feat: add configurable interaction_style with platform-specific structured question directives

Add a new `interaction_style` config setting (open/structured) to module.yaml
that controls how agents ask questions. When set to "structured", agents use
numbered option lists; when "open" (default), they use natural conversation.

Platform-specific templates for Claude Code use `AskUserQuestion` tool,
Gemini uses `ask_user`, OpenCode uses `question` tool, and default/kiro/
other platforms use generic structured options.

Changes:
- Add interaction_style to src/core/module.yaml (between output_folder and
  tool_supports_subagents)
- Add RULE directive to all 27+ IDE templates across 7 platforms
- Add interaction_style to activation-rules, activation-steps, handlers,
  workflow.xml, and agent-command-header
- Create dedicated Claude Code templates (claude-agent, claude-task,
  claude-tool, claude-workflow, claude-workflow-yaml) replacing symlinks
- Add claude template_type to platform-codes.yaml
- Update codex.js installer for claude support
- Document interaction_style in install-bmad.md

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

CHANGELOG.md

@@ -1,5 +1,20 @@
 # Changelog
 
+## [6.0.4]
+
+### 🎁 Features
+
+* Add edge case hunter review task - new reusable review task that exhaustively traces branching paths and boundary conditions in code, reporting only unhandled gaps. Method-driven analysis complementary to adversarial review (#1790)
+
+### 🐛 Bug Fixes
+
+* Fix brainstorming to not overwrite previous sessions; now prompts to continue existing brainstorming or start a new one when older brainstorming sessions are found
+* Fix installer templates - replace legacy `@` path prefixes with explicit `{project-root}` syntax for consistency (#1769)
+* Fix edge case hunter - remove zero-findings halt condition that was pressuring the LLM to hallucinate findings when none legitimately exist (#1797)
+* Fix broken docs domain references in README and GitHub issue templates (#1777)
+
+---
+
 ## [6.0.3]
 
 ### 🎁 Features

docs/how-to/install-bmad.md

@@ -57,9 +57,24 @@ Each tool has its own way of integrating commands. The installer creates tiny pr
 
 The installer shows available modules. Select whichever ones you need — most users just want **BMad Method** (the software development module).
 
-### 5. Follow the Prompts
+### 5. Configure Settings
 
-The installer guides you through the rest — custom content, settings, etc.
+The installer prompts you for core settings that control how agents behave:
+
+| Setting | Default | Description |
+| ------- | ------- | ----------- |
+| **User Name** | `BMad` | What agents call you — use your name or a team name |
+| **Communication Language** | `English` | Language agents use when chatting with you |
+| **Document Output Language** | `English` | Language for generated documents and artifacts |
+| **Output Folder** | `_bmad-output` | Where agents save generated files |
+| **Interaction Style** | `structured` | How agents ask you questions (see below) |
+
+**Interaction Style** controls how agents present choices:
+
+- **Structured** (recommended) — Agents present numbered option lists for every question, using your IDE's native question tool when available. This keeps conversations focused and reduces ambiguity.
+- **Open** — Agents ask natural conversational questions. More flexible but can lead to longer back-and-forth.
+
+These settings are saved to `_bmad/<module>/config.yaml` and can be changed later by editing that file and rerunning the installer.
 
 ## What You Get
 

package-lock.json

@@ -1,12 +1,12 @@
 {
   "name": "bmad-method",
-  "version": "6.0.3",
+  "version": "6.0.4",
   "lockfileVersion": 3,
   "requires": true,
   "packages": {
     "": {
       "name": "bmad-method",
-      "version": "6.0.3",
+      "version": "6.0.4",
       "license": "MIT",
       "dependencies": {
         "@clack/core": "^1.0.0",

package.json

@@ -1,7 +1,7 @@
 {
   "$schema": "https://json.schemastore.org/package.json",
   "name": "bmad-method",
-  "version": "6.0.3",
+  "version": "6.0.4",
   "description": "Breakthrough Method of Agile AI-driven Development",
   "keywords": [
     "agile",

src/core/module.yaml

@@ -2,7 +2,7 @@ code: core
 name: "BMad Core Module"
 
 header: "BMad Core Configuration"
-subheader: "Configure the core settings for your BMad installation.\nThese settings will be used across all modules and agents."
+subheader: "Configure the core settings for your BMad installation.\nThese settings will be used across all installed bmad skills, workflows, and agents."
 
 user_name:
   prompt: "What should agents call you? (Use your name or a team name)"
@@ -23,3 +23,23 @@ output_folder:
   prompt: "Where should output files be saved?"
   default: "_bmad-output"
   result: "{project-root}/{value}"
+
+interaction_style:
+  prompt: "How should agents ask you questions?"
+  default: "open"
+  result: "{value}"
+  single-select:
+    - value: "open"
+      label: "Open - Natural conversational questions (recommended)"
+    - value: "structured"
+      label: "Structured - Numbered option lists"
+
+tool_supports_subagents:
+  prompt: "Subagents are supported by the LLM or Tool I will be using?"
+  default: true
+  result: "{value}"
+
+tool_supports_agent_teams:
+  prompt: "Agent Teams are supported by the LLM or Tool I will be using?"
+  default: false
+  result: "{value}"

src/core/tasks/review-edge-case-hunter.xml

@@ -57,7 +57,6 @@ No extra text, no explanations, no markdown wrapping.</output-format>
   </flow>
 
   <halt-conditions>
-    <condition>HALT if zero findings - this is suspicious, re-analyze or ask for guidance</condition>
     <condition>HALT if content is empty or unreadable</condition>
   </halt-conditions>
 

src/core/tasks/workflow.xml

@@ -2,6 +2,7 @@
   <objective>Execute given workflow by loading its configuration, following instructions, and producing output</objective>
 
   <llm critical="true">
+    <mandate>RULE: Check your stored {interaction_style} session variable from activation step 2. When its value is "structured", EVERY question to the user MUST use the native question tool. No exceptions. No inline prompts. When {interaction_style} is "open", ask questions naturally in conversation. If you cannot determine {interaction_style}, default to open mode.</mandate>
     <mandate>Always read COMPLETE files - NEVER use offset/limit when reading any workflow related files</mandate>
     <mandate>Instructions are MANDATORY - either as file path, steps or embedded list in YAML, XML or markdown</mandate>
     <mandate>Execute ALL steps in instructions IN EXACT ORDER</mandate>

src/core/workflows/brainstorming/steps/step-01-session-setup.md

@@ -29,23 +29,30 @@ Initialize the brainstorming workflow by detecting continuation state and settin
 
 ## INITIALIZATION SEQUENCE:
 
-### 1. Check for Existing Workflow
+### 1. Check for Existing Sessions
 
-First, check if the output document already exists:
+First, check the brainstorming sessions folder for existing sessions:
 
-- Look for file at `{output_folder}/brainstorming/brainstorming-session-{{date}}.md`
-- If exists, read the complete file including frontmatter
-- If not exists, this is a fresh workflow
+- List all files in `{output_folder}/brainstorming/`
+- **DO NOT read any file contents** - only list filenames
+- If files exist, identify the most recent by date/time in the filename
+- If no files exist, this is a fresh workflow
 
-### 2. Handle Continuation (If Document Exists)
+### 2. Handle Existing Sessions (If Files Found)
 
-If the document exists and has frontmatter with `stepsCompleted`:
+If existing session files are found:
 
-- **STOP here** and load `./step-01b-continue.md` immediately
-- Do not proceed with any initialization tasks
-- Let step-01b handle the continuation logic
+- Display the most recent session filename (do NOT read its content)
+- Ask the user: "Found existing session: `[filename]`. Would you like to:
+  **[1]** Continue this session
+  **[2]** Start a new session
+  **[3]** See all existing sessions"
 
-### 3. Fresh Workflow Setup (If No Document)
+- If user selects **[1]** (continue): Set `{brainstorming_session_output_file}` to that file path and load `./step-01b-continue.md`
+- If user selects **[2]** (new): Generate new filename with current date/time and proceed to step 3
+- If user selects **[3]** (see all): List all session filenames and ask which to continue or if new
+
+### 3. Fresh Workflow Setup (If No Files or User Chooses New)
 
 If no document exists or no `stepsCompleted` in frontmatter:
 
@@ -55,10 +62,10 @@ Create the brainstorming session document:
 
 ```bash
 # Create directory if needed
-mkdir -p "$(dirname "{output_folder}/brainstorming/brainstorming-session-{{date}}.md")"
+mkdir -p "$(dirname "{brainstorming_session_output_file}")"
 
 # Initialize from template
-cp "{template_path}" "{output_folder}/brainstorming/brainstorming-session-{{date}}.md"
+cp "{template_path}" "{brainstorming_session_output_file}"
 ```
 
 #### B. Context File Check and Loading
@@ -134,7 +141,7 @@ _[Content based on conversation about session parameters and facilitator approac
 
 ## APPEND TO DOCUMENT:
 
-When user selects approach, append the session overview content directly to `{output_folder}/brainstorming/brainstorming-session-{{date}}.md` using the structure from above.
+When user selects approach, append the session overview content directly to `{brainstorming_session_output_file}` using the structure from above.
 
 ### E. Continue to Technique Selection
 
@@ -152,7 +159,7 @@ Which approach appeals to you most? (Enter 1-4)"
 
 #### When user selects approach number:
 
-- **Append initial session overview to `{output_folder}/brainstorming/brainstorming-session-{{date}}.md`**
+- **Append initial session overview to `{brainstorming_session_output_file}`**
 - **Update frontmatter:** `stepsCompleted: [1]`, `selected_approach: '[selected approach]'`
 - **Load the appropriate step-02 file** based on selection
 
@@ -167,7 +174,9 @@ After user selects approach number:
 
 ## SUCCESS METRICS:
 
-✅ Existing workflow detected and continuation handled properly
+✅ Existing sessions detected without reading file contents
+✅ User prompted to continue existing session or start new
+✅ Correct session file selected for continuation
 ✅ Fresh workflow initialized with correct document structure
 ✅ Session context gathered and understood clearly
 ✅ User's approach selection captured and routed correctly
@@ -176,7 +185,9 @@ After user selects approach number:
 
 ## FAILURE MODES:
 
-❌ Not checking for existing document before creating new one
+❌ Reading file contents during session detection (wastes context)
+❌ Not asking user before continuing existing session
+❌ Not properly routing user's continue/new session selection
 ❌ Missing continuation detection leading to duplicate work
 ❌ Insufficient session context gathering
 ❌ Not properly routing user's approach selection
@@ -184,7 +195,9 @@ After user selects approach number:
 
 ## SESSION SETUP PROTOCOLS:
 
-- Always verify document existence before initialization
+- Always list sessions folder WITHOUT reading file contents
+- Ask user before continuing any existing session
+- Only load continue step after user confirms
 - Load brain techniques CSV only when needed for technique presentation
 - Use collaborative facilitation language throughout
 - Maintain psychological safety for creative exploration

src/core/workflows/brainstorming/steps/step-01b-continue.md

@@ -35,7 +35,7 @@ Load existing document and analyze current state:
 
 **Document Analysis:**
 
-- Read existing `{output_folder}/brainstorming/brainstorming-session-{{date}}.md`
+- Read existing `{brainstorming_session_output_file}`
 - Examine frontmatter for `stepsCompleted`, `session_topic`, `session_goals`
 - Review content to understand session progress and outcomes
 - Identify current stage and next logical steps

src/core/workflows/brainstorming/steps/step-03-technique-execution.md

@@ -296,7 +296,7 @@ After final technique element:
 
 #### If 'C' (Move to organization):
 
-- **Append the technique execution content to `{output_folder}/brainstorming/brainstorming-session-{{date}}.md`**
+- **Append the technique execution content to `{brainstorming_session_output_file}`**
 - **Update frontmatter:** `stepsCompleted: [1, 2, 3]`
 - **Load:** `./step-04-idea-organization.md`
 
@@ -356,7 +356,7 @@ _[Short narrative describing the user and AI collaboration journey - what made t
 
 ## APPEND TO DOCUMENT:
 
-When user selects 'C', append the content directly to `{output_folder}/brainstorming/brainstorming-session-{{date}}.md` using the structure from above.
+When user selects 'C', append the content directly to `{brainstorming_session_output_file}` using the structure from above.
 
 ## SUCCESS METRICS:
 

src/core/workflows/brainstorming/steps/step-04-idea-organization.md

@@ -253,14 +253,14 @@ Provide final session wrap-up and forward guidance:
 
 #### If [C] Complete:
 
-- **Append the final session content to `{output_folder}/brainstorming/brainstorming-session-{{date}}.md`**
+- **Append the final session content to `{brainstorming_session_output_file}`**
 - Update frontmatter: `stepsCompleted: [1, 2, 3, 4]`
 - Set `session_active: false` and `workflow_completed: true`
 - Complete workflow with positive closure message
 
 ## APPEND TO DOCUMENT:
 
-When user selects 'C', append the content directly to `{output_folder}/brainstorming/brainstorming-session-{{date}}.md` using the structure from step 7.
+When user selects 'C', append the content directly to `{brainstorming_session_output_file}` using the structure from step 7.
 
 ## SUCCESS METRICS:
 

src/core/workflows/brainstorming/workflow.md

@@ -45,7 +45,9 @@ Load config from `{project-root}/_bmad/core/config.yaml` and resolve:
 - `installed_path` = `{project-root}/_bmad/core/workflows/brainstorming`
 - `template_path` = `{installed_path}/template.md`
 - `brain_techniques_path` = `{installed_path}/brain-methods.csv`
-- `default_output_file` = `{output_folder}/brainstorming/brainstorming-session-{{date}}.md`
+- `brainstorming_session_output_file` = `{output_folder}/brainstorming/brainstorming-session-{{date}}-{{time}}.md` (evaluated once at workflow start)
+
+All steps MUST reference `{brainstorming_session_output_file}` instead of the full path pattern.
 - `context_file` = Optional context file path from workflow invocation for project-specific guidance
 - `advancedElicitationTask` = `{project-root}/_bmad/core/workflows/advanced-elicitation/workflow.xml`
 

src/utility/agent-components/activation-rules.txt

@@ -1,5 +1,6 @@
   <rules>
     <r>ALWAYS communicate in {communication_language} UNLESS contradicted by communication_style.</r>
+    <r>Check your stored {interaction_style} session variable from activation step 2. When its value is "structured", EVERY question to the user MUST use structured options with a numbered list unless the workflow or user explicitly requests free-form input. If you cannot determine {interaction_style}, default to open mode.</r>
     <r> Stay in character until exit selected</r>
     <r> Display Menu items as the item dictates and in the order given.</r>
     <r> Load files ONLY when executing a user chosen workflow or a command requires it, EXCEPTION: agent activation step 2 config.yaml</r>

src/utility/agent-components/activation-steps.txt

@@ -1,7 +1,7 @@
     <step n="1">Load persona from this current agent file (already in context)</step>
     <step n="2">🚨 IMMEDIATE ACTION REQUIRED - BEFORE ANY OUTPUT:
         - Load and read {project-root}/_bmad/{{module}}/config.yaml NOW
-        - Store ALL fields as session variables: {user_name}, {communication_language}, {output_folder}
+        - Store ALL fields as session variables: {user_name}, {communication_language}, {output_folder}, {interaction_style}, {document_output_language}
         - VERIFY: If config not loaded, STOP and report error to user
         - DO NOT PROCEED to step 3 until config is successfully loaded and variables stored
     </step>

src/utility/agent-components/agent-command-header.md

@@ -1 +1,3 @@
 You must fully embody this agent's persona and follow all activation instructions, steps and rules exactly as specified. NEVER break character until given an exit command.
+
+RULE: Check your stored {interaction_style} session variable from activation step 2. When its value is "structured", EVERY question to the user MUST call the AskUserQuestion tool. Do NOT write questions as plain text. No exceptions. If you cannot determine {interaction_style}, default to open mode.

src/utility/agent-components/handler-action.txt

@@ -1,4 +1,5 @@
   <handler type="action">
     When menu item has: action="#id" → Find prompt with id="id" in current agent XML, follow its content
     When menu item has: action="text" → Follow the text directly as an inline instruction
+    RULE: Check your stored {interaction_style} session variable from activation step 2. When its value is "structured", ALL questions to the user MUST use the AskUserQuestion tool. No plain text prompts. If you cannot determine {interaction_style}, default to open mode.
   </handler>

src/utility/agent-components/handler-exec.txt

@@ -3,4 +3,5 @@
       1. Read fully and follow the file at that path
       2. Process the complete file and follow all instructions within it
       3. If there is data="some/path/data-foo.md" with the same item, pass that data path to the executed file as context.
+      4. RULE: Check your stored {interaction_style} session variable from activation step 2. When its value is "structured", ALL questions to the user MUST use the AskUserQuestion tool. No plain text prompts. If you cannot determine {interaction_style}, default to open mode.
     </handler>

src/utility/agent-components/handler-multi.txt

@@ -10,5 +10,5 @@
             - For workflow="path/to/workflow.yaml": follow the `handler type="workflow"` instructions
             - For action="...": Perform the specified action directly
          5. Support both exact matches and fuzzy matching based on the match attribute
-         6. If no handler matches, prompt user to choose from available options
+         6. If no handler matches, prompt user to choose from available options using the AskUserQuestion tool when interaction_style is "structured"
       </handler>

src/utility/agent-components/handler-validate-workflow.txt

@@ -3,5 +3,5 @@
         1. You MUST LOAD the file at: {project-root}/_bmad/core/tasks/validate-workflow.xml
         2. READ its entire contents and EXECUTE all instructions in that file
         3. Pass the workflow, and also check the workflow yaml validation property to find and load the validation schema to pass as the checklist
-        4. The workflow should try to identify the file to validate based on checklist context or else you will ask the user to specify
+        4. The workflow should try to identify the file to validate based on checklist context or else ask the user to specify using the AskUserQuestion tool when interaction_style is "structured"
     </handler>

src/utility/agent-components/handler-workflow.txt

@@ -7,4 +7,5 @@
       4. Follow workflow.xml instructions precisely following all steps
       5. Save outputs after completing EACH workflow step (never batch multiple steps together)
       6. If workflow.yaml path is "todo", inform user the workflow hasn't been implemented yet
+      7. RULE: Check your stored {interaction_style} session variable from activation step 2. When its value is "structured", ALL questions to the user MUST use the AskUserQuestion tool. No plain text prompts. If you cannot determine {interaction_style}, default to open mode.
     </handler>

tools/cli/installers/lib/ide/codex.js

@@ -416,6 +416,7 @@ class CodexSetup extends BaseIdeSetup {
     const skillContent =
       `---\n${fm}\n---\n` +
       "\nYou must fully embody this agent's persona and follow all activation instructions exactly as specified. NEVER break character until given an exit command.\n" +
+      '\nRULE: Check your stored {interaction_style} session variable from activation step 2. When its value is "structured", EVERY question to the user MUST call the `ask_user_question` tool unless the workflow or user explicitly requests free-form input. If you cannot determine {interaction_style}, default to open mode.\n' +
       '\n<agent-activation CRITICAL="TRUE">\n' +
       `1. LOAD the FULL agent file from @${agentPath}\n` +
       '2. READ its entire contents - this contains the complete agent persona, menu, and instructions\n' +

tools/cli/installers/lib/ide/platform-codes.yaml

@@ -39,7 +39,7 @@ platforms:
     description: "Anthropic's official CLI for Claude"
     installer:
       target_dir: .claude/commands
-      template_type: default
+      template_type: claude
       ancestor_conflict_check: true
 
   cline:

tools/cli/installers/lib/ide/templates/agent-command-template.md

@@ -5,8 +5,10 @@ description: '{{description}}'
 
 You must fully embody this agent's persona and follow all activation instructions exactly as specified. NEVER break character until given an exit command.
 
+RULE: Check your stored {interaction_style} session variable from activation step 2. When its value is "structured", EVERY question to the user MUST use structured options with a numbered list unless the workflow or user explicitly requests free-form input. If you cannot determine {interaction_style}, default to open mode.
+
 <agent-activation CRITICAL="TRUE">
-1. LOAD the FULL agent file from @_bmad/{{module}}/agents/{{path}}
+1. LOAD the FULL agent file from {project-root}/_bmad/{{module}}/agents/{{path}}
 2. READ its entire contents - this contains the complete agent persona, menu, and instructions
 3. Execute ALL activation steps exactly as written in the agent file
 4. Follow the agent's persona and menu system precisely

tools/cli/installers/lib/ide/templates/combined/antigravity.md

@@ -3,6 +3,8 @@ name: '{{name}}'
 description: '{{description}}'
 ---
 
-Read the entire workflow file at: {project-root}/_bmad/{{workflow_path}}
+Read the entire workflow file at: {project-root}/{{bmadFolderName}}/{{workflow_path}}
 
 Follow all instructions in the workflow file exactly as written.
+
+RULE: Check your stored {interaction_style} session variable from activation step 2. When its value is "structured", EVERY question to the user MUST use structured options with a numbered list unless the workflow or user explicitly requests free-form input. If you cannot determine {interaction_style}, default to open mode.

tools/cli/installers/lib/ide/templates/combined/claude-agent.md

@@ -1 +0,0 @@
-default-agent.md

tools/cli/installers/lib/ide/templates/combined/claude-agent.md

@@ -0,0 +1,17 @@
+---
+name: '{{name}}'
+description: '{{description}}'
+---
+
+You must fully embody this agent's persona and follow all activation instructions exactly as specified. NEVER break character until given an exit command.
+
+RULE: Check your stored {interaction_style} session variable from activation step 2. When its value is "structured", EVERY question to the user MUST call the `AskUserQuestion` tool unless the workflow or user explicitly requests free-form input. If you cannot determine {interaction_style}, default to open mode.
+
+<agent-activation CRITICAL="TRUE">
+1. LOAD the FULL agent file from {project-root}/{{bmadFolderName}}/{{path}}
+2. READ its entire contents - this contains the complete agent persona, menu, and instructions
+3. FOLLOW every step in the <activation> section precisely
+4. DISPLAY the welcome/greeting as instructed
+5. PRESENT the numbered menu
+6. WAIT for user input before proceeding
+</agent-activation>

tools/cli/installers/lib/ide/templates/combined/claude-task.md

@@ -0,0 +1,12 @@
+---
+name: '{{name}}'
+description: '{{description}}'
+---
+
+# {{name}}
+
+RULE: Check your stored {interaction_style} session variable from activation step 2. When its value is "structured", EVERY question to the user MUST call the `AskUserQuestion` tool unless the workflow or user explicitly requests free-form input. If you cannot determine {interaction_style}, default to open mode.
+
+Read the entire task file at: {project-root}/{{bmadFolderName}}/{{path}}
+
+Follow all instructions in the task file exactly as written.

tools/cli/installers/lib/ide/templates/combined/claude-tool.md

@@ -0,0 +1,12 @@
+---
+name: '{{name}}'
+description: '{{description}}'
+---
+
+# {{name}}
+
+RULE: Check your stored {interaction_style} session variable from activation step 2. When its value is "structured", EVERY question to the user MUST call the `AskUserQuestion` tool unless the workflow or user explicitly requests free-form input. If you cannot determine {interaction_style}, default to open mode.
+
+Read the entire tool file at: {project-root}/{{bmadFolderName}}/{{path}}
+
+Follow all instructions in the tool file exactly as written.

tools/cli/installers/lib/ide/templates/combined/claude-workflow-yaml.md

@@ -1 +0,0 @@
-default-workflow-yaml.md

tools/cli/installers/lib/ide/templates/combined/claude-workflow-yaml.md

@@ -0,0 +1,16 @@
+---
+name: '{{name}}'
+description: '{{description}}'
+---
+
+RULE: Check your stored {interaction_style} session variable from activation step 2. When its value is "structured", EVERY question to the user MUST call the `AskUserQuestion` tool unless the workflow or user explicitly requests free-form input. If you cannot determine {interaction_style}, default to open mode.
+
+IT IS CRITICAL THAT YOU FOLLOW THESE STEPS - while staying in character as the current agent persona you may have loaded:
+
+<steps CRITICAL="TRUE">
+1. Always LOAD the FULL {project-root}/{{bmadFolderName}}/core/tasks/workflow.xml
+2. READ its entire contents - this is the CORE OS for EXECUTING the specific workflow-config {project-root}/{{bmadFolderName}}/{{path}}
+3. Pass the yaml path {project-root}/{{bmadFolderName}}/{{path}} as 'workflow-config' parameter to the workflow.xml instructions
+4. Follow workflow.xml instructions EXACTLY as written to process and follow the specific workflow config and its instructions
+5. Save outputs after EACH section when generating any documents from templates
+</steps>

tools/cli/installers/lib/ide/templates/combined/claude-workflow.md

@@ -1 +0,0 @@
-default-workflow.md

tools/cli/installers/lib/ide/templates/combined/claude-workflow.md

@@ -0,0 +1,8 @@
+---
+name: '{{name}}'
+description: '{{description}}'
+---
+
+RULE: Check your stored {interaction_style} session variable from activation step 2. When its value is "structured", EVERY question to the user MUST call the `AskUserQuestion` tool unless the workflow or user explicitly requests free-form input. If you cannot determine {interaction_style}, default to open mode.
+
+IT IS CRITICAL THAT YOU FOLLOW THIS COMMAND: LOAD the FULL {project-root}/{{bmadFolderName}}/{{path}}, READ its entire contents and follow its directions exactly!

tools/cli/installers/lib/ide/templates/combined/default-agent.md

@@ -5,8 +5,10 @@ description: '{{description}}'
 
 You must fully embody this agent's persona and follow all activation instructions exactly as specified. NEVER break character until given an exit command.
 
+RULE: Check your stored {interaction_style} session variable from activation step 2. When its value is "structured", EVERY question to the user MUST use structured options with a numbered list unless the workflow or user explicitly requests free-form input. If you cannot determine {interaction_style}, default to open mode.
+
 <agent-activation CRITICAL="TRUE">
-1. LOAD the FULL agent file from {project-root}/_bmad/{{path}}
+1. LOAD the FULL agent file from {project-root}/{{bmadFolderName}}/{{path}}
 2. READ its entire contents - this contains the complete agent persona, menu, and instructions
 3. FOLLOW every step in the <activation> section precisely
 4. DISPLAY the welcome/greeting as instructed

tools/cli/installers/lib/ide/templates/combined/default-task.md

@@ -5,6 +5,8 @@ description: '{{description}}'
 
 # {{name}}
 
+RULE: Check your stored {interaction_style} session variable from activation step 2. When its value is "structured", EVERY question to the user MUST use structured options with a numbered list unless the workflow or user explicitly requests free-form input. If you cannot determine {interaction_style}, default to open mode.
+
 Read the entire task file at: {project-root}/{{bmadFolderName}}/{{path}}
 
 Follow all instructions in the task file exactly as written.

tools/cli/installers/lib/ide/templates/combined/default-tool.md

@@ -5,6 +5,8 @@ description: '{{description}}'
 
 # {{name}}
 
+RULE: Check your stored {interaction_style} session variable from activation step 2. When its value is "structured", EVERY question to the user MUST use structured options with a numbered list unless the workflow or user explicitly requests free-form input. If you cannot determine {interaction_style}, default to open mode.
+
 Read the entire tool file at: {project-root}/{{bmadFolderName}}/{{path}}
 
 Follow all instructions in the tool file exactly as written.

tools/cli/installers/lib/ide/templates/combined/default-workflow-yaml.md

@@ -3,12 +3,14 @@ name: '{{name}}'
 description: '{{description}}'
 ---
 
+RULE: Check your stored {interaction_style} session variable from activation step 2. When its value is "structured", EVERY question to the user MUST use structured options with a numbered list unless the workflow or user explicitly requests free-form input. If you cannot determine {interaction_style}, default to open mode.
+
 IT IS CRITICAL THAT YOU FOLLOW THESE STEPS - while staying in character as the current agent persona you may have loaded:
 
 <steps CRITICAL="TRUE">
-1. Always LOAD the FULL @{project-root}/{{bmadFolderName}}/core/tasks/workflow.xml
-2. READ its entire contents - this is the CORE OS for EXECUTING the specific workflow-config @{project-root}/{{bmadFolderName}}/{{path}}
-3. Pass the yaml path @{project-root}/{{bmadFolderName}}/{{path}} as 'workflow-config' parameter to the workflow.xml instructions
+1. Always LOAD the FULL {project-root}/{{bmadFolderName}}/core/tasks/workflow.xml
+2. READ its entire contents - this is the CORE OS for EXECUTING the specific workflow-config {project-root}/{{bmadFolderName}}/{{path}}
+3. Pass the yaml path {project-root}/{{bmadFolderName}}/{{path}} as 'workflow-config' parameter to the workflow.xml instructions
 4. Follow workflow.xml instructions EXACTLY as written to process and follow the specific workflow config and its instructions
 5. Save outputs after EACH section when generating any documents from templates
 </steps>

tools/cli/installers/lib/ide/templates/combined/default-workflow.md

@@ -3,4 +3,6 @@ name: '{{name}}'
 description: '{{description}}'
 ---
 
-IT IS CRITICAL THAT YOU FOLLOW THIS COMMAND: LOAD the FULL @{project-root}/{{bmadFolderName}}/{{path}}, READ its entire contents and follow its directions exactly!
+RULE: Check your stored {interaction_style} session variable from activation step 2. When its value is "structured", EVERY question to the user MUST use structured options with a numbered list unless the workflow or user explicitly requests free-form input. If you cannot determine {interaction_style}, default to open mode.
+
+IT IS CRITICAL THAT YOU FOLLOW THIS COMMAND: LOAD the FULL {project-root}/{{bmadFolderName}}/{{path}}, READ its entire contents and follow its directions exactly!

tools/cli/installers/lib/ide/templates/combined/gemini-agent.toml

@@ -6,6 +6,9 @@ PRE-FLIGHT CHECKLIST:
 1.  [ ] IMMEDIATE ACTION: Load and parse {project-root}/{{bmadFolderName}}/{{module}}/config.yaml - store ALL config values in memory for use throughout the session.
 2.  [ ] IMMEDIATE ACTION: Read and internalize the full agent definition at {project-root}/{{bmadFolderName}}/{{path}}.
 3.  [ ] CONFIRM: The user's name from config is {user_name}.
+4.  [ ] CONFIRM: interaction_style is set to "{interaction_style}".
+
+RULE: Check your stored {interaction_style} session variable from activation step 2. When its value is "structured", EVERY question to the user MUST call the ask_user tool unless the workflow or user explicitly requests free-form input. If you cannot determine {interaction_style}, default to open mode.
 
 Only after all checks are complete, greet the user by name and display the menu.
 Acknowledge this checklist is complete in your first response.

tools/cli/installers/lib/ide/templates/combined/gemini-task.toml

@@ -7,5 +7,7 @@ TASK INSTRUCTIONS:
 2. READ its entire contents
 3. FOLLOW every instruction precisely as specified
 
+RULE: Check your stored {interaction_style} session variable from activation step 2. When its value is "structured", EVERY question to the user MUST call the ask_user tool unless the workflow or user explicitly requests free-form input. If you cannot determine {interaction_style}, default to open mode.
+
 TASK FILE: {project-root}/{{bmadFolderName}}/{{path}}
 """

tools/cli/installers/lib/ide/templates/combined/gemini-tool.toml

@@ -7,5 +7,7 @@ TOOL INSTRUCTIONS:
 2. READ its entire contents
 3. FOLLOW every instruction precisely as specified
 
+RULE: Check your stored {interaction_style} session variable from activation step 2. When its value is "structured", EVERY question to the user MUST call the ask_user tool unless the workflow or user explicitly requests free-form input. If you cannot determine {interaction_style}, default to open mode.
+
 TOOL FILE: {project-root}/{{bmadFolderName}}/{{path}}
 """

tools/cli/installers/lib/ide/templates/combined/gemini-workflow-yaml.toml

@@ -12,5 +12,7 @@ CRITICAL: This is a structured YAML workflow. Follow these steps precisely:
 3. EXECUTE each step in order
 4. VALIDATE outputs before proceeding to next step
 
+RULE: Check your stored {interaction_style} session variable from activation step 2. When its value is "structured", EVERY question to the user MUST call the ask_user tool unless the workflow or user explicitly requests free-form input. If you cannot determine {interaction_style}, default to open mode.
+
 WORKFLOW FILE: {project-root}/{{bmadFolderName}}/{{workflow_path}}
 """

tools/cli/installers/lib/ide/templates/combined/gemini-workflow.toml

@@ -10,5 +10,7 @@ WORKFLOW INSTRUCTIONS:
 3. FOLLOW every step precisely as specified
 4. DO NOT skip or modify any steps
 
+RULE: Check your stored {interaction_style} session variable from activation step 2. When its value is "structured", EVERY question to the user MUST call the ask_user tool unless the workflow or user explicitly requests free-form input. If you cannot determine {interaction_style}, default to open mode.
+
 WORKFLOW FILE: {project-root}/{{bmadFolderName}}/{{workflow_path}}
 """

tools/cli/installers/lib/ide/templates/combined/kiro-agent.md

@@ -6,6 +6,8 @@ inclusion: manual
 
 You must fully embody this agent's persona and follow all activation instructions exactly as specified. NEVER break character until given an exit command.
 
+RULE: Check your stored {interaction_style} session variable from activation step 2. When its value is "structured", EVERY question to the user MUST use structured options with a numbered list unless the workflow or user explicitly requests free-form input. If you cannot determine {interaction_style}, default to open mode.
+
 <agent-activation CRITICAL="TRUE">
 1. LOAD the FULL agent file from #[[file:{{bmadFolderName}}/{{path}}]]
 2. READ its entire contents - this contains the complete agent persona, menu, and instructions

tools/cli/installers/lib/ide/templates/combined/kiro-task.md

@@ -7,3 +7,5 @@ inclusion: manual
 Read the entire task file at: #[[file:{{bmadFolderName}}/{{path}}]]
 
 Follow all instructions in the task file exactly as written.
+
+RULE: Check your stored {interaction_style} session variable from activation step 2. When its value is "structured", EVERY question to the user MUST use structured options with a numbered list unless the workflow or user explicitly requests free-form input. If you cannot determine {interaction_style}, default to open mode.

tools/cli/installers/lib/ide/templates/combined/kiro-tool.md

@@ -7,3 +7,5 @@ inclusion: manual
 Read the entire tool file at: #[[file:{{bmadFolderName}}/{{path}}]]
 
 Follow all instructions in the tool file exactly as written.
+
+RULE: Check your stored {interaction_style} session variable from activation step 2. When its value is "structured", EVERY question to the user MUST use structured options with a numbered list unless the workflow or user explicitly requests free-form input. If you cannot determine {interaction_style}, default to open mode.

tools/cli/installers/lib/ide/templates/combined/kiro-workflow-yaml.md

@@ -4,6 +4,8 @@ inclusion: manual
 
 # {{name}}
 
+RULE: Check your stored {interaction_style} session variable from activation step 2. When its value is "structured", EVERY question to the user MUST use structured options with a numbered list unless the workflow or user explicitly requests free-form input. If you cannot determine {interaction_style}, default to open mode.
+
 IT IS CRITICAL THAT YOU FOLLOW THESE STEPS - while staying in character as the current agent persona you may have loaded:
 
 <steps CRITICAL="TRUE">

tools/cli/installers/lib/ide/templates/combined/kiro-workflow.md

@@ -4,4 +4,6 @@ inclusion: manual
 
 # {{name}}
 
+RULE: Check your stored {interaction_style} session variable from activation step 2. When its value is "structured", EVERY question to the user MUST use structured options with a numbered list unless the workflow or user explicitly requests free-form input. If you cannot determine {interaction_style}, default to open mode.
+
 IT IS CRITICAL THAT YOU FOLLOW THIS COMMAND: LOAD the FULL #[[file:{{bmadFolderName}}/{{path}}]], READ its entire contents and follow its directions exactly!

tools/cli/installers/lib/ide/templates/combined/opencode-agent.md

@@ -5,6 +5,8 @@ description: '{{description}}'
 
 You must fully embody this agent's persona and follow all activation instructions exactly as specified. NEVER break character until given an exit command.
 
+RULE: Check your stored {interaction_style} session variable from activation step 2. When its value is "structured", EVERY question to the user MUST call the `question` tool unless the workflow or user explicitly requests free-form input. If you cannot determine {interaction_style}, default to open mode.
+
 <agent-activation CRITICAL="TRUE">
 1. LOAD the FULL agent file from {project-root}/{{bmadFolderName}}/{{path}}
 2. READ its entire contents - this contains the complete agent persona, menu, and instructions

tools/cli/installers/lib/ide/templates/combined/opencode-task.md

@@ -10,4 +10,6 @@ TASK INSTRUCTIONS:
 2. READ its entire contents
 3. FOLLOW every instruction precisely as specified
 
+RULE: Check your stored {interaction_style} session variable from activation step 2. When its value is "structured", EVERY question to the user MUST call the `question` tool unless the workflow or user explicitly requests free-form input. If you cannot determine {interaction_style}, default to open mode.
+
 TASK FILE: {project-root}/{{bmadFolderName}}/{{path}}

tools/cli/installers/lib/ide/templates/combined/opencode-tool.md

@@ -10,4 +10,6 @@ TOOL INSTRUCTIONS:
 2. READ its entire contents
 3. FOLLOW every instruction precisely as specified
 
+RULE: Check your stored {interaction_style} session variable from activation step 2. When its value is "structured", EVERY question to the user MUST call the `question` tool unless the workflow or user explicitly requests free-form input. If you cannot determine {interaction_style}, default to open mode.
+
 TOOL FILE: {project-root}/{{bmadFolderName}}/{{path}}

tools/cli/installers/lib/ide/templates/combined/opencode-workflow-yaml.md

@@ -13,4 +13,6 @@ WORKFLOW INSTRUCTIONS:
 3. FOLLOW every step precisely as specified
 4. DO NOT skip or modify any steps
 
+RULE: Check your stored {interaction_style} session variable from activation step 2. When its value is "structured", EVERY question to the user MUST call the `question` tool unless the workflow or user explicitly requests free-form input. If you cannot determine {interaction_style}, default to open mode.
+
 WORKFLOW FILE: {project-root}/{{bmadFolderName}}/{{path}}

tools/cli/installers/lib/ide/templates/combined/opencode-workflow.md

@@ -13,4 +13,6 @@ WORKFLOW INSTRUCTIONS:
 3. FOLLOW every step precisely as specified
 4. DO NOT skip or modify any steps
 
+RULE: Check your stored {interaction_style} session variable from activation step 2. When its value is "structured", EVERY question to the user MUST call the `question` tool unless the workflow or user explicitly requests free-form input. If you cannot determine {interaction_style}, default to open mode.
+
 WORKFLOW FILE: {project-root}/{{bmadFolderName}}/{{path}}

tools/cli/installers/lib/ide/templates/combined/rovodev.md

@@ -4,6 +4,8 @@
 
 ---
 
-Read the entire workflow file at: {project-root}/_bmad/{{workflow_path}}
+RULE: Check your stored {interaction_style} session variable from activation step 2. When its value is "structured", EVERY question to the user MUST use structured options with a numbered list unless the workflow or user explicitly requests free-form input. If you cannot determine {interaction_style}, default to open mode.
+
+Read the entire workflow file at: {project-root}/{{bmadFolderName}}/{{workflow_path}}
 
 Follow all instructions in the workflow file exactly as written.

tools/cli/installers/lib/ide/templates/combined/trae.md

@@ -4,6 +4,8 @@
 
 ## Instructions
 
-Read the entire workflow file at: {project-root}/_bmad/{{workflow_path}}
+Read the entire workflow file at: {project-root}/{{bmadFolderName}}/{{workflow_path}}
 
 Follow all instructions in the workflow file exactly as written.
+
+RULE: Check your stored {interaction_style} session variable from activation step 2. When its value is "structured", EVERY question to the user MUST use structured options with a numbered list unless the workflow or user explicitly requests free-form input. If you cannot determine {interaction_style}, default to open mode.

tools/cli/installers/lib/ide/templates/combined/windsurf-workflow.md

@@ -5,6 +5,8 @@ auto_execution_mode: "iterate"
 
 # {{name}}
 
-Read the entire workflow file at {project-root}/_bmad/{{workflow_path}}
+Read the entire workflow file at {project-root}/{{bmadFolderName}}/{{workflow_path}}
 
 Follow all instructions in the workflow file exactly as written.
+
+RULE: Check your stored {interaction_style} session variable from activation step 2. When its value is "structured", EVERY question to the user MUST use structured options with a numbered list unless the workflow or user explicitly requests free-form input. If you cannot determine {interaction_style}, default to open mode.

tools/cli/installers/lib/ide/templates/workflow-command-template.md

@@ -2,11 +2,13 @@
 description: '{{description}}'
 ---
 
+RULE: Check your stored {interaction_style} session variable from activation step 2. When its value is "structured", EVERY question to the user MUST use structured options with a numbered list unless the workflow or user explicitly requests free-form input. If you cannot determine {interaction_style}, default to open mode.
+
 IT IS CRITICAL THAT YOU FOLLOW THESE STEPS - while staying in character as the current agent persona you may have loaded:
 
 <steps CRITICAL="TRUE">
-1. Always LOAD the FULL @_bmad/core/tasks/workflow.xml
-2. READ its entire contents - this is the CORE OS for EXECUTING the specific workflow-config @{{workflow_path}}
+1. Always LOAD the FULL {project-root}/_bmad/core/tasks/workflow.xml
+2. READ its entire contents - this is the CORE OS for EXECUTING the specific workflow-config {project-root}/{{workflow_path}}
 3. Pass the yaml path {{workflow_path}} as 'workflow-config' parameter to the workflow.xml instructions
 4. Follow workflow.xml instructions EXACTLY as written to process and follow the specific workflow config and its instructions
 5. Save outputs after EACH section when generating any documents from templates

tools/cli/installers/lib/ide/templates/workflow-commander.md

@@ -2,4 +2,6 @@
 description: '{{description}}'
 ---
 
-IT IS CRITICAL THAT YOU FOLLOW THIS COMMAND: LOAD the FULL @{{workflow_path}}, READ its entire contents and follow its directions exactly!
+RULE: Check your stored {interaction_style} session variable from activation step 2. When its value is "structured", EVERY question to the user MUST use structured options with a numbered list unless the workflow or user explicitly requests free-form input. If you cannot determine {interaction_style}, default to open mode.
+
+IT IS CRITICAL THAT YOU FOLLOW THIS COMMAND: LOAD the FULL {project-root}/{{workflow_path}}, READ its entire contents and follow its directions exactly!