refactor: Optimize context-gather workflow with Synthesis role clarification

- Rename Track 0 from 'Exploration Aggregation' to 'Exploration Synthesis'
- Add explicit synthesis logic for critical_files prioritization and deduplication
- Enhance explore-json-schema to support relevance scores in relevant_files
- Update explore agent prompts across context-gather and lite-plan commands
- Add synthesizeCriticalFiles and synthesizeConflictIndicators helper functions

🤖 Generated with [Claude Code](https://claude.com/claude-code)

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

.claude/agents/context-search-agent.md

@@ -104,10 +104,12 @@ Execute all tracks in parallel for comprehensive coverage.
 
 **Note**: Historical archive analysis (querying `.workflow/archives/manifest.json`) is optional and should be performed if the manifest exists. Inject findings into `conflict_detection.historical_conflicts[]`.
 
-#### Track 0: Exploration Aggregation (Optional)
+#### Track 0: Exploration Synthesis (Optional)
 
 **Trigger**: When `explorations-manifest.json` exists in session `.process/` folder
 
+**Purpose**: Transform raw exploration data into prioritized, deduplicated insights. This is NOT simple aggregation - it synthesizes `critical_files` (priority-ranked), deduplicates patterns/integration_points, and generates `conflict_indicators`.
+
 ```javascript
 // Check for exploration results from context-gather parallel explore phase
 const manifestPath = `.workflow/active/${session_id}/.process/explorations-manifest.json`;
@@ -133,14 +135,28 @@ if (file_exists(manifestPath)) {
     }
   }));
 
-  // Aggregate insights across all explorations (fixed data access)
+  // SYNTHESIS (not aggregation): Transform raw data into prioritized insights
   const aggregated_insights = {
-    critical_files: deduplicateByRelevance(explorationData.flatMap(e => e.data.relevant_files || [])),
+    // CRITICAL: Synthesize priority-ranked critical_files from multiple relevant_files lists
-    conflict_indicators: explorationData.flatMap(e => extractConflictIndicators(e.data, e.angle)),
+    // - Deduplicate by path
+    // - Rank by: mention count across angles + individual relevance scores
+    // - Top 10-15 files only (focused, actionable)
+    critical_files: synthesizeCriticalFiles(explorationData.flatMap(e => e.data.relevant_files || [])),
+
+    // SYNTHESIS: Generate conflict indicators from pattern mismatches, constraint violations
+    conflict_indicators: synthesizeConflictIndicators(explorationData),
+
+    // Deduplicate clarification questions (merge similar questions)
     clarification_needs: deduplicateQuestions(explorationData.flatMap(e => e.data.clarification_needs || [])),
+
+    // Preserve source attribution for traceability
     constraints: explorationData.map(e => ({ constraint: e.data.constraints, source_angle: e.angle })).filter(c => c.constraint),
-    all_patterns: explorationData.map(e => ({ patterns: e.data.patterns, source_angle: e.angle })),
+
-    all_integration_points: explorationData.map(e => ({ points: e.data.integration_points, source_angle: e.angle }))
+    // Deduplicate patterns across angles (merge identical patterns)
+    all_patterns: deduplicatePatterns(explorationData.map(e => ({ patterns: e.data.patterns, source_angle: e.angle }))),
+
+    // Deduplicate integration points (merge by file:line location)
+    all_integration_points: deduplicateIntegrationPoints(explorationData.map(e => ({ points: e.data.integration_points, source_angle: e.angle })))
   };
 
   // Store for Phase 3 packaging
@@ -148,6 +164,22 @@ if (file_exists(manifestPath)) {
                          complexity: manifest.complexity, angles: manifest.angles_explored,
                          explorations, aggregated_insights };
 }
+
+// Synthesis helper functions (conceptual)
+function synthesizeCriticalFiles(allRelevantFiles) {
+  // 1. Group by path
+  // 2. Count mentions across angles
+  // 3. Average relevance scores
+  // 4. Rank by: (mention_count * 0.6) + (avg_relevance * 0.4)
+  // 5. Return top 10-15 with mentioned_by_angles attribution
+}
+
+function synthesizeConflictIndicators(explorationData) {
+  // 1. Detect pattern mismatches across angles
+  // 2. Identify constraint violations
+  // 3. Flag files mentioned with conflicting integration approaches
+  // 4. Assign severity: critical/high/medium/low
+}
 ```
 
 #### Track 1: Reference Documentation

.claude/commands/workflow/lite-plan.md

@@ -196,9 +196,12 @@ Execute **${angle}** exploration for task planning context. Analyze codebase fro
 **Required Fields** (all ${angle} focused):
 - project_structure: Modules/architecture relevant to ${angle}
 - relevant_files: Files affected from ${angle} perspective
+  **IMPORTANT**: Use object format with relevance scores for synthesis:
+  \`[{path: "src/file.ts", relevance: 0.85, rationale: "Core ${angle} logic"}]\`
+  Scores: 0.7+ high priority, 0.5-0.7 medium, <0.5 low
 - patterns: ${angle}-related patterns to follow
 - dependencies: Dependencies relevant to ${angle}
-- integration_points: Where to integrate from ${angle} viewpoint
+- integration_points: Where to integrate from ${angle} viewpoint (include file:line locations)
 - constraints: ${angle}-specific limitations/conventions
 - clarification_needs: ${angle}-related ambiguities (with options array)
 - _metadata.exploration_angle: "${angle}"

.claude/commands/workflow/tools/context-gather.md

@@ -46,7 +46,7 @@ Step 2: Complexity Assessment & Parallel Explore (NEW)
 Step 3: Invoke Context-Search Agent (with exploration input)
    ├─ Phase 1: Initialization & Pre-Analysis
    ├─ Phase 2: Multi-Source Discovery
-   │  ├─ Track 0: Exploration aggregation (NEW)
+   │  ├─ Track 0: Exploration Synthesis (prioritize & deduplicate)
    │  ├─ Track 1-4: Existing tracks
    └─ Phase 3: Synthesis & Packaging
       └─ Generate context-package.json with exploration_results
@@ -164,9 +164,12 @@ Execute **${angle}** exploration for task planning context. Analyze codebase fro
 **Required Fields** (all ${angle} focused):
 - project_structure: Modules/architecture relevant to ${angle}
 - relevant_files: Files affected from ${angle} perspective
+  **IMPORTANT**: Use object format with relevance scores for synthesis:
+  \`[{path: "src/file.ts", relevance: 0.85, rationale: "Core ${angle} logic"}]\`
+  Scores: 0.7+ high priority, 0.5-0.7 medium, <0.5 low
 - patterns: ${angle}-related patterns to follow
 - dependencies: Dependencies relevant to ${angle}
-- integration_points: Where to integrate from ${angle} viewpoint
+- integration_points: Where to integrate from ${angle} viewpoint (include file:line locations)
 - constraints: ${angle}-specific limitations/conventions
 - clarification_needs: ${angle}-related ambiguities (with options array)
 - _metadata.exploration_angle: "${angle}"
@@ -239,7 +242,7 @@ Execute complete context-search-agent workflow for implementation planning:
 
 ### Phase 2: Multi-Source Context Discovery
 Execute all discovery tracks:
-- **Track 0**: Exploration aggregation (load ${sessionFolder}/explorations-manifest.json and aggregate)
+- **Track 0**: Exploration Synthesis (load ${sessionFolder}/explorations-manifest.json, prioritize critical_files, deduplicate patterns/integration_points)
 - **Track 1**: Historical archive analysis (query manifest.json for lessons learned)
 - **Track 2**: Reference documentation (CLAUDE.md, architecture docs)
 - **Track 3**: Web examples (use Exa MCP for unfamiliar tech/APIs)

.claude/skills/command-guide/reference/commands/workflow/lite-plan.md

@@ -196,9 +196,12 @@ Execute **${angle}** exploration for task planning context. Analyze codebase fro
 **Required Fields** (all ${angle} focused):
 - project_structure: Modules/architecture relevant to ${angle}
 - relevant_files: Files affected from ${angle} perspective
+  **IMPORTANT**: Use object format with relevance scores for synthesis:
+  \`[{path: "src/file.ts", relevance: 0.85, rationale: "Core ${angle} logic"}]\`
+  Scores: 0.7+ high priority, 0.5-0.7 medium, <0.5 low
 - patterns: ${angle}-related patterns to follow
 - dependencies: Dependencies relevant to ${angle}
-- integration_points: Where to integrate from ${angle} viewpoint
+- integration_points: Where to integrate from ${angle} viewpoint (include file:line locations)
 - constraints: ${angle}-specific limitations/conventions
 - clarification_needs: ${angle}-related ambiguities (with options array)
 - _metadata.exploration_angle: "${angle}"

.claude/workflows/cli-templates/schemas/explore-json-schema.json

@@ -20,8 +20,21 @@
     },
     "relevant_files": {
       "type": "array",
-      "items": {"type": "string"},
+      "items": {
-      "description": "File paths to be modified or referenced for the task"
+        "oneOf": [
+          {"type": "string"},
+          {
+            "type": "object",
+            "required": ["path", "relevance"],
+            "properties": {
+              "path": {"type": "string", "description": "File path relative to project root"},
+              "relevance": {"type": "number", "minimum": 0, "maximum": 1, "description": "Relevance score 0.0-1.0 (0.7+ high, 0.5-0.7 medium, <0.5 low)"},
+              "rationale": {"type": "string", "description": "Brief explanation of why this file is relevant from this exploration angle"}
+            }
+          }
+        ]
+      },
+      "description": "File paths to be modified or referenced for the task. Prefer object format with relevance scores for synthesis prioritization."
     },
     "patterns": {
       "type": "string",