bmad-method 6.0.0-alpha.7 → 6.0.0-alpha.9

package/src/modules/bmgd/workflows/4-production/create-story/instructions.md

@@ -1,51 +1,27 @@
 # Create Story - Workflow Instructions (Spec-compliant, non-interactive by default)
 
 ````xml
-<critical>The workflow execution engine is governed by: {project_root}/bmad/core/tasks/workflow.xml</critical>
+<critical>The workflow execution engine is governed by: {project_root}/{bmad_folder}/core/tasks/workflow.xml</critical>
 <critical>You MUST have already loaded and processed: {installed_path}/workflow.yaml</critical>
 <critical>Generate all documents in {document_output_language}</critical>
 <critical>This workflow creates or updates the next user story from epics/PRD and architecture context, saving to the configured stories directory and optionally invoking Story Context.</critical>
 <critical>DOCUMENT OUTPUT: Concise, technical, actionable story specifications. Use tables/lists for acceptance criteria and tasks.</critical>
 
-## 📚 Document Discovery - Selective Epic Loading
-
-**Strategy**: This workflow needs only ONE specific epic and its stories, not all epics. This provides huge efficiency gains when epics are sharded.
-
-**Epic Discovery Process (SELECTIVE OPTIMIZATION):**
-
-1. **Determine which epic** you need (epic_num from story context - e.g., story "3-2-feature-name" needs Epic 3)
-2. **Check for sharded version**: Look for `epics/index.md`
-3. **If sharded version found**:
-   - Read `index.md` to understand structure
-   - **Load ONLY `epic-{epic_num}.md`** (e.g., `epics/epic-3.md` for Epic 3)
-   - DO NOT load all epic files - only the one needed!
-   - This is the key efficiency optimization for large multi-epic projects
-4. **If whole document found**: Load the complete `epics.md` file and extract the relevant epic
-
-**Other Documents (prd, architecture, ux-design) - Full Load:**
-
-1. **Search for whole document first** - Use fuzzy file matching
-2. **Check for sharded version** - If whole document not found, look for `{doc-name}/index.md`
-3. **If sharded version found**:
-   - Read `index.md` to understand structure
-   - Read ALL section files listed in the index
-   - Treat combined content as single document
-4. **Brownfield projects**: The `document-project` workflow creates `{output_folder}/docs/index.md`
-
-**Priority**: If both whole and sharded versions exist, use the whole document.
-
-**UX-Heavy Projects**: Always check for ux-design documentation as it provides critical context for UI-focused stories.
-
 <workflow>
 
   <step n="1" goal="Load config and initialize">
-    <action>Resolve variables from config_source: story_dir (dev_story_location), output_folder, user_name, communication_language. If story_dir missing and {{non_interactive}} == false → ASK user to provide a stories directory and update variable. If {{non_interactive}} == true and missing, HALT with a clear message.</action>
+    <action>Resolve variables from config_source: story_dir (sprint_artifacts), output_folder, user_name, communication_language. If story_dir missing → ASK user to provide a stories directory and update variable.</action>
     <action>Create {{story_dir}} if it does not exist</action>
     <action>Resolve installed component paths from workflow.yaml: template, instructions, validation</action>
-    <action>Resolve recommended inputs if present: epics_file, prd_file, architecture_file</action>
+    <action>Load architecture/standards docs: For each file name in {{arch_docs_file_names}} within {{arch_docs_search_dirs}}, read if exists. Collect testing, coding standards, security, and architectural patterns.</action>
   </step>
 
-  <step n="2" goal="Discover and load source documents">
+  <step n="1.5" goal="Discover and load project documents">
+    <invoke-protocol name="discover_inputs" />
+    <note>After discovery, these content variables are available: {prd_content}, {tech_spec_content}, {architecture_content}, {ux_design_content}, {epics_content}, {document_project_content}</note>
+  </step>
+
+  <step n="2" goal="Discover previous story context">
     <critical>PREVIOUS STORY CONTINUITY: Essential for maintaining context and learning from prior development</critical>
 
     <action>Find the previous completed story to extract dev agent learnings and review findings:
@@ -115,19 +91,17 @@
     </action>
 
     <action>If {{tech_spec_file}} empty: derive from {{tech_spec_glob_template}} with {{epic_num}} and search {{tech_spec_search_dir}} recursively. If multiple, pick most recent by modified time.</action>
-    <action>Build a prioritized document set for this epic:
+    <action>Build a prioritized document set for this epic - search and load from {input_file_patterns} list of potential locations:
       1) tech_spec_file (epic-scoped)
-      2) epics_file (acceptance criteria and breakdown)
-      3) prd_file (business requirements and constraints)
-      4) architecture_file (architecture constraints)
-      5) Architecture docs under docs/ and output_folder/: tech-stack.md, unified-project-structure.md, coding-standards.md, testing-strategy.md, backend-architecture.md, frontend-architecture.md, data-models.md, database-schema.md, rest-api-spec.md, external-apis.md (include if present)
+      2) epics_file (acceptance criteria and breakdown) the specific epic the story will be part of
+      3) prd_file (business requirements and constraints) whole or sharded
+      4) architecture_file (architecture constraints) whole or sharded
     </action>
     <action>READ COMPLETE FILES for all items found in the prioritized set. Store content and paths for citation.</action>
   </step>
 
   <step n="3" goal="Find next backlog story to draft" tag="sprint-status">
-    <critical>MUST read COMPLETE sprint-status.yaml file from start to end to preserve order</critical>
-    <action>Load the FULL file: {{output_folder}}/sprint-status.yaml</action>
+    <critical>MUST read COMPLETE {sprint_status} file from start to end to preserve order</critical>
     <action>Read ALL lines from beginning to end - do not skip any content</action>
     <action>Parse the development_status section completely to understand story order</action>
 
@@ -140,12 +114,12 @@
     <check if="no backlog story found">
       <output>📋 No backlog stories found in sprint-status.yaml
 
-All stories are either already drafted or completed.
+        All stories are either already drafted or completed.
 
-**Options:**
-1. Run sprint-planning to refresh story tracking
-2. Load PM agent and run correct-course to add more stories
-3. Check if current sprint is complete
+        **Options:**
+        1. Run sprint-planning to refresh story tracking
+        2. Load PM agent and run correct-course to add more stories
+        3. Check if current sprint is complete
       </output>
       <action>HALT</action>
     </check>
@@ -164,7 +138,6 @@ All stories are either already drafted or completed.
     <action>Check if story file already exists at expected path in {{story_dir}}</action>
     <check if="story file exists">
       <output>ℹ️ Story file already exists: {{story_file_path}}
-
 Will update existing story file rather than creating new one.
       </output>
       <action>Set update_mode = true</action>
@@ -240,7 +213,7 @@ Will update existing story file rather than creating new one.
   </step>
 
   <step n="8" goal="Validate, save, and mark story drafted" tag="sprint-status">
-    <invoke-task>Validate against checklist at {installed_path}/checklist.md using bmad/core/tasks/validate-workflow.xml</invoke-task>
+    <invoke-task>Validate against checklist at {installed_path}/checklist.md using {bmad_folder}/core/tasks/validate-workflow.xml</invoke-task>
     <action>Save document unconditionally (non-interactive default). In interactive mode, allow user confirmation.</action>
 
     <!-- Mark story as drafted in sprint status -->

package/src/modules/bmgd/workflows/4-production/create-story/workflow.yaml

@@ -3,21 +3,23 @@ description: "Create the next user story markdown from epics/PRD and architectur
 author: "BMad"
 
 # Critical variables from config
-config_source: "{project-root}/bmad/bmgd/config.yaml"
+config_source: "{project-root}/{bmad_folder}/bmgd/config.yaml"
 output_folder: "{config_source}:output_folder"
 user_name: "{config_source}:user_name"
 communication_language: "{config_source}:communication_language"
 date: system-generated
+sprint_artifacts: "{config_source}:sprint_artifacts"
+story_dir: "{sprint_artifacts}"
 
 # Workflow components
-installed_path: "{project-root}/bmad/bmm/workflows/4-implementation/create-story"
+installed_path: "{project-root}/{bmad_folder}/bmm/workflows/4-implementation/create-story"
 template: "{installed_path}/template.md"
 instructions: "{installed_path}/instructions.md"
 validation: "{installed_path}/checklist.md"
 
 # Variables and inputs
 variables:
-  story_dir: "{config_source}:dev_story_location" # Directory where stories are stored
+  sprint_status: "{sprint_artifacts}/sprint-status.yaml || {output_folder}/sprint-status.yaml" # Primary source for story tracking
   epics_file: "{output_folder}/epics.md" # Preferred source for epic/story breakdown
   prd_file: "{output_folder}/PRD.md" # Fallback for requirements
   architecture_file: "{output_folder}/architecture.md" # Optional architecture context
@@ -28,48 +30,38 @@ variables:
     - "{project-root}/docs"
     - "{output_folder}"
   arch_docs_file_names: |
-    - architecture.md
-    - infrastructure-architecture.md
+    - *architecture*.md
   story_title: "" # Will be elicited if not derivable
-  epic_num: 1
-  story_num: 1
-  non_interactive: true # Generate without elicitation; avoid interactive prompts
 
-# Output configuration
-# Uses story_key from sprint-status.yaml (e.g., "1-2-user-authentication")
 default_output_file: "{story_dir}/{{story_key}}.md"
 
-recommended_inputs:
-  - epics: "Epic breakdown (epics.md)"
-  - prd: "PRD document"
-  - architecture: "Architecture (optional)"
-
 # 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
 input_file_patterns:
   prd:
     whole: "{output_folder}/*prd*.md"
-    sharded: "{output_folder}/*prd*/index.md"
-
+    sharded: "{output_folder}/*prd*/*.md"
+    load_strategy: "FULL_LOAD"
   tech_spec:
     whole: "{output_folder}/tech-spec.md"
-
+    load_strategy: "FULL_LOAD"
   architecture:
     whole: "{output_folder}/*architecture*.md"
-    sharded: "{output_folder}/*architecture*/index.md"
-
+    sharded: "{output_folder}/*architecture*/*.md"
+    load_strategy: "FULL_LOAD"
   ux_design:
     whole: "{output_folder}/*ux*.md"
-    sharded: "{output_folder}/*ux*/index.md"
-
+    sharded: "{output_folder}/*ux*/*.md"
+    load_strategy: "FULL_LOAD"
   epics:
     whole: "{output_folder}/*epic*.md"
     sharded_index: "{output_folder}/*epic*/index.md"
     sharded_single: "{output_folder}/*epic*/epic-{{epic_num}}.md"
-
+    load_strategy: "SELECTIVE_LOAD"
   document_project:
-    sharded: "{output_folder}/docs/index.md"
+    sharded: "{output_folder}/index.md"
+    load_strategy: "INDEX_GUIDED"
 
 standalone: true
 

package/src/modules/bmgd/workflows/4-production/dev-story/instructions.md

@@ -1,7 +1,7 @@
 # Develop Story - Workflow Instructions
 
 ```xml
-<critical>The workflow execution engine is governed by: {project-root}/bmad/core/tasks/workflow.xml</critical>
+<critical>The workflow execution engine is governed by: {project-root}/{bmad_folder}/core/tasks/workflow.xml</critical>
 <critical>You MUST have already loaded and processed: {installed_path}/workflow.yaml</critical>
 <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>
@@ -39,7 +39,7 @@
 1. Run `story-context` to generate context file and mark drafted stories as ready
 2. Run `story-ready` to quickly mark drafted stories as ready without generating context
 3. Run `create-story` if no incomplete stories are drafted yet
-4. Check {output-folder}/sprint-status.yaml to see current sprint status
+4. Check {output_folder}/sprint-status.yaml to see current sprint status
       </output>
       <action>HALT</action>
     </check>
@@ -72,6 +72,11 @@ Proceeding with story file only. For better context, consider running `story-con
     <action if="incomplete task or subtask requirements ambiguous">ASK user to clarify or HALT</action>
   </step>
 
+  <step n="0.5" goal="Discover and load project documents">
+    <invoke-protocol name="discover_inputs" />
+    <note>After discovery, these content variables are available: {architecture_content}, {tech_spec_content}, {ux_design_content}, {epics_content} (selective load), {document_project_content}</note>
+  </step>
+
   <step n="1.5" goal="Detect review continuation and extract review context">
     <critical>Determine if this is a fresh start or continuation after code review</critical>
 
@@ -227,7 +232,7 @@ Story is marked Ready for Review in file, but sprint-status.yaml may be out of s
   </step>
 
   <step n="7" goal="Completion communication and user support">
-    <action>Optionally run the workflow validation task against the story using {project-root}/bmad/core/tasks/validate-workflow.xml</action>
+    <action>Optionally run the workflow validation task against the story using {project-root}/{bmad_folder}/core/tasks/validate-workflow.xml</action>
     <action>Prepare a concise summary in Dev Agent Record → Completion Notes</action>
 
     <action>Communicate to {user_name} that story implementation is complete and ready for review</action>

package/src/modules/bmgd/workflows/4-production/dev-story/workflow.yaml

@@ -3,23 +3,48 @@ description: "Execute a story by implementing tasks/subtasks, writing tests, val
 author: "BMad"
 
 # Critical variables from config
-config_source: "{project-root}/bmad/bmgd/config.yaml"
+config_source: "{project-root}/{bmad_folder}/bmgd/config.yaml"
 output_folder: "{config_source}:output_folder"
 user_name: "{config_source}:user_name"
 communication_language: "{config_source}:communication_language"
 user_skill_level: "{config_source}:user_skill_level"
 document_output_language: "{config_source}:document_output_language"
-story_dir: "{config_source}:dev_story_location"
-run_until_complete: "{config_source}:run_until_complete"
-run_tests_command: "{config_source}:run_tests_command"
+story_dir: "{config_source}:sprint_artifacts"
 date: system-generated
 
 story_file: "" # Explicit story path; auto-discovered if empty
 # Context file uses same story_key as story file (e.g., "1-2-user-authentication.context.xml")
 context_file: "{story_dir}/{{story_key}}.context.xml"
+sprint_artifacts: "{config_source}:sprint_artifacts"
+sprint_status: "{sprint_artifacts}/sprint-status.yaml || {output_folder}/sprint-status.yaml"
+
+# Smart input file references - handles both whole docs and sharded docs
+# Priority: Whole document first, then sharded version
+# Strategy: Load necessary context for story implementation
+input_file_patterns:
+  architecture:
+    whole: "{output_folder}/*architecture*.md"
+    sharded: "{output_folder}/*architecture*/*.md"
+    load_strategy: "FULL_LOAD"
+  tech_spec:
+    whole: "{output_folder}/tech-spec*.md"
+    sharded: "{sprint_artifacts}/tech-spec-epic-*.md"
+    load_strategy: "SELECTIVE_LOAD"
+  ux_design:
+    whole: "{output_folder}/*ux*.md"
+    sharded: "{output_folder}/*ux*/*.md"
+    load_strategy: "FULL_LOAD"
+  epics:
+    whole: "{output_folder}/*epic*.md"
+    sharded_index: "{output_folder}/*epic*/index.md"
+    sharded_single: "{output_folder}/*epic*/epic-{{epic_num}}.md"
+    load_strategy: "SELECTIVE_LOAD"
+  document_project:
+    sharded: "{output_folder}/docs/index.md"
+    load_strategy: "INDEX_GUIDED"
 
 # Workflow components
-installed_path: "{project-root}/bmad/bmm/workflows/4-implementation/dev-story"
+installed_path: "{project-root}/{bmad_folder}/bmm/workflows/4-implementation/dev-story"
 instructions: "{installed_path}/instructions.md"
 validation: "{installed_path}/checklist.md"
 

package/src/modules/bmgd/workflows/4-production/epic-tech-context/checklist.md

@@ -1,7 +1,7 @@
 # Tech Spec Validation Checklist
 
 ```xml
-<checklist id="bmad/bmm/workflows/4-implementation/epic-tech-context/checklist">
+<checklist id="{bmad_folder}/bmm/workflows/4-implementation/epic-tech-context/checklist">
   <item>Overview clearly ties to PRD goals</item>
   <item>Scope explicitly lists in-scope and out-of-scope</item>
   <item>Design lists all services/modules with responsibilities</item>

package/src/modules/bmgd/workflows/4-production/epic-tech-context/instructions.md

@@ -1,49 +1,19 @@
 <!-- BMAD BMM Tech Spec Workflow Instructions (v6) -->
 
 ```xml
-<critical>The workflow execution engine is governed by: {project_root}/bmad/core/tasks/workflow.xml</critical>
+<critical>The workflow execution engine is governed by: {project_root}/{bmad_folder}/core/tasks/workflow.xml</critical>
 <critical>You MUST have already loaded and processed: {installed_path}/workflow.yaml</critical>
 <critical>Communicate all responses in {communication_language}</critical>
 <critical>This workflow generates a comprehensive Technical Specification from PRD and Architecture, including detailed design, NFRs, acceptance criteria, and traceability mapping.</critical>
 <critical>If required inputs cannot be auto-discovered HALT with a clear message listing missing documents, allow user to provide them to proceed.</critical>
 
-## 📚 Document Discovery - Selective Epic Loading
-
-**Strategy**: This workflow needs only ONE specific epic and its stories, not all epics. This provides huge efficiency gains when epics are sharded.
-
-**Epic Discovery Process (SELECTIVE OPTIMIZATION):**
-
-1. **Determine which epic** you need (epic_num from workflow context or user input)
-2. **Check for sharded version**: Look for `epics/index.md`
-3. **If sharded version found**:
-   - Read `index.md` to understand structure
-   - **Load ONLY `epic-{epic_num}.md`** (e.g., `epics/epic-3.md` for Epic 3)
-   - DO NOT load all epic files - only the one needed!
-   - This is the key efficiency optimization for large multi-epic projects
-4. **If whole document found**: Load the complete `epics.md` file and extract the relevant epic
-
-**Other Documents (prd, gdd, architecture, ux-design) - Full Load:**
-
-1. **Search for whole document first** - Use fuzzy file matching
-2. **Check for sharded version** - If whole document not found, look for `{doc-name}/index.md`
-3. **If sharded version found**:
-   - Read `index.md` to understand structure
-   - Read ALL section files listed in the index
-   - Treat combined content as single document
-4. **Brownfield projects**: The `document-project` workflow creates `{output_folder}/docs/index.md`
-
-**Priority**: If both whole and sharded versions exist, use the whole document.
-
-**UX-Heavy Projects**: Always check for ux-design documentation as it provides critical context for UI-focused epics and stories.
-
 <workflow>
   <step n="1" goal="Collect inputs and discover next epic" tag="sprint-status">
     <action>Identify PRD and Architecture documents from recommended_inputs. Attempt to auto-discover at default paths.</action>
     <ask if="inputs are missing">ask the user for file paths. HALT and wait for docs to proceed</ask>
 
     <!-- Intelligent Epic Discovery -->
-    <critical>MUST read COMPLETE sprint-status.yaml file to discover next epic</critical>
-    <action>Load the FULL file: {{output_folder}}/sprint-status.yaml</action>
+    <critical>MUST read COMPLETE {sprint-status} file to discover next epic</critical>
     <action>Read ALL development_status entries</action>
     <action>Find all epics with status "backlog" (not yet contexted)</action>
     <action>Identify the FIRST backlog epic as the suggested default</action>
@@ -81,10 +51,15 @@ No epics with status "backlog" found in sprint-status.yaml.
       </check>
     </check>
 
-    <action>Extract {{epic_title}} from PRD based on {{epic_id}}.</action>
     <action>Resolve output file path using workflow variables and initialize by writing the template.</action>
   </step>
 
+  <step n="1.5" goal="Discover and load project documents">
+    <invoke-protocol name="discover_inputs" />
+    <note>After discovery, these content variables are available: {prd_content}, {gdd_content}, {architecture_content}, {ux_design_content}, {epics_content} (will load only epic-{{epic_id}}.md if sharded), {document_project_content}</note>
+    <action>Extract {{epic_title}} from {prd_content} or {epics_content} based on {{epic_id}}.</action>
+  </step>
+
   <step n="2" goal="Validate epic exists in sprint status" tag="sprint-status">
     <action>Look for epic key "epic-{{epic_id}}" in development_status (already loaded from step 1)</action>
     <action>Get current status value if epic exists</action>
@@ -157,10 +132,10 @@ Continuing to regenerate tech spec...
   </step>
 
   <step n="9" goal="Validate and mark epic contexted" tag="sprint-status">
-    <invoke-task>Validate against checklist at {installed_path}/checklist.md using bmad/core/tasks/validate-workflow.xml</invoke-task>
+    <invoke-task>Validate against checklist at {installed_path}/checklist.md using {bmad_folder}/core/tasks/validate-workflow.xml</invoke-task>
 
     <!-- Mark epic as contexted -->
-    <action>Load the FULL file: {{output_folder}}/sprint-status.yaml</action>
+    <action>Load the FULL file: {sprint_status}</action>
     <action>Find development_status key "epic-{{epic_id}}"</action>
     <action>Verify current status is "backlog" (expected previous state)</action>
     <action>Update development_status["epic-{{epic_id}}"] = "contexted"</action>

package/src/modules/bmgd/workflows/4-production/epic-tech-context/workflow.yaml

@@ -3,20 +3,13 @@ description: "Generate a comprehensive Technical Specification from PRD and Arch
 author: "BMAD BMM"
 
 # Critical variables
-config_source: "{project-root}/bmad/bmgd/config.yaml"
+config_source: "{project-root}/{bmad_folder}/bmgd/config.yaml"
 output_folder: "{config_source}:output_folder"
 user_name: "{config_source}:user_name"
 communication_language: "{config_source}:communication_language"
 date: system-generated
-
-# Inputs expected (check output_folder or ask user if missing)
-recommended_inputs:
-  - prd
-  - gdd
-  - architecture
-  - ux_design
-  - epics (only the specific epic needed for this tech spec)
-  - prior epic tech-specs for model, style and consistency reference
+sprint_artifacts: "{config_source}:sprint_artifacts"
+sprint_status: "{sprint_artifacts}/sprint-status.yaml || {output_folder}/sprint-status.yaml"
 
 # Smart input file references - handles both whole docs and sharded docs
 # Priority: Whole document first, then sharded version
@@ -24,37 +17,36 @@ recommended_inputs:
 input_file_patterns:
   prd:
     whole: "{output_folder}/*prd*.md"
-    sharded: "{output_folder}/*prd*/index.md"
-
+    sharded: "{output_folder}/*prd*/*.md"
+    load_strategy: "FULL_LOAD"
   gdd:
     whole: "{output_folder}/*gdd*.md"
-    sharded: "{output_folder}/*gdd*/index.md"
-
+    sharded: "{output_folder}/*gdd*/*.md"
+    load_strategy: "FULL_LOAD"
   architecture:
     whole: "{output_folder}/*architecture*.md"
-    sharded: "{output_folder}/*architecture*/index.md"
-
+    sharded: "{output_folder}/*architecture*/*.md"
+    load_strategy: "FULL_LOAD"
   ux_design:
     whole: "{output_folder}/*ux*.md"
-    sharded: "{output_folder}/*ux*/index.md"
-
+    sharded: "{output_folder}/*ux*/*.md"
+    load_strategy: "FULL_LOAD"
   epics:
     whole: "{output_folder}/*epic*.md"
     sharded_index: "{output_folder}/*epic*/index.md"
     sharded_single: "{output_folder}/*epic*/epic-{{epic_num}}.md"
-
+    load_strategy: "SELECTIVE_LOAD"
   document_project:
-    sharded: "{output_folder}/docs/index.md"
+    sharded: "{output_folder}/index.md"
+    load_strategy: "INDEX_GUIDED"
 
 # Workflow components
-installed_path: "{project-root}/bmad/bmm/workflows/4-implementation/epic-tech-context"
+installed_path: "{project-root}/{bmad_folder}/bmm/workflows/4-implementation/epic-tech-context"
 template: "{installed_path}/template.md"
 instructions: "{installed_path}/instructions.md"
 validation: "{installed_path}/checklist.md"
 
 # Output configuration
-default_output_file: "{output_folder}/tech-spec-epic-{{epic_id}}.md"
-
+default_output_file: "{sprint_artifacts}/tech-spec-epic-{{epic_id}}.md"
 standalone: true
-
 web_bundle: false

package/src/modules/bmgd/workflows/4-production/retrospective/instructions.md

@@ -1,12 +1,12 @@
 # Retrospective - Epic Completion Review Instructions
 
-<critical>The workflow execution engine is governed by: {project-root}/bmad/core/tasks/workflow.xml</critical>
-<critical>You MUST have already loaded and processed: {project-root}/bmad/bmm/workflows/4-implementation/retrospective/workflow.yaml</critical>
+<critical>The workflow execution engine is governed by: {project-root}/{bmad_folder}/core/tasks/workflow.xml</critical>
+<critical>You MUST have already loaded and processed: {project-root}/{bmad_folder}/bmm/workflows/4-implementation/retrospective/workflow.yaml</critical>
 <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>
-DOCUMENT OUTPUT: Retrospective analysis. Concise insights, lessons learned, action items. User skill level ({user_skill_level}) affects conversation style ONLY, not retrospective content.
+  DOCUMENT OUTPUT: Retrospective analysis. Concise insights, lessons learned, action items. User skill level ({user_skill_level}) affects conversation style ONLY, not retrospective content.
 
 FACILITATION NOTES:
 
@@ -26,29 +26,6 @@ PARTY MODE PROTOCOL:
 - Show disagreements, diverse perspectives, authentic team dynamics
   </critical>
 
-## 📚 Document Discovery - Selective Epic Loading
-
-**Strategy**: This workflow needs the completed epic, previous retrospective, and potentially architecture/PRD for context.
-
-**Epic Discovery (SELECTIVE LOAD):**
-
-1. Determine completed epic number (from sprint-status or user)
-2. If sharded: Load ONLY `epic-{epic_num}.md`
-3. If whole: Load complete epics file and extract relevant epic
-
-**Retrospective History:**
-
-1. Load previous epic's retrospective to check if lessons were applied
-2. Pattern: `retrospectives/epic-{prev_num}-retro-*.md`
-
-**Supporting Documents (Full Load if needed):**
-
-1. Architecture: Check for whole document first, then sharded index + all sections
-2. PRD: Same pattern as architecture
-3. These provide additional context for understanding epic execution
-
-**Priority**: Whole document first, then sharded version.
-
 <workflow>
 
 <step n="1" goal="Epic Discovery - Find Completed Epic with Priority Logic">
@@ -59,7 +36,7 @@ PARTY MODE PROTOCOL:
 Bob (Scrum Master): "Welcome to the retrospective, {user_name}. Let me help you identify which epic we just completed. I'll check sprint-status first, but you're the ultimate authority on what we're reviewing today."
 </output>
 
-<action>PRIORITY 1: Check sprint-status.yaml first</action>
+<action>PRIORITY 1: Check {sprint_status_file} first</action>
 
 <action>Load the FULL file: {sprint_status_file}</action>
 <action>Read ALL development_status entries</action>
@@ -71,7 +48,7 @@ Bob (Scrum Master): "Welcome to the retrospective, {user_name}. Let me help you
   <action>Present finding to user with context</action>
 
   <output>
-Bob (Scrum Master): "Based on sprint-status.yaml, it looks like Epic {{detected_epic}} was recently completed. Is that the epic you want to review today, {user_name}?"
+Bob (Scrum Master): "Based on {sprint_status_file}, it looks like Epic {{detected_epic}} was recently completed. Is that the epic you want to review today, {user_name}?"
   </output>
 
 <action>WAIT for {user_name} to confirm or correct</action>
@@ -92,7 +69,7 @@ Bob (Scrum Master): "Got it, we're reviewing Epic {{epic_number}}. Let me gather
   <action>PRIORITY 2: Ask user directly</action>
 
   <output>
-Bob (Scrum Master): "I'm having trouble detecting the completed epic from sprint-status.yaml. {user_name}, which epic number did you just complete?"
+Bob (Scrum Master): "I'm having trouble detecting the completed epic from {sprint_status_file}. {user_name}, which epic number did you just complete?"
   </output>
 
 <action>WAIT for {user_name} to provide epic number</action>
@@ -116,7 +93,7 @@ Bob (Scrum Master): "I found stories for Epic {{detected_epic}} in the stories f
 
 <action>Once {{epic_number}} is determined, verify epic completion status</action>
 
-<action>Find all stories for epic {{epic_number}} in sprint-status.yaml:
+<action>Find all stories for epic {{epic_number}} in {sprint_status_file}:
 
 - Look for keys starting with "{{epic_number}}-" (e.g., "1-1-", "1-2-", etc.)
 - Exclude epic key itself ("epic-{{epic_number}}")
@@ -179,6 +156,11 @@ Bob (Scrum Master): "Perfect. Epic {{epic_number}} is complete and ready for ret
 
 </step>
 
+<step n="0.5" goal="Discover and load project documents">
+  <invoke-protocol name="discover_inputs" />
+  <note>After discovery, these content variables are available: {epics_content} (selective load for this epic), {architecture_content}, {prd_content}, {document_project_content}</note>
+</step>
+
 <step n="2" goal="Deep Story Analysis - Extract Lessons from Implementation">
 
 <output>
@@ -382,7 +364,7 @@ Alice (Product Owner): "Good thinking - helps us connect what we learned to what
 <action>Attempt to load next epic using selective loading strategy:</action>
 
 **Try sharded first (more specific):**
-<action>Check if file exists: {output*folder}/\_epic*/epic-{{next_epic_num}}.md</action>
+<action>Check if file exists: {output_folder}/epic\*/epic-{{next_epic_num}}.md</action>
 
 <check if="sharded epic file found">
   <action>Load {output_folder}/*epic*/epic-{{next_epic_num}}.md</action>
@@ -391,7 +373,7 @@ Alice (Product Owner): "Good thinking - helps us connect what we learned to what
 
 **Fallback to whole document:**
 <check if="sharded epic not found">
-<action>Check if file exists: {output*folder}/\_epic*.md</action>
+<action>Check if file exists: {output_folder}/epic\*.md</action>
 
   <check if="whole epic file found">
     <action>Load entire epics document</action>
@@ -1346,7 +1328,7 @@ Bob (Scrum Master): "See you all when prep work is done. Meeting adjourned!"
 ✅ Retrospective document saved: {retrospectives_folder}/epic-{{epic_number}}-retro-{date}.md
 </output>
 
-<action>Update sprint-status.yaml to mark retrospective as completed</action>
+<action>Update {sprint_status_file} to mark retrospective as completed</action>
 
 <action>Load the FULL file: {sprint_status_file}</action>
 <action>Find development_status key "epic-{{epic_number}}-retrospective"</action>
@@ -1356,7 +1338,7 @@ Bob (Scrum Master): "See you all when prep work is done. Meeting adjourned!"
 
 <check if="update successful">
   <output>
-✅ Retrospective marked as completed in sprint-status.yaml
+✅ Retrospective marked as completed in {sprint_status_file}
 
 Retrospective key: epic-{{epic_number}}-retrospective
 Status: {{previous_status}} → done
@@ -1365,9 +1347,9 @@ Status: {{previous_status}} → done
 
 <check if="retrospective key not found">
   <output>
-⚠️ Could not update retrospective status: epic-{{epic_number}}-retrospective not found in sprint-status.yaml
+⚠️ Could not update retrospective status: epic-{{epic_number}}-retrospective not found in {sprint_status_file}
 
-Retrospective document was saved successfully, but sprint-status.yaml may need manual update.
+Retrospective document was saved successfully, but {sprint_status_file} may need manual update.
 </output>
 </check>