diff --git a/src/modules/bmm/workflows/4-implementation/batch-super-dev/instructions.md b/src/modules/bmm/workflows/4-implementation/batch-super-dev/instructions.md
index a57add07..98d417e9 100644
--- a/src/modules/bmm/workflows/4-implementation/batch-super-dev/instructions.md
+++ b/src/modules/bmm/workflows/4-implementation/batch-super-dev/instructions.md
@@ -820,26 +820,130 @@ QUALITY OVER SPEED: Taking time to ensure correctness.
Set quality_multiplier = 1.5
+
+
+
+ For each selected story:
+
+ Read story file Tasks section
+ Analyze task descriptions for dependencies on other selected stories:
+
+ Dependency detection rules:
+ - Look for mentions of other story keys (e.g., "18-1", "18-2")
+ - Look for phrases like "requires", "depends on", "needs", "after"
+ - Look for file paths that other stories create
+ - Look for models/services that other stories define
+
+
+ Build dependency map:
+ story_key: {
+ depends_on: [list of story keys this depends on],
+ blocks: [list of story keys that depend on this]
+ }
+
+
+ Compute waves using topological sort:
+
+ Wave 1: Stories with no dependencies (can start immediately)
+ Wave 2: Stories that only depend on Wave 1
+ Wave 3: Stories that depend on Wave 2
+ ...
+
+
+
+
+
-**How should these stories be processed?**
+**Choose execution strategy:**
-Options:
-- **sequential**: Run stories one-by-one in this session (slower, easier to monitor)
-- **parallel**: Spawn Task agents to process stories concurrently (faster, autonomous)
+{{#if waves.length > 1}}
+[W] WAVE-BASED PARALLEL (Recommended)
+ - Respects dependencies between stories
+ - Runs independent stories in parallel within each wave
+ - Wave 1: {{wave_1_stories}} → Wave 2: {{wave_2_stories}} → ...
+ - Estimated time: {{wave_time}} ({{savings}}% faster than sequential)
+ - Safer than full parallel (honors dependencies)
+{{/if}}
-Enter: sequential or parallel
+[S] SEQUENTIAL
+ - Process stories one-by-one in this session
+ - Easier to monitor and debug
+ - Estimated time: {{sequential_time}}
+ - Best for: When you want full control
+
+{{#if waves.length == 1}}
+[P] FULL PARALLEL (All {{count}} stories)
+ - All stories independent, no dependencies
+ - Spawn {{count}} agents concurrently
+ - Estimated time: {{parallel_time}} ({{savings}}% faster)
+{{else}}
+[P] FULL PARALLEL (Ignore dependencies - RISKY)
+ - Spawn all {{count}} agents concurrently
+ - ⚠️ May fail if stories depend on each other
+ - Use only if you're certain dependencies are wrong
+{{/if}}
+
+Enter: {{#if waves.length > 1}}w{{/if}}/s/p
- Capture response as: execution_mode
+ Capture response as: execution_strategy
-
+
+ Set execution_mode = "wave_based"
+ Set use_task_agents = true
+ Set wave_execution = true
+
+
+
+
+ Set execution_mode = "sequential"
Set parallel_count = 1
Set use_task_agents = false
+ Set wave_execution = false
-
+
+ Set execution_mode = "full_parallel"
Set use_task_agents = true
+ Set wave_execution = false
**How many agents should run in parallel?**
@@ -895,8 +999,12 @@ Enter number (2-10) or 'all':
Initialize counters: completed=0, failed=0, failed_stories=[], reconciliation_warnings=[], reconciliation_warnings_count=0
Set start_time = current timestamp
-
- Jump to Step 4-Parallel (Task Agent execution)
+
+ Jump to Step 4-Wave (Wave-based execution)
+
+
+
+ Jump to Step 4-Parallel (Full parallel execution)
@@ -904,6 +1012,80 @@ Enter number (2-10) or 'all':
+
+
+
+ For each wave in sequence:
+
+
+
+
+ Spawn Task agents in PARALLEL (send all in single message):
+
+ For each story in this wave:
+
+
+ Task tool:
+ - subagent_type: "general-purpose"
+ - description: "Implement story {{story_key}}"
+ - prompt: "Execute super-dev-pipeline for story {{story_key}}.
+
+ Story file: docs/sprint-artifacts/{{story_key}}.md
+ Complexity: {{complexity_level}}
+ Mode: batch, wave {{wave_num}}
+
+ Follow all 11 steps, commit when complete, report status."
+ - Store agent_id
+
+
+ Wait for ALL agents in this wave to complete
+
+ For each completed agent in wave:
+
+
+
+ Increment completed counter
+ Execute Step 4.5: Reconciliation
+
+
+
+
+ Increment failed counter
+ Add to failed_stories list
+
+
+
+ Jump to Step 5 (Summary)
+
+
+
+
+
+
+ After all waves processed, jump to Step 5 (Summary)
+
+