feat(workflows): Implement intelligent file discovery protocol and Phase 4 BMGD workflows

## Core Workflow Engine Enhancements

### discover_inputs Protocol (MAJOR)
- Added reusable `discover_inputs` protocol to workflow.xml for intelligent file loading
- Supports three loading strategies:
  - FULL_LOAD: Load all shards for PRD, Architecture, UX (changed pattern from /index.md to /*/*.md)
  - SELECTIVE_LOAD: Load specific shard via template variable (e.g., epic-{{epic_num}}.md)
  - INDEX_GUIDED: Load index, analyze TOC, intelligently load relevant docs (with "DO NOT BE LAZY" mandate)
- Auto-discovers whole vs sharded documents with proper fallback
- Provides transparent reporting of loaded content with file counts
- Invoked via <invoke-protocol name="discover_inputs" /> tag in workflow instructions

### Advanced Elicitation Improvements
- Renamed adv-elicit.xml to advanced-elicitation.xml for clarity
- Updated all references across agents and commands

### Shard Document Tool Enhancement
- Added Step 6: Handle Original Document with three options:
  - [d] Delete - Remove original (recommended, prevents confusion)
  - [m] Move to archive - Backup original to archive folder
  - [k] Keep - Warning about defeating sharding purpose
- Prevents issue where both whole and sharded versions exist, confusing discover_inputs protocol

## BMM Module - Input File Pattern Standardization

### Phase 1 - Analysis (1 workflow)
- product-brief: Added load_strategy (FULL_LOAD for research/brainstorming, INDEX_GUIDED for document_project)
- Updated instructions.md to use invoke-protocol, replaced manual fuzzy matching

### Phase 2 - Planning (4 workflows)
- prd: Added load_strategy, updated instructions to reference {product_brief_content}, {research_content}
- create-ux-design: Added load_strategy, removed fuzzy matching from instructions
- tech-spec: Added load_strategy for brownfield context discovery
- All epics patterns updated to support SELECTIVE_LOAD for specific epic shards

### Phase 3 - Solutioning (2 workflows)
- architecture: Added load_strategy, updated instructions to use pre-loaded {prd_content}, {epics_content}, {ux_design_content}
- solutioning-gate-check: Added load_strategy, replaced manual discovery with protocol invocation

### Phase 4 - Implementation (8 workflows)
- code-review: Added load_strategy, fixed sharded patterns to /*/*.md, added step 1.5 for protocol
- correct-course: Added complete input_file_patterns section (was missing), added step 0.5
- create-story: Added load_strategy, updated to SELECTIVE_LOAD for epics, added step 1.5
- dev-story: Added complete input_file_patterns section (was missing), added step 0.5
- epic-tech-context: Added load_strategy, updated PRD extraction to use {prd_content}, added step 1.5
- retrospective: Added load_strategy for architecture/prd (FULL_LOAD), epics (SELECTIVE_LOAD), added step 0.5
- sprint-planning: Fixed sharded pattern to load ALL epics (/*/*.md), added step 0.5
- story-context: Added load_strategy, updated doc collection to reference pre-loaded content, added step 1.5

### Sprint Artifacts Path Corrections
- story-done: Added missing sprint_artifacts variable, fixed sprint_status path from {context_dir} to {sprint_artifacts}
- story-ready: Added missing sprint_artifacts variable
- story-context: Fixed undefined {context_dir} -> {sprint_artifacts}
- correct-course: Added sprint_artifacts and sprint_status variables

## BMGD Module - Phase 4 Production Workflows (NEW)

Added complete Phase 4 implementation workflows for game development:
- code-review: Senior developer review for completed game features
- correct-course: Sprint change management for game projects
- create-story: Story generation for game mechanics/features
- dev-story: Feature implementation workflow
- epic-tech-context: Technical spec generation per game epic
- retrospective: Epic completion review and lessons learned
- sprint-planning: Game development sprint status tracking
- story-context: Dynamic context assembly for game stories
- story-done: Story completion workflow
- story-ready: Story readiness workflow

All BMGD workflows follow BMM patterns with game-specific adaptations.

## Agent Updates

### BMM Agents
- Updated all 7 BMM agents (analyst, architect, dev, pm, sm, tea, tech-writer, ux-designer)
- Standardized web bundle configurations

### BMGD Agents
- Updated 4 game development agents (game-architect, game-designer, game-dev, game-scrum-master)
- Aligned with BMM agent structure

### CIS Agents
- Updated 5 creative intelligence agents for consistency

## Documentation & Configuration

- Updated CHANGELOG.md with Phase 4 workflow additions
- Updated files-manifest.csv and task-manifest.csv
- Updated .claude commands for all agents
- Fixed formatting issues from previous commits

## Breaking Changes

NONE - All changes are backward compatible. Workflows without input_file_patterns continue to work.
Workflows with input_file_patterns now benefit from intelligent auto-loading.

## Migration Notes

Existing workflows can gradually adopt discover_inputs protocol by:
1. Adding load_strategy to existing input_file_patterns in workflow.yaml
2. Adding <invoke-protocol name="discover_inputs" /> step in instructions.md
3. Replacing manual file loading with references to {pattern_name_content} variables

src/core/tools/shard-doc.xml

@@ -57,6 +57,50 @@
       <i>- Any tool output or warnings</i>
       <action>Inform user that sharding completed successfully</action>
     </step>
+
+    <step n="6" title="Handle Original Document">
+      <critical>Keeping both the original and sharded versions defeats the purpose of sharding and can cause confusion</critical>
+      <action>Present user with options for the original document:</action>
+
+      <ask>What would you like to do with the original document `[source-document-name]`?
+
+Options:
+[d] Delete - Remove the original (recommended - shards can always be recombined)
+[m] Move to archive - Move original to a backup/archive location
+[k] Keep - Leave original in place (NOT recommended - defeats sharding purpose)
+
+Your choice (d/m/k):</ask>
+
+      <check if="user selects 'd' (delete)">
+        <action>Delete the original source document file</action>
+        <action>Confirm deletion to user: "✓ Original document deleted: [source-document-path]"</action>
+        <note>The document can be reconstructed from shards by concatenating all section files in order</note>
+      </check>
+
+      <check if="user selects 'm' (move)">
+        <action>Determine default archive location: same directory as source, in an "archive" subfolder</action>
+        <action>Example: /path/to/architecture.md → /path/to/archive/architecture.md</action>
+        <ask>Archive location ([y] to use default: [default-archive-path], or provide custom path):</ask>
+        <action if="user accepts default">Use default archive path</action>
+        <action if="user provides custom path">Use custom archive path</action>
+        <action>Create archive directory if it doesn't exist</action>
+        <action>Move original document to archive location</action>
+        <action>Confirm move to user: "✓ Original document moved to: [archive-path]"</action>
+      </check>
+
+      <check if="user selects 'k' (keep)">
+        <action>Display warning to user:</action>
+        <output>⚠️ WARNING: Keeping both original and sharded versions is NOT recommended.
+
+This creates confusion because:
+- The discover_inputs protocol may load the wrong version
+- Updates to one won't reflect in the other
+- You'll have duplicate content taking up space
+
+Consider deleting or archiving the original document.</output>
+        <action>Confirm user choice: "Original document kept at: [source-document-path]"</action>
+      </check>
+    </step>
   </flow>
 
   <halt-conditions critical="true">