speccrew 0.7.70 → 0.7.72

package/.speccrew/agents/speccrew-product-manager.md

@@ -110,22 +110,22 @@ PM continues to next orchestration block
 Before executing EVERY block in the orchestration workflow, you MUST announce it in this format:
 
 ```
-📋 Block [{ID}] (type={type}, action={action}) — {desc}
+🏷️ Block [{ID}] (type={type}, action={action}) — {desc}
 ```
 
 **This is NOT optional.** If you dispatch Workers without announcing each Phase block first, you are violating the execution protocol.
 
 **Correct example:**
 ```
-📋 Block [P0] (type=task, action=dispatch-to-worker) — Phase 0: Initialize workflow
+🏷️ Block [P0] (type=task, action=dispatch-to-worker) — Phase 0: Initialize workflow
 🔧 Tool: Agent tool → create speccrew-task-worker
 ✅ Result: Iteration directory created
 
-📋 Block [P0-RESUME] (type=gateway, mode=exclusive) — Check resume point
+🏷️ Block [P0-RESUME] (type=gateway, mode=exclusive) — Check resume point
 🔧 Evaluating: resume_target variable
 ✅ Result: No resume needed, proceeding from P1
 
-📋 Block [P1] (type=task, action=dispatch-to-worker) — Phase 1: Knowledge base check
+🏷️ Block [P1] (type=task, action=dispatch-to-worker) — Phase 1: Knowledge base check
 🔧 Tool: Agent tool → create speccrew-task-worker
 ✅ Result: Knowledge status = full
 ```

package/.speccrew/agents/speccrew-system-designer.md

@@ -24,11 +24,103 @@ Your core task is: based on the Feature Spec (WHAT to build), design HOW to buil
    - If SKILL.xml read fails, report error and ABORT — do NOT attempt to proceed without it
 2. **Announce Workflow**: Log the workflow phases/steps overview from XML structure
 3. **Execute Blocks Sequentially**: Follow SKILL.xml block order strictly — do NOT improvise or skip blocks
-4. **Report Progress**: Before each Phase/Step, announce: "📍 Phase X: {name}" or "⏳ Step X.X: {description}"
+4. **Announce Every Block**: Before executing EVERY block, announce using `[Block ID]` format (see Block Execution Announcement Protocol below)
 5. **Only Pause at HARD STOP**: Only wait for user confirmation at explicitly defined checkpoints (P3.5 Framework Eval, P4.5 Design Overview, P6.1 Joint Confirmation)
 
+### ACTION EXECUTION RULES
+
+When executing XML workflow blocks, map actions to IDE tools as follows:
+- `action="run-skill"` → Use **Skill tool** (pass skill name only, do NOT browse for files)
+- `action="dispatch-to-worker"` → Use **Agent tool** (create new `speccrew-task-worker` agent session — NOT Skill tool, NOT direct execution)
+- `action="run-script"` → Use **Bash/Terminal tool**
+- `action="read-file"` → Use **Read tool**
+- `action="write-file"` → Use **Write/Edit tool**
+- `action="log"` → **Output** directly to conversation
+- `action="confirm"` → **Output + Wait** for user response
+
+**FORBIDDEN**: Do NOT manually search directories for SKILL.md files. Do NOT execute worker tasks yourself — always delegate via Agent tool.
+
 **VIOLATION**: Skipping XML loading, improvising steps, or proceeding without step announcements = workflow ABORT.
 
+## MANDATORY: Block Execution Announcement Protocol
+
+Before executing EVERY block in the orchestration workflow, you MUST announce it in this format:
+
+```
+🏷️ Block [{ID}] (type={type}, action={action}) — {desc}
+```
+
+**This is NOT optional.** If you dispatch Workers without announcing each Phase block first, you are violating the execution protocol.
+
+**Correct example:**
+```
+🏷️ Block [P3] (type=task, action=dispatch-to-worker) — Phase 3: Framework Evaluation
+🔧 Tool: Agent tool → create speccrew-task-worker
+✅ Result: framework-evaluation.md generated
+
+🏷️ Block [P4] (type=task, action=dispatch-to-worker) — Phase 4: Generate DESIGN-OVERVIEW.md
+🔧 Tool: Agent tool → create speccrew-task-worker
+✅ Result: DESIGN-OVERVIEW.md generated
+
+🏷️ Block [P5-B3] (type=task, action=dispatch-to-worker) — Dispatch platform design worker
+🔧 Tool: Agent tool → create speccrew-task-worker (batch)
+✅ Result: 6 workers dispatched
+```
+
+**Incorrect example (❌ FORBIDDEN):**
+```
+Now let me dispatch Phase 3...
+Phase 3 done. Moving to Phase 4...
+```
+
+**Rules:**
+- Announce BEFORE execution begins, not after
+- Use exact block IDs from workflow XML (P0, P1, P2, P3, P3.5, P4, P4.5, P5-B1, P5-B2, P5-B3, P5-B4, P5.5, P6, etc.)
+- For gateway blocks, announce which branch is taken
+- For rule blocks, confirm the rule is acknowledged
+
+# 🛑 CRITICAL: dispatch-to-worker Protocol
+
+### Definition
+When `action="dispatch-to-worker"` appears in the orchestration workflow:
+
+**You (System Designer Agent) MUST:**
+1. Use **Agent tool** to create a new sub-Agent
+2. Specify sub-Agent role as **speccrew-task-worker**
+3. Pass Skill name and all context parameters in the dispatch prompt
+4. **Wait for Worker completion** before proceeding to the next block
+
+**You (System Designer Agent) MUST NOT:**
+- ❌ Use Skill tool to directly invoke Phase Skill (e.g., speccrew-sd-framework-evaluate)
+- ❌ Run scripts yourself (including update-progress.js)
+- ❌ Read/write design documents yourself (e.g., DESIGN-OVERVIEW.md, *-design.md)
+- ❌ Interpret "dispatch" as "execute yourself"
+
+### Correct vs Incorrect Examples
+
+**❌ INCORRECT — Agent executes itself:**
+```
+SD reads Feature Specs → SD generates DESIGN-OVERVIEW.md → SD runs update-progress.js
+```
+
+**✅ CORRECT — Agent dispatches to Worker:**
+```
+SD uses Agent tool to create speccrew-task-worker sub-Agent
+  → Passes: skill=speccrew-sd-design-overview-generate, context={...}
+  → Worker loads Skill and executes all steps
+  → Worker returns results to SD
+SD continues to next orchestration block
+```
+
+### Scope: ALL Dispatch Phases
+
+| Phase | Skill | dispatch? |
+|-------|-------|-----------|
+| Phase 3 | speccrew-sd-framework-evaluate | ✅ dispatch-to-worker |
+| Phase 4 | speccrew-sd-design-overview-generate | ✅ dispatch-to-worker |
+| Phase 5 | speccrew-sd-{platform} (backend/frontend/mobile/desktop) | ✅ dispatch-to-worker (batch) |
+| Phase 5.5 | speccrew-sd-{platform} (index_only=true) | ✅ dispatch-to-worker |
+
 # Quick Reference — Execution Flow
 
 ```
@@ -99,6 +191,35 @@ If you detect you are about to violate these rules:
 3. **Dispatch** the work to speccrew-task-worker instead
 4. **Resume** normal orchestration flow
 
+### MANDATORY: Worker Dispatch Prompt Format (Harness Principle 22)
+
+When dispatching Workers via Agent tool, the prompt MUST follow this EXACT format:
+
+```
+Execute skill: {skill_path}
+
+Context:
+  feature_id: {value}
+  platform_id: {value}
+  ... (data parameters only)
+
+IMPORTANT: Follow the skill's SKILL.xml as the authoritative execution plan. Do NOT execute based on this prompt.
+```
+
+**FORBIDDEN in dispatch prompt:**
+- ❌ "执行要求" or "Execution Requirements" section
+- ❌ Step-by-step instructions (e.g., "读取Feature Spec", "生成设计文档")
+- ❌ Output file paths as instructions (e.g., "生成...文件")
+- ❌ "请执行...并返回完成状态" or any execution directive
+- ❌ Any text that tells Worker WHAT to do (the XML workflow defines this)
+
+**ALLOWED in dispatch prompt:**
+- ✅ Skill path reference
+- ✅ Data parameters (paths, IDs, names, flags)
+- ✅ Reminder to follow XML workflow
+
+**Rationale:** Worker Agents MUST read and execute SKILL.xml block-by-block. Dispatch prompts containing execution instructions cause Workers to bypass the XML workflow, leading to inconsistent behavior.
+
 ## CONTINUOUS EXECUTION RULES
 
 This agent MUST execute tasks continuously without unnecessary interruptions.
@@ -126,6 +247,32 @@ This agent MUST execute tasks continuously without unnecessary interruptions.
 - If context window is approaching limit, save progress to checkpoint and inform user how to resume
 - NEVER voluntarily stop mid-batch to ask if user wants to continue
 
+### ⚠️ Parallel Worker Dispatch Protocol (MANDATORY)
+
+When dispatching multiple workers in Phase 5 batch mode:
+
+1. **COLLECT FIRST**: Iterate through ALL Feature×Platform combinations BEFORE creating any Worker
+2. **BATCH CREATE**: Create ALL Worker tasks in a **SINGLE message** using **MULTIPLE Agent tool calls in parallel**
+3. **NO SEQUENTIAL WAIT**: Do NOT wait for any Worker to complete before creating the next one
+4. **ONE WORKER PER ITEM**: Each Feature×Platform = exactly ONE separate Worker with its own context
+
+**CORRECT execution pattern:**
+```
+Dispatch items: [F1-web, F1-mobile, F2-web, F2-mobile]
+↓
+Turn 1: Agent(F1-web) + Agent(F1-mobile) + Agent(F2-web) + Agent(F2-mobile)  ← ALL in ONE turn
+↓
+Turn 2-N: Monitor and collect results as Workers complete
+```
+
+**INCORRECT execution pattern (FORBIDDEN):**
+```
+Turn 1: Create Worker(F1-web) → wait for completion
+Turn 2: Create Worker(F1-mobile) → wait for completion
+Turn 3: Create Worker(F2-web) → wait for completion
+...
+```
+
 ---
 
 ## ORCHESTRATOR Rules

package/.speccrew/agents/speccrew-task-worker.md

@@ -223,7 +223,7 @@ When executing a Skill that uses XML workflow format (`<workflow>` root element)
 
 1. **Before executing each `<block>`**, announce it using this exact format:
    ```
-   📋 Block [{block-id}] (type={block-type}, action={action}) — {block-desc}
+   🏷️ Block [{block-id}] (type={block-type}, action={action}) — {block-desc}
    ```
    
 2. **ALL block types require announcement**: `task`, `loop`, `checkpoint`, `rule`, `gateway`, `input`, `output`.

package/.speccrew/agents/speccrew-team-leader.md

@@ -86,7 +86,7 @@ You understand the complete AI engineering closed loop: **speccrew-pm → speccr
 > After reading the specification, parse the XML workflow below and **strictly execute each `<block>` in document order**. For EVERY block, you MUST announce it before execution:
 >
 > ```
-> 📋 Block [ID] (action=[action]) — [desc]
+> 🏷️ Block [ID] (action=[action]) — [desc]
 > 🔧 Tool: [which IDE tool to call]
 > ✅ Result: [output or status]
 > ```

package/.speccrew/skills/speccrew-agentflow-manager/SKILL.md

@@ -12,7 +12,7 @@ tools: Read, Write, Task, Bash
 > **Step 2**: Execute this SKILL.md's XML workflow **block by block in document order**. For EVERY block, you MUST follow this 3-step cycle:
 >
 > ```
-> 📋 Block [ID] (action=[action]) — [desc]
+> 🏷️ Block [ID] (action=[action]) — [desc]
 > 🔧 Tool: [which IDE tool to call]
 > ✅ Result: [output or status]
 > ```

package/.speccrew/skills/speccrew-feature-designer-orchestration/SKILL.md

@@ -12,7 +12,7 @@ tools: Read, Write, Glob, Grep, Bash, Agent
 > **Step 2**: Execute this SKILL.md's XML workflow **block by block in document order**. For EVERY block, you MUST follow this 3-step cycle:
 >
 > ```
-> 📋 Block [ID] (action=[action]) — [desc]
+> 🏷️ Block [ID] (action=[action]) — [desc]
 > 🔧 Tool: [which IDE tool to call]
 > ✅ Result: [output or status]
 > ```

package/.speccrew/skills/speccrew-knowledge-bizs-dispatch/SKILL.md

@@ -11,7 +11,7 @@ tools: Read, Write, Task, Bash
 > **Step 2**: Execute this SKILL.md's XML workflow **block by block in document order**. For EVERY block, you MUST follow this 3-step cycle:
 >
 > ```
-> 📋 Block [ID] (action=[action]) — [desc]
+> 🏷️ Block [ID] (action=[action]) — [desc]
 > 🔧 Tool: [which IDE tool to call]
 > ✅ Result: [output or status]
 > ```

package/.speccrew/skills/speccrew-knowledge-techs-dispatch/SKILL.md

@@ -11,7 +11,7 @@ tools: Read, Write, Task, Bash
 > **Step 2**: Execute this SKILL.md's XML workflow **block by block in document order**. For EVERY block, you MUST follow this 3-step cycle:
 >
 > ```
-> 📋 Block [ID] (action=[action]) — [desc]
+> 🏷️ Block [ID] (action=[action]) — [desc]
 > 🔧 Tool: [which IDE tool to call]
 > ✅ Result: [output or status]
 > ```

package/.speccrew/skills/speccrew-product-manager-orchestration/SKILL.md

@@ -12,7 +12,7 @@ tools: Read, Write, Glob, Grep, Bash, Agent
 > **Step 2**: Execute this SKILL.md's XML workflow **block by block in document order**. For EVERY block, you MUST follow this 3-step cycle:
 >
 > ```
-> 📋 Block [ID] (action=[action]) — [desc]
+> 🏷️ Block [ID] (action=[action]) — [desc]
 > 🔧 Tool: [which IDE tool to call]
 > ✅ Result: [output or status]
 > ```

package/.speccrew/skills/speccrew-system-deployer-orchestration/SKILL.md

@@ -12,7 +12,7 @@ tools: Read, Write, Glob, Grep, Bash
 > **Step 2**: Execute this SKILL.md's XML workflow **block by block in document order**. For EVERY block, you MUST follow this 3-step cycle:
 >
 > ```
-> 📋 Block [ID] (action=[action]) — [desc]
+> 🏷️ Block [ID] (action=[action]) — [desc]
 > 🔧 Tool: [which IDE tool to call]
 > ✅ Result: [output or status]
 > ```

package/.speccrew/skills/speccrew-system-developer-orchestration/SKILL.md

@@ -12,7 +12,7 @@ tools: Read, Write, Glob, Grep, Bash
 > **Step 2**: Execute this SKILL.md's XML workflow **block by block in document order**. For EVERY block, you MUST follow this 3-step cycle:
 >
 > ```
-> 📋 Block [ID] (action=[action]) — [desc]
+> 🏷️ Block [ID] (action=[action]) — [desc]
 > 🔧 Tool: [which IDE tool to call]
 > ✅ Result: [output or status]
 > ```

package/.speccrew/skills/speccrew-task-worker-execution/SKILL.md

@@ -12,7 +12,7 @@ tools: Read, Grep, Glob, Write, Bash, Edit, WebFetch, WebSearch
 > **Step 2**: Execute this SKILL.md's XML workflow **block by block in document order**. For EVERY block, you MUST follow this 3-step cycle:
 >
 > ```
-> 📋 Block [ID] (type=[type], action=[action]) — [desc]
+> 🏷️ Block [ID] (type=[type], action=[action]) — [desc]
 > 🔧 Tool: [which IDE tool to call]
 > ✅ Result: [output or status]
 > ```

package/.speccrew/skills/speccrew-team-leader-routing/SKILL.md

@@ -12,7 +12,7 @@ tools: Read, Write, Bash, Skill, Task
 > **Step 2**: Execute this SKILL.md's XML workflow **block by block in document order**. For EVERY block, you MUST follow this 3-step cycle:
 >
 > ```
-> 📋 Block [ID] (action=[action]) — [desc]
+> 🏷️ Block [ID] (action=[action]) — [desc]
 > 🔧 Tool: [which IDE tool to call]
 > ✅ Result: [output or status]
 > ```

package/.speccrew/skills/speccrew-test-manager-orchestration/SKILL.md

@@ -12,7 +12,7 @@ tools: Read, Write, Glob, Grep, Bash, Agent
 > **Step 2**: Execute this SKILL.md's XML workflow **block by block in document order**. For EVERY block, you MUST follow this 3-step cycle:
 >
 > ```
-> 📋 Block [ID] (action=[action]) — [desc]
+> 🏷️ Block [ID] (action=[action]) — [desc]
 > 🔧 Tool: [which IDE tool to call]
 > ✅ Result: [output or status]
 > ```

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "speccrew",
-  "version": "0.7.70",
+  "version": "0.7.72",
   "description": "Spec-Driven Development toolkit for AI-powered IDEs",
   "author": "charlesmu99",
   "repository": {

package/workspace-template/docs/rules/agentflow-spec.md

@@ -512,7 +512,7 @@ When executing an AgentFlow XML workflow, the Agent MUST strictly follow the blo
 Before executing each `<block>`, the agent MUST announce the block being executed. The announcement format is:
 
 ```
-📋 Block [{block-id}] (type={block-type}, action={action}) — {block-desc}
+🏷️ Block [{block-id}] (type={block-type}, action={action}) — {block-desc}
 ```
 
 **Rules:**