Merge 78646069ef into ed0defbe08

* fix: normalize workflow manifest schema

* fix: escape workflow manifest values safely

---------

Co-authored-by: Brian <bmadcode@gmail.com>

.coderabbit.yaml

@@ -4,9 +4,10 @@ language: "en-US"
 early_access: true
 reviews:
   profile: chill
-  high_level_summary: true
+  high_level_summary: false # don't post summary until explicitly invoked
   request_changes_workflow: false
   review_status: false
+  commit_status: false # don't set commit status until explicitly invoked
   collapse_walkthrough: false
   poem: false
   auto_review:
@@ -33,4 +34,7 @@ reviews:
         Flag any process.exit() without error message.
 chat:
   auto_reply: true # Response to mentions in comments, a la @coderabbit review
+issue_enrichment:
+  auto_enrich:
+    enabled: false # don't auto-comment on issues
 

package-lock.json

@@ -1,12 +1,12 @@
 {
   "name": "bmad-method",
-  "version": "6.0.0-alpha.15",
+  "version": "6.0.0-alpha.16",
   "lockfileVersion": 3,
   "requires": true,
   "packages": {
     "": {
       "name": "bmad-method",
-      "version": "6.0.0-alpha.15",
+      "version": "6.0.0-alpha.16",
       "license": "MIT",
       "dependencies": {
         "@kayvan/markdown-tree-parser": "^1.6.1",

src/core/tasks/workflow.xml

@@ -63,6 +63,8 @@
           <tag>invoke-workflow xml tag → Execute another workflow with given inputs and the workflow.xml runner</tag>
           <tag>invoke-task xml tag → Execute specified task</tag>
           <tag>invoke-protocol name="protocol_name" xml tag → Execute reusable protocol from protocols section</tag>
+          <tag>invoke-bash cmd="command" → Execute shell command, capture stdout/stderr, set {{bash_exit_code}}, {{bash_stdout}}, {{bash_stderr}}</tag>
+          <tag>set-var name="varname" value="..." → Set runtime variable {{varname}} to specified value (supports expressions)</tag>
           <tag>goto step="x" → Jump to specified step</tag>
         </execute-tags>
       </substep>
@@ -126,6 +128,8 @@
       <tag>invoke-workflow - Call another workflow</tag>
       <tag>invoke-task - Call a task</tag>
       <tag>invoke-protocol - Execute a reusable protocol (e.g., discover_inputs)</tag>
+      <tag>invoke-bash cmd="..." - Execute shell command, results in {{bash_exit_code}}, {{bash_stdout}}, {{bash_stderr}}</tag>
+      <tag>set-var name="..." value="..." - Set runtime variable dynamically</tag>
     </execution>
     <output>
       <tag>template-output - Save content checkpoint</tag>

src/modules/bmgd/workflows/4-production/code-review/instructions.md

@@ -330,7 +330,7 @@ Review was saved to story file, but sprint-status.yaml may be out of sync.
       <action>All action items are included in the standalone review report</action>
       <ask if="action items exist">Would you like me to create tracking items for these action items? (backlog/tasks)</ask>
       <action if="user confirms">
-        If {{backlog_file}} does not exist, copy {installed_path}/backlog_template.md to {{backlog_file}} location.
+        If {{backlog_file}} does not exist, copy {installed_path}/backlog-template.md to {{backlog_file}} location.
         Append a row per action item with Date={{date}}, Story="Ad-Hoc Review", Epic="N/A", Type, Severity, Owner (or "TBD"), Status="Open", Notes with file refs and context.
       </action>
     </check>
@@ -342,7 +342,7 @@ Review was saved to story file, but sprint-status.yaml may be out of sync.
         Append under the story's "Tasks / Subtasks" a new subsection titled "Review Follow-ups (AI)", adding each item as an unchecked checkbox in imperative form, prefixed with "[AI-Review]" and severity. Example: "- [ ] [AI-Review][High] Add input validation on server route /api/x (AC #2)".
       </action>
       <action>
-        If {{backlog_file}} does not exist, copy {installed_path}/backlog_template.md to {{backlog_file}} location.
+        If {{backlog_file}} does not exist, copy {installed_path}/backlog-template.md to {{backlog_file}} location.
         Append a row per action item with Date={{date}}, Story={{epic_num}}.{{story_num}}, Epic={{epic_num}}, Type, Severity, Owner (or "TBD"), Status="Open", Notes with short context and file refs.
       </action>
       <action>

src/modules/bmm/agents/dev.agent.yaml

@@ -24,7 +24,7 @@ agent:
 
   critical_actions:
     - "READ the entire story file BEFORE any implementation - tasks/subtasks sequence is your authoritative implementation guide"
-    - "Load project_context.md if available for coding standards only - never let it override story requirements"
+    - "Load project-context.md if available for coding standards only - never let it override story requirements"
     - "Execute tasks/subtasks IN ORDER as written in story file - no skipping, no reordering, no doing what you want"
     - "For each task/subtask: follow red-green-refactor cycle - write failing test first, then implementation"
     - "Mark task/subtask [x] ONLY when both implementation AND tests are complete and passing"

src/modules/bmm/docs/test-architecture.md

@@ -26,14 +26,17 @@ graph TB
     subgraph Phase3["<b>Phase 3: SOLUTIONING</b>"]
         Architecture["<b>Architect: *architecture</b>"]
         EpicsStories["<b>PM/Architect: *create-epics-and-stories</b>"]
+        TestDesignSys["<b>TEA: *test-design (system-level)</b>"]
         Framework["<b>TEA: *framework</b>"]
         CI["<b>TEA: *ci</b>"]
         GateCheck["<b>Architect: *implementation-readiness</b>"]
         Architecture --> EpicsStories
+        Architecture --> TestDesignSys
+        TestDesignSys --> Framework
         EpicsStories --> Framework
         Framework --> CI
         CI --> GateCheck
-        Phase3Note["<b>Epics created AFTER architecture,</b><br/><b>then test infrastructure setup</b>"]
+        Phase3Note["<b>Epics created AFTER architecture,</b><br/><b>then system-level test design and test infrastructure setup</b>"]
         EpicsStories -.-> Phase3Note
     end
 
@@ -93,12 +96,17 @@ graph TB
 - **Documentation** (Optional for brownfield): Prerequisite using `*document-project`
 - **Phase 1** (Optional): Discovery/Analysis (`*brainstorm`, `*research`, `*product-brief`)
 - **Phase 2** (Required): Planning (`*prd` creates PRD with FRs/NFRs)
-- **Phase 3** (Track-dependent): Solutioning (`*architecture` → `*create-epics-and-stories` → TEA: `*framework`, `*ci` → `*implementation-readiness`)
+- **Phase 3** (Track-dependent): Solutioning (`*architecture` → `*test-design` (system-level) → `*create-epics-and-stories` → TEA: `*framework`, `*ci` → `*implementation-readiness`)
 - **Phase 4** (Required): Implementation (`*sprint-planning` → per-epic: `*test-design` → per-story: dev workflows)
 
-**TEA workflows:** `*framework` and `*ci` run once in Phase 3 after architecture. `*test-design` runs per-epic in Phase 4. Output: `test-design-epic-N.md`.
+**TEA workflows:** `*framework` and `*ci` run once in Phase 3 after architecture. `*test-design` is **dual-mode**:
 
-Quick Flow track skips Phase 1 and 3. BMad Method and Enterprise use all phases based on project needs.
+- **System-level (Phase 3):** Run immediately after architecture/ADR drafting to produce `test-design-system.md` (testability review, ADR → test mapping, Architecturally Significant Requirements (ASRs), environment needs). Feeds the implementation-readiness gate.
+- **Epic-level (Phase 4):** Run per-epic to produce `test-design-epic-N.md` (risk, priorities, coverage plan).
+
+Quick Flow track skips Phases 1 and 3.
+BMad Method and Enterprise use all phases based on project needs.
+When an ADR or architecture draft is produced, run `*test-design` in **system-level** mode before the implementation-readiness gate. This ensures the ADR has an attached testability review and ADR → test mapping. Keep the test-design updated if ADRs change.
 
 ### Why TEA is Different from Other BMM Agents
 

src/modules/bmm/module.yaml

@@ -51,3 +51,23 @@ tea_use_playwright_utils:
     - "You must install packages yourself, or use test architect's *framework command."
   default: false
   result: "{value}"
+
+# External Code Review Agent Selection
+# Allows delegating code reviews to an external AI agent CLI for independent, unbiased reviews
+# Useful when using a different AI as primary IDE agent (e.g., Codex/Gemini users can use Claude for reviews)
+external_review_agent:
+  prompt:
+    - "Which external agent should perform code reviews?"
+    - "External agents provide independent, unbiased reviews separate from your primary IDE agent."
+    - "The selected CLI must be installed and configured on your system."
+  default: "none"
+  result: "{value}"
+  single-select:
+    - value: "codex"
+      label: "Codex (OpenAI) - Code review using OpenAI Codex CLI"
+    - value: "gemini"
+      label: "Gemini (Google) - Code review using Google Gemini CLI"
+    - value: "claude"
+      label: "Claude Code (Anthropic) - Code review using Claude Code CLI"
+    - value: "none"
+      label: "None - Use built-in review (no external agent)"

src/modules/bmm/workflows/2-plan-workflows/prd/workflow.md

@@ -1,6 +1,6 @@
 ---
 name: create-prd
-description: Creates a comprehensive PRDs through collaborative step-by-step discovery between two product managers working as peers.
+description: Creates a comprehensive PRD through collaborative step-by-step discovery between two product managers working as peers.
 main_config: '{project-root}/.bmad/bmm/config.yaml'
 web_bundle: true
 ---

src/modules/bmm/workflows/3-solutioning/architecture/steps/step-01-init.md

@@ -94,7 +94,7 @@ Discover and load context documents using smart discovery:
 
 **Project Context Rules (Critical for AI Agents):**
 
-1. Check for project context file: `**/project_context.md`
+1. Check for project context file: `**/project-context.md`
 2. If exists: Load COMPLETE file contents - this contains critical rules for AI agents
 3. Add to frontmatter `hasProjectContext: true` and track file path
 4. Report to user: "Found existing project context with {number_of_rules} agent rules"

src/modules/bmm/workflows/3-solutioning/architecture/steps/step-08-complete.md

@@ -280,7 +280,7 @@ Your architecture will ensure consistent, high-quality implementation across all
 
 **💡 Optional Enhancement: Project Context File**
 
-Would you like to create a `project_context.md` file? This is a concise, optimized guide for AI agents that captures:
+Would you like to create a `project-context.md` file? This is a concise, optimized guide for AI agents that captures:
 
 - Critical language and framework rules they might miss
 - Specific patterns and conventions for your project
@@ -310,7 +310,7 @@ This will help ensure consistent implementation by capturing:
 - Testing and quality standards
 - Anti-patterns to avoid
 
-The workflow will collaborate with you to create an optimized `project_context.md` file that AI agents will read before implementing any code."
+The workflow will collaborate with you to create an optimized `project-context.md` file that AI agents will read before implementing any code."
 
 **Execute the Generate Project Context workflow:**
 

src/modules/bmm/workflows/4-implementation/code-review/checklist.md

@@ -1,5 +1,7 @@
 # Senior Developer Review - Validation Checklist
 
+## Story Setup
+
 - [ ] Story file loaded from `{{story_path}}`
 - [ ] Story Status verified as reviewable (review)
 - [ ] Epic and Story IDs resolved ({{epic_num}}.{{story_num}})
@@ -7,12 +9,33 @@
 - [ ] Epic Tech Spec located or warning recorded
 - [ ] Architecture/standards docs loaded (as available)
 - [ ] Tech stack detected and documented
-- [ ] MCP doc search performed (or web fallback) and references captured
+
+## External Agent Detection (Runtime)
+
+- [ ] `invoke-bash cmd="command -v codex"` executed → {{codex_available}}
+- [ ] `invoke-bash cmd="command -v gemini"` executed → {{gemini_available}}
+- [ ] `invoke-bash cmd="command -v claude"` executed → {{claude_available}}
+- [ ] Review method determined: {{use_external_agent}} = true/false
+- [ ] If external: {{external_agent_cmd}} = codex OR gemini OR claude
+- [ ] Config updated with detection results and timestamp
+
+## Code Review Execution
+
+- [ ] Git vs Story discrepancies identified ({{git_findings}})
+- [ ] If external agent available: Prompt written to /tmp/code-review-prompt.txt
+- [ ] If external agent available: CLI invoked via `invoke-bash` (MANDATORY - NO EXCEPTIONS)
+- [ ] External agent output captured in {{bash_stdout}}
+- [ ] If external agent CLI failed (non-zero exit): Fallback to built-in review
+- [ ] ⚠️ VIOLATION CHECK: Did you skip external agent with a rationalization? If yes, RE-RUN with external agent.
 - [ ] Acceptance Criteria cross-checked against implementation
 - [ ] File List reviewed and validated for completeness
 - [ ] Tests identified and mapped to ACs; gaps noted
-- [ ] Code quality review performed on changed files
-- [ ] Security review performed on changed files and dependencies
+- [ ] Code quality review performed (security, performance, maintainability)
+- [ ] Minimum 3 issues found (adversarial review requirement)
+
+## Finalization
+
+- [ ] Findings categorized: HIGH/MEDIUM/LOW severity
 - [ ] Outcome decided (Approve/Changes Requested/Blocked)
 - [ ] Review notes appended under "Senior Developer Review (AI)"
 - [ ] Change Log updated with review entry
@@ -21,3 +44,4 @@
 - [ ] Story saved successfully
 
 _Reviewer: {{user_name}} on {{date}}_
+_External Agent: {{external_agent_cmd}} (codex:{{codex_available}} / gemini:{{gemini_available}} / claude:{{claude_available}})_

src/modules/bmm/workflows/4-implementation/code-review/external-agent-prompt.md

@@ -0,0 +1,35 @@
+You are an ADVERSARIAL code reviewer. Your job is to find problems, not approve code.
+
+VERY IMPORTANT!
+
+- This is a READ ONLY operation. You are not to change anything in this code.
+- You are FORBIDDEN to write to any files.
+- You are FORBIDDEN to change any files.
+- You are FORBIDDEN to delete any files.
+
+REQUIREMENTS:
+
+- Find 3-10 specific issues minimum - no lazy looks good reviews
+- Categorize as HIGH (must fix), MEDIUM (should fix), LOW (nice to fix)
+- For each issue: specify file:line, describe problem, suggest fix
+- Check: Security vulnerabilities, performance issues, error handling, test quality
+- Verify: Tasks marked [x] are actually done, ACs are actually implemented
+
+STORY CONTEXT: {{story_path}}
+FILES TO REVIEW: {{comprehensive_file_list}}
+ACCEPTANCE CRITERIA: {{acceptance_criteria_list}}
+TASKS: {{task_list}}
+
+OUTPUT FORMAT:
+
+## HIGH SEVERITY
+
+- [file:line] Issue description | Suggested fix
+
+## MEDIUM SEVERITY
+
+- [file:line] Issue description | Suggested fix
+
+## LOW SEVERITY
+
+- [file:line] Issue description | Suggested fix

src/modules/bmm/workflows/4-implementation/code-review/instructions.xml

@@ -4,16 +4,56 @@
   <critical>Communicate all responses in {communication_language} and language MUST be tailored to {user_skill_level}</critical>
   <critical>Generate all documents in {document_output_language}</critical>
 
-  <critical>🔥 YOU ARE AN ADVERSARIAL CODE REVIEWER - Find what's wrong or missing! 🔥</critical>
+  <!-- ================================================================ -->
+  <!-- CLAUDE CODE CLEANUP - MANDATORY KILL OF ALL BACKGROUND SHELLS   -->
+  <!-- ================================================================ -->
+  <!-- CRITICAL: Stale external agent processes cause context pollution.
+       You MUST kill ALL background shells BEFORE doing ANYTHING else.
+       DO NOT read their output. DO NOT check what they're doing.
+       Just KILL them unconditionally. -->
+  <critical>🚨 FIRST ACTION REQUIRED: Kill all background shells 🚨</critical>
+  <critical>Before ANY other workflow step, you MUST terminate all background processes.</critical>
+  <critical>DO NOT use BashOutput to read from stale shells - this causes context pollution.</critical>
+  <critical>DO NOT try to "check what they're doing" - just kill them.</critical>
+
+  <check if="BMAD is running as Claude Code (KillShell tool is available)">
+    <action>IMMEDIATELY use KillShell to terminate ALL background shells - no exceptions</action>
+    <action>Do NOT read output from these shells first - kill them blind</action>
+    <action>Do NOT rationalize keeping them alive - they contain stale data</action>
+    <action>If multiple shells exist, kill ALL of them one by one</action>
+    <output>🔪 Killed all background shells to prevent stale data contamination</output>
+  </check>
+  <critical>Only proceed to Step 1 AFTER all background shells are terminated.</critical>
+
+  <!-- ================================================================ -->
+  <!-- EXTERNAL AGENT MANDATE - THIS IS THE MOST IMPORTANT RULE        -->
+  <!-- ================================================================ -->
+  <critical>🚨 MANDATORY EXTERNAL AGENT RULE - NO EXCEPTIONS 🚨</critical>
+  <critical>If an external agent CLI (codex, gemini, or claude) is detected as available, you MUST delegate the code review to that agent.</critical>
+  <critical>You are FORBIDDEN from performing your own code review analysis if an external agent is available.</critical>
+  <critical>The external agent provides an independent, unbiased review. Your job is to INVOKE it, not replace it.</critical>
+  <critical>Only perform built-in review if ALL external agents fail detection OR the CLI invocation actually fails with a non-zero exit code.</critical>
+  <critical>DO NOT SKIP the invoke-bash commands for detection and invocation - they are MANDATORY.</critical>
+
+  <!-- PROHIBITED EXCUSES - DO NOT USE THESE TO SKIP EXTERNAL AGENT -->
+  <critical>🚫 PROHIBITED RATIONALIZATIONS - You may NOT skip the external agent for ANY of these reasons:</critical>
+  <critical>❌ "The prompt is too long" - Long prompts are expected and supported. Invoke anyway.</critical>
+  <critical>❌ "CLI is meant for simple operations" - FALSE. The CLI handles complex prompts. Invoke anyway.</critical>
+  <critical>❌ "This is a re-review" - Re-reviews MUST use external agent. No exception.</critical>
+  <critical>❌ "I can do this myself" - You are FORBIDDEN from self-review when external agent is available.</critical>
+  <critical>❌ "It would be faster/better if I do it" - Irrelevant. External agent is MANDATORY.</critical>
+  <critical>❌ "The context is too complex" - The external agent handles complexity. Invoke anyway.</critical>
+  <critical>If you find yourself rationalizing why to skip the external agent, STOP and invoke it anyway.</critical>
+
+  <critical>🔥 ADVERSARIAL CODE REVIEW REQUIREMENTS 🔥</critical>
   <critical>Your purpose: Validate story file claims against actual implementation</critical>
   <critical>Challenge everything: Are tasks marked [x] actually done? Are ACs really implemented?</critical>
-  <critical>Find 3-10 specific issues in every review minimum - no lazy "looks good" reviews - YOU are so much better than the dev agent
-    that wrote this slop</critical>
+  <critical>Find 3-10 specific issues in every review minimum - no lazy "looks good" reviews</critical>
   <critical>Read EVERY file in the File List - verify implementation against story requirements</critical>
   <critical>Tasks marked complete but not done = CRITICAL finding</critical>
   <critical>Acceptance Criteria not implemented = HIGH severity finding</critical>
 
-  <step n="1" goal="Load story and discover changes">
+  <step n="1" goal="Load story and detect external agents">
     <action>Use provided {{story_path}} or ask user which story file to review</action>
     <action>Read COMPLETE story file</action>
     <action>Set {{story_key}} = extracted key from filename (e.g., "1-2-user-authentication.md" → "1-2-user-authentication") or story metadata</action>
@@ -38,6 +78,86 @@
 
     <invoke-protocol name="discover_inputs" />
     <action>Load {project_context} for coding standards (if exists)</action>
+
+    <!-- ============================================================== -->
+    <!-- EXTERNAL AGENT DETECTION - CHECK CONFIG FIRST, THEN DETECT     -->
+    <!-- ============================================================== -->
+    <set-var name="use_external_agent" value="false" />
+    <set-var name="external_agent_cmd" value="" />
+    <set-var name="codex_available" value="false" />
+    <set-var name="gemini_available" value="false" />
+    <set-var name="claude_available" value="false" />
+    <set-var name="external_agent_failed" value="false" />
+    <set-var name="preferred_agent" value="{external_review_agent}" />
+
+    <!-- Check if user has disabled external agents -->
+    <check if="{{preferred_agent}} == 'none'">
+      <output>📋 External agent disabled in config - will use built-in adversarial review</output>
+    </check>
+
+    <!-- Only detect and use external agents if not set to "none" -->
+    <check if="{{preferred_agent}} != 'none'">
+      <output>🔍 Detecting external agent availability...</output>
+
+      <!-- Detect Codex CLI availability -->
+      <invoke-bash cmd="command -v codex &amp;&amp; codex --version 2>/dev/null || echo 'NOT_FOUND'" />
+      <check if="{{bash_exit_code}} == 0 AND {{bash_stdout}} does not contain 'NOT_FOUND'">
+        <set-var name="codex_available" value="true" />
+        <output>✓ Codex CLI detected</output>
+      </check>
+
+      <!-- Detect Gemini CLI availability -->
+      <invoke-bash cmd="command -v gemini &amp;&amp; gemini --version 2>/dev/null || echo 'NOT_FOUND'" />
+      <check if="{{bash_exit_code}} == 0 AND {{bash_stdout}} does not contain 'NOT_FOUND'">
+        <set-var name="gemini_available" value="true" />
+        <output>✓ Gemini CLI detected</output>
+      </check>
+
+      <!-- Detect Claude CLI availability -->
+      <invoke-bash cmd="command -v claude &amp;&amp; claude --version 2>/dev/null || echo 'NOT_FOUND'" />
+      <check if="{{bash_exit_code}} == 0 AND {{bash_stdout}} does not contain 'NOT_FOUND'">
+        <set-var name="claude_available" value="true" />
+        <output>✓ Claude CLI detected</output>
+      </check>
+
+      <!-- Select which external agent to use based on availability and preference -->
+      <check if="{{preferred_agent}} == 'codex' AND {{codex_available}} == true">
+        <set-var name="use_external_agent" value="true" />
+        <set-var name="external_agent_cmd" value="codex" />
+      </check>
+      <check if="{{preferred_agent}} == 'gemini' AND {{gemini_available}} == true">
+        <set-var name="use_external_agent" value="true" />
+        <set-var name="external_agent_cmd" value="gemini" />
+      </check>
+      <check if="{{preferred_agent}} == 'claude' AND {{claude_available}} == true">
+        <set-var name="use_external_agent" value="true" />
+        <set-var name="external_agent_cmd" value="claude" />
+      </check>
+
+      <!-- Fallback selection if preferred agent not available -->
+      <check if="{{use_external_agent}} == false AND {{codex_available}} == true">
+        <set-var name="use_external_agent" value="true" />
+        <set-var name="external_agent_cmd" value="codex" />
+        <output>⚠️ Preferred agent ({{preferred_agent}}) not available, falling back to Codex</output>
+      </check>
+      <check if="{{use_external_agent}} == false AND {{gemini_available}} == true">
+        <set-var name="use_external_agent" value="true" />
+        <set-var name="external_agent_cmd" value="gemini" />
+        <output>⚠️ Preferred agent ({{preferred_agent}}) not available, falling back to Gemini</output>
+      </check>
+      <check if="{{use_external_agent}} == false AND {{claude_available}} == true">
+        <set-var name="use_external_agent" value="true" />
+        <set-var name="external_agent_cmd" value="claude" />
+        <output>⚠️ Preferred agent ({{preferred_agent}}) not available, falling back to Claude</output>
+      </check>
+
+      <check if="{{use_external_agent}} == true">
+        <output>🤖 External agent selected: {{external_agent_cmd}} - will delegate code review</output>
+      </check>
+      <check if="{{use_external_agent}} == false">
+        <output>📋 No external agent available - will use built-in adversarial review</output>
+      </check>
+    </check>
   </step>
 
   <step n="2" goal="Build review attack plan">
@@ -56,41 +176,105 @@
   <step n="3" goal="Execute adversarial review">
     <critical>VALIDATE EVERY CLAIM - Check git reality vs story claims</critical>
 
-    <!-- Git vs Story Discrepancies -->
+    <!-- Git vs Story Discrepancies - ALWAYS runs -->
     <action>Review git vs story File List discrepancies:
       1. **Files changed but not in story File List** → MEDIUM finding (incomplete documentation)
       2. **Story lists files but no git changes** → HIGH finding (false claims)
       3. **Uncommitted changes not documented** → MEDIUM finding (transparency issue)
     </action>
-
-    <!-- Use combined file list: story File List + git discovered files -->
     <action>Create comprehensive review file list from story File List and git changes</action>
+    <action>Store git discrepancy findings in {{git_findings}}</action>
 
-    <!-- AC Validation -->
-    <action>For EACH Acceptance Criterion:
-      1. Read the AC requirement
-      2. Search implementation files for evidence
-      3. Determine: IMPLEMENTED, PARTIAL, or MISSING
-      4. If MISSING/PARTIAL → HIGH SEVERITY finding
-    </action>
+    <!-- ============================================================== -->
+    <!-- MANDATORY: INVOKE EXTERNAL AGENT IF AVAILABLE                  -->
+    <!-- ============================================================== -->
+    <critical>If {{use_external_agent}} == true, you MUST invoke the external agent via CLI.</critical>
+    <critical>DO NOT perform your own code review - delegate to the external agent.</critical>
 
-    <!-- Task Completion Audit -->
-    <action>For EACH task marked [x]:
-      1. Read the task description
-      2. Search files for evidence it was actually done
-      3. **CRITICAL**: If marked [x] but NOT DONE → CRITICAL finding
-      4. Record specific proof (file:line)
-    </action>
+    <check if="{{use_external_agent}} == true">
+      <output>🔄 Invoking {{external_agent_cmd}} CLI for adversarial code review...</output>
 
-    <!-- Code Quality Deep Dive -->
-    <action>For EACH file in comprehensive review list:
-      1. **Security**: Look for injection risks, missing validation, auth issues
-      2. **Performance**: N+1 queries, inefficient loops, missing caching
-      3. **Error Handling**: Missing try/catch, poor error messages
-      4. **Code Quality**: Complex functions, magic numbers, poor naming
-      5. **Test Quality**: Are tests real assertions or placeholders?
-    </action>
+      <!-- ============================================================== -->
+      <!-- INVOKE EXTERNAL AGENT - USE EXACT COMMANDS AS WRITTEN          -->
+      <!-- ============================================================== -->
+      <critical>🚨 USE EXACT COMMAND SYNTAX - DO NOT MODIFY OR SIMPLIFY 🚨</critical>
+      <critical>Copy the invoke-bash cmd attribute EXACTLY as written below.</critical>
+      <critical>DO NOT remove flags, reorder arguments, or "improve" the command.</critical>
 
+      <!-- External agent prompt is loaded from external-agent-prompt.md -->
+      <set-var name="external_prompt_file" value="{installed_path}/external-agent-prompt.md" />
+      <action>Load {{external_prompt_file}} content into {{external_prompt}}</action>
+
+      <check if="{{external_agent_cmd}} == 'codex'">
+        <critical>CODEX: Use codex exec with read-only sandbox and full-auto</critical>
+        <invoke-bash cmd="codex exec --sandbox read-only --full-auto &quot;$(cat '{{external_prompt_file}}')&quot;" timeout="300000" />
+      </check>
+      <check if="{{external_agent_cmd}} == 'gemini'">
+        <critical>GEMINI: Use gemini -p with prompt from file and --yolo</critical>
+        <invoke-bash cmd="gemini -p &quot;$(cat '{{external_prompt_file}}')&quot; --yolo" timeout="300000" />
+      </check>
+      <check if="{{external_agent_cmd}} == 'claude'">
+        <critical>CLAUDE: Use claude -p with prompt from file</critical>
+        <invoke-bash cmd="claude -p &quot;$(cat '{{external_prompt_file}}')&quot; --dangerously-skip-permissions" timeout="300000" />
+      </check>
+
+      <check if="{{bash_exit_code}} != 0 OR {{bash_stdout}} is empty">
+        <output>⚠️ External agent CLI failed (exit code: {{bash_exit_code}}), falling back to built-in review</output>
+        <output>Error: {{bash_stderr}}</output>
+        <set-var name="use_external_agent" value="false" />
+        <set-var name="external_agent_failed" value="true" />
+      </check>
+
+      <check if="{{bash_exit_code}} == 0 AND {{bash_stdout}} is not empty">
+        <set-var name="external_findings" value="{{bash_stdout}}" />
+        <action>Parse {{external_findings}} into structured HIGH/MEDIUM/LOW lists</action>
+        <action>Merge {{git_findings}} with {{external_findings}} into {{all_findings}}</action>
+        <output>✅ External review complete - {{external_agent_cmd}} CLI findings received</output>
+      </check>
+    </check>
+
+    <!-- Fallback to built-in if external agent failed -->
+    <check if="{{external_agent_failed}} == true">
+      <set-var name="use_external_agent" value="false" />
+    </check>
+
+    <check if="{{use_external_agent}} == false">
+      <!-- ============================================================== -->
+      <!-- FALLBACK ONLY: Built-in Review (when NO external agent works)  -->
+      <!-- ============================================================== -->
+      <critical>This section should ONLY execute if ALL external agents failed detection or invocation.</critical>
+      <critical>If you are here but an external agent was available, you have violated the workflow rules.</critical>
+      <output>⚠️ No external agent available - performing built-in adversarial review</output>
+
+      <!-- AC Validation -->
+      <action>For EACH Acceptance Criterion:
+        1. Read the AC requirement
+        2. Search implementation files for evidence
+        3. Determine: IMPLEMENTED, PARTIAL, or MISSING
+        4. If MISSING/PARTIAL → HIGH SEVERITY finding
+      </action>
+
+      <!-- Task Completion Audit -->
+      <action>For EACH task marked [x]:
+        1. Read the task description
+        2. Search files for evidence it was actually done
+        3. **CRITICAL**: If marked [x] but NOT DONE → CRITICAL finding
+        4. Record specific proof (file:line)
+      </action>
+
+      <!-- Code Quality Deep Dive -->
+      <action>For EACH file in comprehensive review list:
+        1. **Security**: Look for injection risks, missing validation, auth issues
+        2. **Performance**: N+1 queries, inefficient loops, missing caching
+        3. **Error Handling**: Missing try/catch, poor error messages
+        4. **Code Quality**: Complex functions, magic numbers, poor naming
+        5. **Test Quality**: Are tests real assertions or placeholders?
+      </action>
+
+      <action>Merge {{git_findings}} with built-in findings into {{all_findings}}</action>
+    </check>
+
+    <!-- Minimum issue check - applies to both paths -->
     <check if="total_issues_found lt 3">
       <critical>NOT LOOKING HARD ENOUGH - Find more problems!</critical>
       <action>Re-examine code for:
@@ -113,6 +297,7 @@
     <output>**🔥 CODE REVIEW FINDINGS, {user_name}!**
 
       **Story:** {{story_file}}
+      **Review Method:** {{external_agent_cmd}} OR built-in
       **Git vs Story Discrepancies:** {{git_discrepancy_count}} found
       **Issues Found:** {{high_count}} High, {{medium_count}} Medium, {{low_count}} Low
 
@@ -185,7 +370,7 @@
       <action>Set {{current_sprint_status}} = "no-sprint-tracking"</action>
     </check>
 
-    <!-- Sync sprint-status.yaml when story status changes (only if sprint tracking enabled) -->
+    <!-- Sync sprint-status.yaml when story status changes -->
     <check if="{{current_sprint_status}} != 'no-sprint-tracking'">
       <action>Load the FULL file: {sprint_status}</action>
       <action>Find development_status key matching {{story_key}}</action>
@@ -217,7 +402,7 @@
       **Issues Fixed:** {{fixed_count}}
       **Action Items Created:** {{action_count}}
 
-      {{#if new_status == "done"}}Story is ready for next work!{{else}}Address the action items and continue development.{{/if}}
+      {{#if new_status == "done"}}Code review complete!{{else}}Address the action items and continue development.{{/if}}
     </output>
   </step>
 

src/modules/bmm/workflows/4-implementation/code-review/workflow.yaml

@@ -18,6 +18,7 @@ sprint_status: "{sprint_artifacts}/sprint-status.yaml || {output_folder}/sprint-
 installed_path: "{project-root}/.bmad/bmm/workflows/4-implementation/code-review"
 instructions: "{installed_path}/instructions.xml"
 validation: "{installed_path}/checklist.md"
+external_agent_prompt: "{installed_path}/external-agent-prompt.md"
 template: false
 
 variables:
@@ -25,6 +26,11 @@ variables:
   project_context: "**/project-context.md"
   story_dir: "{sprint_artifacts}"
 
+  # External code review agent configuration
+  # User selects preferred agent during install; detection verifies availability at runtime
+  # Supported values: codex, gemini, claude, none
+  external_review_agent: "{config_source}:external_review_agent || 'none'"
+
 # Smart input file references - handles both whole docs and sharded docs
 # Priority: Whole document first, then sharded version
 # Strategy: SELECTIVE LOAD - only load the specific epic needed for this story review
@@ -51,4 +57,3 @@ input_file_patterns:
     load_strategy: "INDEX_GUIDED"
 
 standalone: true
-web_bundle: false

src/modules/bmm/workflows/4-implementation/dev-story/checklist.md

@@ -35,7 +35,7 @@ validation-rules:
 - [ ] **Acceptance Criteria Satisfaction:** Implementation satisfies EVERY Acceptance Criterion in the story
 - [ ] **No Ambiguous Implementation:** Clear, unambiguous implementation that meets story requirements
 - [ ] **Edge Cases Handled:** Error conditions and edge cases appropriately addressed
-- [ ] **Dependencies Within Scope:** Only uses dependencies specified in story or project_context.md
+- [ ] **Dependencies Within Scope:** Only uses dependencies specified in story or project-context.md
 
 ## 🧪 Testing & Quality Assurance
 

src/modules/bmm/workflows/generate-project-context/steps/step-01-discover.md

@@ -33,7 +33,7 @@ Discover the project's technology stack, existing patterns, and critical impleme
 
 First, check if project context already exists:
 
-- Look for file at `{output_folder}/project_context.md`
+- Look for file at `{output_folder}/project-context.md`
 - If exists: Read complete file to understand existing rules
 - Present to user: "Found existing project context with {number_of_sections} sections. Would you like to update this or create a new one?"
 
@@ -122,7 +122,7 @@ Based on discovery, create or update the context document:
 
 #### A. Fresh Document Setup (if no existing context)
 
-Copy template from `{installed_path}/project-context-template.md` to `{output_folder}/project_context.md`
+Copy template from `{installed_path}/project-context-template.md` to `{output_folder}/project-context.md`
 Initialize frontmatter with:
 
 ```yaml

src/modules/bmm/workflows/generate-project-context/steps/step-02-generate.md

@@ -288,7 +288,7 @@ After each category, show the generated rules and present choices:
 
 ## APPEND TO PROJECT CONTEXT:
 
-When user selects 'C' for a category, append the content directly to `{output_folder}/project_context.md` using the structure from step 8.
+When user selects 'C' for a category, append the content directly to `{output_folder}/project-context.md` using the structure from step 8.
 
 ## SUCCESS METRICS:
 

src/modules/bmm/workflows/generate-project-context/steps/step-03-complete.md

@@ -134,7 +134,7 @@ Based on user skill level, present the completion:
 **Expert Mode:**
 "Project context complete. Optimized for LLM consumption with {{rule_count}} critical rules across {{section_count}} sections.
 
-File saved to: `{output_folder}/project_context.md`
+File saved to: `{output_folder}/project-context.md`
 
 Ready for AI agent integration."
 
@@ -227,7 +227,7 @@ Present final completion to user:
 "✅ **Project Context Generation Complete!**
 
 Your optimized project context file is ready at:
-`{output_folder}/project_context.md`
+`{output_folder}/project-context.md`
 
 **📊 Context Summary:**
 

src/modules/bmm/workflows/generate-project-context/workflow.md

@@ -1,11 +1,11 @@
 ---
 name: generate-project-context
-description: Creates a concise project_context.md file with critical rules and patterns that AI agents must follow when implementing code. Optimized for LLM context efficiency.
+description: Creates a concise project-context.md file with critical rules and patterns that AI agents must follow when implementing code. Optimized for LLM context efficiency.
 ---
 
 # Generate Project Context Workflow
 
-**Goal:** Create a concise, optimized `project_context.md` file containing critical rules, patterns, and guidelines that AI agents must follow when implementing code. This file focuses on unobvious details that LLMs need to be reminded of.
+**Goal:** Create a concise, optimized `project-context.md` file containing critical rules, patterns, and guidelines that AI agents must follow when implementing code. This file focuses on unobvious details that LLMs need to be reminded of.
 
 **Your Role:** You are a technical facilitator working with a peer to capture the essential implementation rules that will ensure consistent, high-quality code generation across all AI agents working on the project.
 
@@ -37,7 +37,7 @@ Load config from `{project-root}/.bmad/bmm/config.yaml` and resolve:
 
 - `installed_path` = `{project-root}/.bmad/bmm/workflows/generate-project-context`
 - `template_path` = `{installed_path}/project-context-template.md`
-- `output_file` = `{output_folder}/project_context.md`
+- `output_file` = `{output_folder}/project-context.md`
 
 ---
 

src/modules/bmm/workflows/testarch/test-design/workflow.yaml

@@ -24,8 +24,14 @@ variables:
 
 # Output configuration
 # Note: Actual output file determined dynamically based on mode detection
-# - System-Level (Phase 3): {output_folder}/test-design-system.md
-# - Epic-Level (Phase 4): {output_folder}/test-design-epic-{epic_num}.md
+# Declared outputs for new workflow format
+outputs:
+  - id: system-level
+    description: "System-level testability review (Phase 3)"
+    path: "{output_folder}/test-design-system.md"
+  - id: epic-level
+    description: "Epic-level test plan (Phase 4)"
+    path: "{output_folder}/test-design-epic-{epic_num}.md"
 default_output_file: "{output_folder}/test-design-epic-{epic_num}.md"
 
 # Required tools

tools/cli/installers/lib/core/config-collector.js

@@ -248,14 +248,21 @@ class ConfigCollector {
     const configKeys = Object.keys(moduleConfig).filter((key) => key !== 'prompt');
     const existingKeys = this.existingConfig && this.existingConfig[moduleName] ? Object.keys(this.existingConfig[moduleName]) : [];
 
+    // Find new interactive fields (with prompt)
     const newKeys = configKeys.filter((key) => {
       const item = moduleConfig[key];
       // Check if it's a config item and doesn't exist in existing config
       return item && typeof item === 'object' && item.prompt && !existingKeys.includes(key);
     });
 
-    // If in silent mode and no new keys, use existing config and skip prompts
-    if (silentMode && newKeys.length === 0) {
+    // Find new static fields (without prompt, just result)
+    const newStaticKeys = configKeys.filter((key) => {
+      const item = moduleConfig[key];
+      return item && typeof item === 'object' && !item.prompt && item.result && !existingKeys.includes(key);
+    });
+
+    // If in silent mode and no new keys (neither interactive nor static), use existing config and skip prompts
+    if (silentMode && newKeys.length === 0 && newStaticKeys.length === 0) {
       if (this.existingConfig && this.existingConfig[moduleName]) {
         if (!this.collectedConfig[moduleName]) {
           this.collectedConfig[moduleName] = {};
@@ -294,9 +301,12 @@ class ConfigCollector {
       return false; // No new fields
     }
 
-    // If we have new fields, build questions first
-    if (newKeys.length > 0) {
+    // If we have new fields (interactive or static), process them
+    if (newKeys.length > 0 || newStaticKeys.length > 0) {
       const questions = [];
+      const staticAnswers = {};
+
+      // Build questions for interactive fields
       for (const key of newKeys) {
         const item = moduleConfig[key];
         const question = await this.buildQuestion(moduleName, key, item, moduleConfig);
@@ -305,39 +315,50 @@ class ConfigCollector {
         }
       }
 
+      // Prepare static answers (no prompt, just result)
+      for (const key of newStaticKeys) {
+        staticAnswers[`${moduleName}_${key}`] = undefined;
+      }
+
+      // Collect all answers (static + prompted)
+      let allAnswers = { ...staticAnswers };
+
       if (questions.length > 0) {
         // Only show header if we actually have questions
         CLIUtils.displayModuleConfigHeader(moduleName, moduleConfig.header, moduleConfig.subheader);
         console.log(); // Line break before questions
-        const answers = await inquirer.prompt(questions);
+        const promptedAnswers = await inquirer.prompt(questions);
 
-        // Store answers for cross-referencing
-        Object.assign(this.allAnswers, answers);
-
-        // Process answers and build result values
-        for (const key of Object.keys(answers)) {
-          const originalKey = key.replace(`${moduleName}_`, '');
-          const item = moduleConfig[originalKey];
-          const value = answers[key];
-
-          let result;
-          if (Array.isArray(value)) {
-            result = value;
-          } else if (item.result) {
-            result = this.processResultTemplate(item.result, value);
-          } else {
-            result = value;
-          }
-
-          if (!this.collectedConfig[moduleName]) {
-            this.collectedConfig[moduleName] = {};
-          }
-          this.collectedConfig[moduleName][originalKey] = result;
-        }
-      } else {
-        // New keys exist but no questions generated - show no config message
+        // Merge prompted answers with static answers
+        Object.assign(allAnswers, promptedAnswers);
+      } else if (newStaticKeys.length > 0) {
+        // Only static fields, no questions - show no config message
         CLIUtils.displayModuleNoConfig(moduleName, moduleConfig.header, moduleConfig.subheader);
       }
+
+      // Store all answers for cross-referencing
+      Object.assign(this.allAnswers, allAnswers);
+
+      // Process all answers (both static and prompted)
+      for (const key of Object.keys(allAnswers)) {
+        const originalKey = key.replace(`${moduleName}_`, '');
+        const item = moduleConfig[originalKey];
+        const value = allAnswers[key];
+
+        let result;
+        if (Array.isArray(value)) {
+          result = value;
+        } else if (item.result) {
+          result = this.processResultTemplate(item.result, value);
+        } else {
+          result = value;
+        }
+
+        if (!this.collectedConfig[moduleName]) {
+          this.collectedConfig[moduleName] = {};
+        }
+        this.collectedConfig[moduleName][originalKey] = result;
+      }
     }
 
     // Copy over existing values for fields that weren't prompted
@@ -353,7 +374,7 @@ class ConfigCollector {
       }
     }
 
-    return newKeys.length > 0; // Return true if we prompted for new fields
+    return newKeys.length > 0 || newStaticKeys.length > 0; // Return true if we had any new fields (interactive or static)
   }
 
   /**
@@ -501,30 +522,52 @@ class ConfigCollector {
 
     // Process each config item
     const questions = [];
+    const staticAnswers = {};
     const configKeys = Object.keys(moduleConfig).filter((key) => key !== 'prompt');
 
     for (const key of configKeys) {
       const item = moduleConfig[key];
 
       // Skip if not a config object
-      if (!item || typeof item !== 'object' || !item.prompt) {
+      if (!item || typeof item !== 'object') {
         continue;
       }
 
-      const question = await this.buildQuestion(moduleName, key, item, moduleConfig);
-      if (question) {
-        questions.push(question);
+      // Handle static values (no prompt, just result)
+      if (!item.prompt && item.result) {
+        // Add to static answers with a marker value
+        staticAnswers[`${moduleName}_${key}`] = undefined;
+        continue;
+      }
+
+      // Handle interactive values (with prompt)
+      if (item.prompt) {
+        const question = await this.buildQuestion(moduleName, key, item, moduleConfig);
+        if (question) {
+          questions.push(question);
+        }
       }
     }
 
+    // Collect all answers (static + prompted)
+    let allAnswers = { ...staticAnswers };
+
     // Display appropriate header based on whether there are questions
     if (questions.length > 0) {
       CLIUtils.displayModuleConfigHeader(moduleName, moduleConfig.header, moduleConfig.subheader);
       console.log(); // Line break before questions
-      const answers = await inquirer.prompt(questions);
+      const promptedAnswers = await inquirer.prompt(questions);
 
-      // Store answers for cross-referencing
-      Object.assign(this.allAnswers, answers);
+      // Merge prompted answers with static answers
+      Object.assign(allAnswers, promptedAnswers);
+    }
+
+    // Store all answers for cross-referencing
+    Object.assign(this.allAnswers, allAnswers);
+
+    // Process all answers (both static and prompted)
+    if (Object.keys(allAnswers).length > 0) {
+      const answers = allAnswers;
 
       // Process answers and build result values
       for (const key of Object.keys(answers)) {

tools/cli/installers/lib/core/manifest-generator.js

@@ -581,6 +581,11 @@ class ManifestGenerator {
    */
   async writeWorkflowManifest(cfgDir) {
     const csvPath = path.join(cfgDir, 'workflow-manifest.csv');
+    const escapeCsv = (value) => `"${String(value ?? '').replaceAll('"', '""')}"`;
+    const parseCsvLine = (line) => {
+      const columns = line.match(/(".*?"|[^",\s]+)(?=\s*,|\s*$)/g) || [];
+      return columns.map((c) => c.replaceAll(/^"|"$/g, ''));
+    };
 
     // Read existing manifest to preserve entries
     const existingEntries = new Map();
@@ -592,18 +597,21 @@ class ManifestGenerator {
       for (let i = 1; i < lines.length; i++) {
         const line = lines[i];
         if (line) {
-          // Parse CSV (simple parsing assuming no commas in quoted fields)
-          const parts = line.split('","');
+          const parts = parseCsvLine(line);
           if (parts.length >= 4) {
-            const name = parts[0].replace(/^"/, '');
-            const module = parts[2];
-            existingEntries.set(`${module}:${name}`, line);
+            const [name, description, module, workflowPath] = parts;
+            existingEntries.set(`${module}:${name}`, {
+              name,
+              description,
+              module,
+              path: workflowPath,
+            });
           }
         }
       }
     }
 
-    // Create CSV header - removed standalone column as ALL workflows now generate commands
+    // Create CSV header - standalone column removed, everything is canonicalized to 4 columns
     let csv = 'name,description,module,path\n';
 
     // Combine existing and new workflows
@@ -617,12 +625,18 @@ class ManifestGenerator {
     // Add/update new workflows
     for (const workflow of this.workflows) {
       const key = `${workflow.module}:${workflow.name}`;
-      allWorkflows.set(key, `"${workflow.name}","${workflow.description}","${workflow.module}","${workflow.path}"`);
+      allWorkflows.set(key, {
+        name: workflow.name,
+        description: workflow.description,
+        module: workflow.module,
+        path: workflow.path,
+      });
     }
 
     // Write all workflows
     for (const [, value] of allWorkflows) {
-      csv += value + '\n';
+      const row = [escapeCsv(value.name), escapeCsv(value.description), escapeCsv(value.module), escapeCsv(value.path)].join(',');
+      csv += row + '\n';
     }
 
     await fs.writeFile(csvPath, csv);