feat: Enhance role functionality and task management across coordinator, explorer, implementer, planner, reviewer, and workflow phases

.claude/skills/team-issue/roles/coordinator.md

@@ -101,7 +101,8 @@ function detectMode(issueIds, userMode) {
     const hasHighPriority = issues.some(i => i.priority >= 4)
     return hasHighPriority ? 'full' : 'quick'
   }
-  return count <= 5 ? 'full' : 'batch'
+  // 3-4 issues with review, 5+ triggers batch parallel processing
+  return count >= 5 ? 'batch' : 'full'
 }
 ```
 
@@ -228,19 +229,25 @@ for (const issueId of issueIds) {
 const exploreBatches = chunkArray(issueIds, 5)  // max 5 parallel
 const solveBatches = chunkArray(issueIds, 3)    // max 3 parallel
 
-// Create EXPLORE tasks (parallel within batch)
+// Create EXPLORE tasks — all parallel within each batch, batches run in rolling window
+// Each batch of ≤5 runs concurrently; next batch starts when current batch completes
 const exploreTaskIds = []
+let prevBatchLastId = null
 for (const [batchIdx, batch] of exploreBatches.entries()) {
+  const batchTaskIds = []
   for (const issueId of batch) {
     const id = TaskCreate({
       subject: `EXPLORE-${String(exploreTaskIds.length + 1).padStart(3, '0')}: Context for ${issueId}`,
       description: `Batch ${batchIdx + 1}: Explore codebase context for issue ${issueId}.`,
       activeForm: `Exploring ${issueId}`,
       owner: "explorer",
-      addBlockedBy: batchIdx > 0 ? [exploreTaskIds[exploreTaskIds.length - 1]] : []
+      // Only block on previous batch's LAST task (not within same batch)
+      addBlockedBy: prevBatchLastId ? [prevBatchLastId] : []
     })
+    batchTaskIds.push(id)
     exploreTaskIds.push(id)
   }
+  prevBatchLastId = batchTaskIds[batchTaskIds.length - 1]
 }
 
 // Create SOLVE tasks (blocked by corresponding EXPLORE)

.claude/skills/team-issue/roles/explorer.md

@@ -72,6 +72,9 @@ TaskUpdate({ taskId: task.id, status: 'in_progress' })
 ### Phase 2: Issue Loading & Context Setup
 
 ```javascript
+// Resolve project root from working directory
+const projectRoot = Bash('pwd').trim()
+
 // Extract issue ID from task description
 const issueIdMatch = task.description.match(/(?:GH-\d+|ISS-\d{8}-\d{6})/)
 const issueId = issueIdMatch ? issueIdMatch[0] : null

.claude/skills/team-issue/roles/implementer.md

@@ -185,8 +185,20 @@ Dependencies: ${explorerContext.dependencies?.join(', ') || 'N/A'}
 ### Phase 4: Verify & Commit
 
 ```javascript
+// Detect test command from package.json or project config
+let testCmd = 'npm test'
+try {
+  const pkgJson = JSON.parse(Read('package.json'))
+  if (pkgJson.scripts?.test) testCmd = 'npm test'
+  else if (pkgJson.scripts?.['test:unit']) testCmd = 'npm run test:unit'
+} catch {
+  // Fallback: try common test runners
+  const hasYarn = Bash('test -f yarn.lock && echo yes || echo no').trim() === 'yes'
+  if (hasYarn) testCmd = 'yarn test'
+}
+
 // Verify implementation
-const testResult = Bash(`npm test 2>&1 || echo "TEST_FAILED"`)
+const testResult = Bash(`${testCmd} 2>&1 || echo "TEST_FAILED"`)
 const testPassed = !testResult.includes('TEST_FAILED') && !testResult.includes('FAIL')
 
 if (!testPassed) {

.claude/skills/team-issue/roles/planner.md

@@ -71,6 +71,9 @@ TaskUpdate({ taskId: task.id, status: 'in_progress' })
 ### Phase 2: Context Loading
 
 ```javascript
+// Resolve project root from working directory
+const projectRoot = Bash('pwd').trim()
+
 // Extract issue ID
 const issueIdMatch = task.description.match(/(?:GH-\d+|ISS-\d{8}-\d{6})/)
 const issueId = issueIdMatch ? issueIdMatch[0] : null

.claude/skills/team-issue/roles/reviewer.md

@@ -163,7 +163,7 @@ for (const issueId of issueIds) {
     completeness: { score: 0, findings: [] }
   }
   
-  // 1. Technical Feasibility — verify solution references real files
+  // 1. Technical Feasibility — verify solution references real files + semantic validation
   if (context && context.relevant_files) {
     const solutionFiles = solution.bound.tasks?.flatMap(t => t.files || []) || []
     const contextFiles = context.relevant_files.map(f => f.path || f)
@@ -177,6 +177,24 @@ for (const issueId of issueIds) {
         `Uncovered files: ${uncovered.join(', ')}`
       )
     }
+    
+    // Semantic validation via ACE — verify solution references exist in codebase
+    const projectRoot = Bash('pwd').trim()
+    const aceResults = mcp__ace-tool__search_context({
+      project_root_path: projectRoot,
+      query: `${solution.bound.title || issue.title}. Verify patterns: ${solutionFiles.slice(0, 5).join(', ')}`
+    })
+    if (aceResults && aceResults.length > 0) {
+      // Cross-check ACE results against solution's assumed patterns
+      const aceFiles = aceResults.map(r => r.file || r.path).filter(Boolean)
+      const missedByAce = solutionFiles.filter(sf => !aceFiles.some(af => af.includes(sf)))
+      if (missedByAce.length > solutionFiles.length * 0.5) {
+        review.technical_feasibility.score = Math.max(50, review.technical_feasibility.score - 10)
+        review.technical_feasibility.findings.push(
+          `ACE semantic search found divergent patterns — solution may reference outdated code`
+        )
+      }
+    }
   } else {
     review.technical_feasibility.score = 70  // No context to validate against
     review.technical_feasibility.findings.push('Explorer context not available for cross-validation')

.claude/skills/workflow-plan/phases/04-task-generation.md

@@ -468,7 +468,12 @@ if (userChoice.answers["Next Action"] === "Verify Plan Quality (Recommended)") {
   Skill(skill="workflow-execute", args="--session " + sessionId);
 } else if (userChoice.answers["Next Action"] === "Review Status Only") {
   console.log("\nDisplaying session status...\n");
-  Skill(skill="workflow:status", args="--session " + sessionId);
+  // Display session status inline
+  const sessionMeta = JSON.parse(Read(`.workflow/active/${sessionId}/workflow-session.json`));
+  const todoList = Read(`.workflow/active/${sessionId}/TODO_LIST.md`);
+  console.log(`Session: ${sessionId}`);
+  console.log(`Status: ${sessionMeta.status}`);
+  console.log(`\n--- TODO List ---\n${todoList}`);
 }
 ```
 
@@ -477,7 +482,7 @@ if (userChoice.answers["Next Action"] === "Verify Plan Quality (Recommended)") {
 **Return to Orchestrator**: Based on user's choice:
 - **Verify** -> Orchestrator reads phases/05-plan-verify.md and executes Phase 5 in-process
 - **Execute** -> Skill(skill="workflow-execute")
-- **Review** -> Route to /workflow:status
+- **Review** -> Display session status inline
 
 ## Output
 
@@ -492,4 +497,4 @@ if (userChoice.answers["Next Action"] === "Verify Plan Quality (Recommended)") {
 Based on user's plan confirmation choice:
 - If "Verify" -> [Phase 5: Plan Verification](05-plan-verify.md)
 - If "Execute" -> Skill(skill="workflow-execute")
-- If "Review" -> External: /workflow:status
+- If "Review" -> Display session status inline

.claude/skills/workflow-tdd/phases/05-tdd-task-generation.md

@@ -113,7 +113,7 @@ const userConfig = {
 }
 ```
 
-**Auto Mode**: When `--yes` or `-y`: Skip user questions, use defaults (no materials, Agent executor).
+**Auto Mode**: When `workflowPreferences.autoYes` is true, skip user questions, use defaults (no materials, Agent executor).
 
 ---
 

.claude/skills/workflow-tdd/phases/06-tdd-structure-validation.md

@@ -159,7 +159,12 @@ if (userChoice === "Verify TDD Compliance (Recommended)") {
 } else if (userChoice === "Start Execution") {
   Skill(skill="workflow-execute", args="--session " + sessionId);
 } else if (userChoice === "Review Status Only") {
-  Skill(skill="workflow:status", args="--session " + sessionId);
+  // Display session status inline
+  const sessionMeta = JSON.parse(Read(`.workflow/active/${sessionId}/workflow-session.json`));
+  const todoList = Read(`.workflow/active/${sessionId}/TODO_LIST.md`);
+  console.log(`\nSession: ${sessionId}`);
+  console.log(`Status: ${sessionMeta.status}`);
+  console.log(`\n--- TODO List ---\n${todoList}`);
 }
 ```
 
@@ -176,4 +181,4 @@ if (userChoice === "Verify TDD Compliance (Recommended)") {
 Based on user's plan confirmation choice:
 - If "Verify" → [Phase 7: TDD Verification](07-tdd-verify.md)
 - If "Execute" → Skill(skill="workflow-execute")
-- If "Review" → External: /workflow:status
+- If "Review" -> Display session status inline

.claude/skills/workflow-test-fix/SKILL.md

@@ -54,20 +54,14 @@ Task Pipeline (generated in Phase 4, executed in Phase 5):
 5. **Progressive Phase Loading**: Phase docs read **only** when that phase executes, not upfront
 6. **Adaptive Strategy**: Fix loop auto-selects strategy (conservative/aggressive/surgical) based on iteration context
 7. **Quality Gate**: Pass rate >= 95% (criticality-aware) terminates the fix loop
-8. **Original Commands Preserved**: Phase files preserve full original command content and Skill() calls
+8. **Phase File Hygiene**: Phase files reference `workflowPreferences.*` for preferences, no CLI flag parsing
 
 ## Usage
 
-```bash
+Full pipeline and execute-only modes are triggered by skill name routing (see Mode Detection). Workflow preferences (auto mode) are collected interactively via AskUserQuestion before dispatching to phases.
-# Full pipeline: generate + execute
-/workflow:test-fix-gen "Test the user authentication API"
-/workflow:test-fix-gen WFS-user-auth-v2
 
-# Execute only (resume from existing test session with generated tasks)
+**Full pipeline** (workflow:test-fix-gen): Task description or session ID as arguments → interactive preference collection → generate + execute pipeline
-/workflow:test-cycle-execute
+**Execute only** (workflow:test-cycle-execute): Auto-discovers active session → interactive preference collection → execution loop
-/workflow:test-cycle-execute --resume-session="WFS-test-user-auth"
-/workflow:test-cycle-execute --max-iterations=15
-```
 
 ## Interactive Preference Collection