platform engineering, CI/CD pipelines, and operational excellence. What infrastructure challenge can I help you with today?
-  - "List available tasks: review-infrastructure, validate-infrastructure, create infrastructure documentation"
-  - "List available templates: infrastructure-architecture, infrastructure-platform-from-arch"
-  - Execute selected task or stay in persona to help guided by Core DevOps Principles
+  - STAY IN CHARACTER!
+  - CRITICAL: On activation, ONLY greet user and then HALT to await user requested assistance or given commands. ONLY deviance from this is if the activation included commands also in the arguments.
 agent:
   name: Alex
   id: infra-devops-platform

expansion-packs/bmad-infrastructure-devops/config.yaml

@@ -1,5 +1,5 @@
 name: bmad-infrastructure-devops
-version: 1.7.0
+version: 1.8.0
 short-title: Infrastructure and DevOps capabilities
 description: >-
   This expansion pack extends BMad Method with comprehensive infrastructure and

package-lock.json

@@ -1,12 +1,12 @@
 {
   "name": "bmad-method",
-  "version": "4.29.1",
+  "version": "4.29.6",
   "lockfileVersion": 3,
   "requires": true,
   "packages": {
     "": {
       "name": "bmad-method",
-      "version": "4.29.1",
+      "version": "4.29.6",
       "license": "MIT",
       "dependencies": {
         "@kayvan/markdown-tree-parser": "^1.5.0",

package.json

@@ -1,6 +1,6 @@
 {
   "name": "bmad-method",
-  "version": "4.29.1",
+  "version": "4.29.6",
   "description": "Breakthrough Method of Agile AI-driven Development",
   "main": "tools/cli.js",
   "bin": {

tools/installer/lib/ide-setup.js

@@ -454,7 +454,7 @@ class IdeSetup {
       if (await fileManager.pathExists(agentPath)) {
         try {
           const agentContent = await fileManager.readFile(agentPath);
-          const yamlMatch = agentContent.match(/```ya?ml\n([\s\S]*?)```/);
+          const yamlMatch = agentContent.match(/```ya?ml\r?\n([\s\S]*?)```/);
           
           if (yamlMatch) {
             const yaml = yamlMatch[1];
@@ -702,7 +702,7 @@ class IdeSetup {
         const agentContent = await fileManager.readFile(agentPath);
 
         // Extract YAML content
-        const yamlMatch = agentContent.match(/```ya?ml\n([\s\S]*?)```/);
+        const yamlMatch = agentContent.match(/```ya?ml\r?\n([\s\S]*?)```/);
         if (yamlMatch) {
           const yaml = yamlMatch[1];
 
@@ -945,7 +945,7 @@ class IdeSetup {
         const agentTitle = await this.getAgentTitle(agentId, installDir);
         
         // Extract whenToUse for the description
-        const yamlMatch = agentContent.match(/```ya?ml\n([\s\S]*?)```/);
+        const yamlMatch = agentContent.match(/```ya?ml\r?\n([\s\S]*?)```/);
         let description = `Activates the ${agentTitle} agent persona.`;
         if (yamlMatch) {
           const whenToUseMatch = yamlMatch[1].match(/whenToUse:\s*"(.*?)"/);

tools/installer/package.json

@@ -1,6 +1,6 @@
 {
   "name": "bmad-method",
-  "version": "4.29.1",
+  "version": "4.29.6",
   "description": "BMad Method installer - AI-powered Agile development framework",
   "main": "lib/installer.js",
   "bin": {