claude-code-workflow 7.2.26 → 7.2.27

package/.claude/skills/team-arch-opt/SKILL.md

@@ -78,7 +78,7 @@ Execute built-in Phase 1 (task discovery) -> role Phase 2-4 -> built-in Phase 5
 })
 ```
 
-**Inner Loop roles** (refactorer): Set `inner_loop: true`.
+**Inner Loop roles** (refactorer): Set `inner_loop` dynamically — `true` for single mode, `false` for fan-out/independent (parallel branches).
 **Single-task roles** (analyzer, designer, validator, reviewer): Set `inner_loop: false`.
 
 ## User Commands

package/.claude/skills/team-arch-opt/roles/coordinator/commands/monitor.md

@@ -82,7 +82,9 @@ Find ready tasks, spawn workers, STOP.
 2. No ready + work in progress -> report waiting, STOP
 3. No ready + nothing in progress -> handleComplete
 4. Has ready -> for each:
-   a. Check if inner loop role with active worker -> skip (worker picks up)
+   a. Check inner_loop: parse task description `InnerLoop:` field (NOT role.md default)
+      - InnerLoop: true AND same-role worker already active -> skip (worker picks up)
+      - InnerLoop: false OR no active same-role worker -> spawn new worker
    b. TaskUpdate -> in_progress
    c. team_msg log -> task_unblocked
    d. Spawn team-worker (see SKILL.md Spawn Template):

package/.claude/skills/team-arch-opt/roles/refactorer/role.md

@@ -1,12 +1,14 @@
 ---
 role: refactorer
 prefix: REFACTOR
-inner_loop: true
+inner_loop: dynamic
 message_types: [state_update]
 ---
 
 # Code Refactorer
 
+> **inner_loop: dynamic** — Dispatch sets per-task: `true` for single mode (one REFACTOR task with iterative fix cycles), `false` for fan-out/independent modes (REFACTOR-B01..N run as separate parallel workers). When false, each branch gets its own worker.
+
 Implement architecture refactoring changes following the design plan. For FIX tasks, apply targeted corrections based on review/validation feedback.
 
 ## Modes

package/.claude/skills/team-arch-opt/specs/team-config.json

@@ -64,10 +64,10 @@
       "type": "code_generation",
       "description": "Implements architecture refactoring changes following the design plan",
       "role_spec": "roles/refactorer/role.md",
-      "inner_loop": true,
+      "inner_loop": "dynamic",
       "frontmatter": {
         "prefix": "REFACTOR",
-        "inner_loop": true,
+        "inner_loop": "dynamic",
         "additional_prefixes": ["FIX"],
         "discuss_rounds": [],
         "cli_tools": ["explore"],

package/.claude/skills/team-coordinate/SKILL.md

@@ -130,9 +130,10 @@ Execute built-in Phase 1 (task discovery) -> role-spec Phase 2-4 -> built-in Pha
 })
 ```
 
-**Inner Loop roles** (role has 2+ serial same-prefix tasks): Set `inner_loop: true`. The team-worker agent handles the loop internally.
-
-**Single-task roles**: Set `inner_loop: false`.
+**Inner Loop**: Determined per-task from task description `InnerLoop:` field, not per-role:
+- Serial chain (2+ tasks, each blockedBy previous): `inner_loop: true` — single worker loops
+- Parallel tasks (no mutual blockedBy): `inner_loop: false` — separate workers per task
+- Single-task roles: `inner_loop: false`
 
 ---
 

package/.claude/skills/team-coordinate/roles/coordinator/commands/analyze-task.md

@@ -130,7 +130,7 @@ For each role, determine frontmatter and generation hints:
 | Field | Derivation |
 |-------|------------|
 | `prefix` | From capability prefix (e.g., RESEARCH, DRAFT, IMPL) |
-| `inner_loop` | `true` if role has 2+ serial same-prefix tasks |
+| `inner_loop` | `true` if role has 2+ same-prefix tasks AND they form a serial chain (each blockedBy the previous). `false` if tasks are parallel (no mutual blockedBy) or role has only 1 task |
 | `CLI tools` | Suggested, not mandatory — coordinator may adjust based on task needs |
 | `pattern_hint` | Reference pattern name from role-spec-template (research/document/code/analysis/validation) — guides coordinator's Phase 2-4 composition, NOT a rigid template selector |
 | `output_type` | `artifact` (new files in session/artifacts/) / `codebase` (modify existing project files) / `mixed` (both) — determines verification strategy in Behavioral Traits |

package/.claude/skills/team-coordinate/roles/coordinator/commands/dispatch.md

@@ -95,9 +95,10 @@ RoleSpec: <session-folder>/role-specs/<role-name>.md
 
 | Condition | InnerLoop |
 |-----------|-----------|
-| Role has 2+ serial same-prefix tasks | true |
+| Role has 2+ same-prefix tasks forming a serial chain (each blockedBy the previous) | true |
 | Role has 1 task | false |
-| Tasks are parallel (no dependency between them) | false |
+| Role has 2+ same-prefix tasks but they are parallel (no mutual blockedBy) | false |
+| Mixed: some serial, some parallel within same role | Set per-task: true for serial chain members, false for parallel members |
 
 ### Dependency Validation
 

package/.claude/skills/team-coordinate/roles/coordinator/commands/monitor.md

@@ -144,9 +144,10 @@ Ready tasks found?
   +- NONE + work in progress -> report waiting -> STOP
   +- NONE + nothing in progress -> PIPELINE_COMPLETE -> handleComplete
   +- HAS ready tasks -> for each:
-      +- Is task owner an Inner Loop role AND that role already has an active_worker?
+      +- Parse task description `InnerLoop:` field (NOT session.roles[].inner_loop)
+      +- InnerLoop: true AND same-role worker already in active_workers?
       |   +- YES -> SKIP spawn (existing worker will pick it up via inner loop)
-      |   +- NO -> normal spawn below
+      |   +- NO -> normal spawn below (InnerLoop: false OR no active same-role worker)
       +- TaskUpdate -> in_progress
       +- team_msg log -> task_unblocked (session_id=<session-id>)
       +- Spawn team-worker (see spawn tool call below)

package/.claude/skills/team-coordinate/roles/coordinator/role.md

@@ -207,15 +207,9 @@ Regardless of complexity score or role count, coordinator MUST:
    - `project_root` = result of `Bash({ command: "pwd" })`
    - `skill_root` = `<project_root>/.claude/skills/team-coordinate`
 
-2. **Check `needs_research` flag** from task-analysis.json:
-   - If `true`: **Spawn researcher worker first** to gather codebase context
-     - Wait for researcher callback
-     - Merge research findings into task context
-     - Update task-analysis.json with enriched context
+2. **Generate session ID**: `TC-<slug>-<date>` (slug from first 3 meaningful words of task)
 
-3. **Generate session ID**: `TC-<slug>-<date>` (slug from first 3 meaningful words of task)
-
-4. **Create session folder structure**:
+3. **Create session folder structure**:
    ```
    .workflow/.team/<session-id>/
    +-- role-specs/
@@ -226,11 +220,11 @@ Regardless of complexity score or role count, coordinator MUST:
    +-- .msg/
    ```
 
-5. **Call TeamCreate** with team name derived from session ID
+4. **Call TeamCreate** with team name derived from session ID
 
-6. **Read `specs/role-spec-template.md`** for Behavioral Traits + Reference Patterns
+5. **Read `specs/role-spec-template.md`** for Behavioral Traits + Reference Patterns
 
-7. **For each role in task-analysis.json#roles**:
+6. **For each role in task-analysis.json#roles**:
    - Fill YAML frontmatter: role, prefix, inner_loop, additional_members, message_types
    - **Compose Phase 2-4 content** (NOT copy from template):
      - Phase 2: Derive input sources and context loading steps from **task description + upstream dependencies**
@@ -239,14 +233,14 @@ Regardless of complexity score or role count, coordinator MUST:
      - Reference Patterns may guide phase structure, but task description determines specific content
    - Write generated role-spec to `<session>/role-specs/<role-name>.md`
 
-8. **Register roles** in team-session.json#roles (with `role_spec` path instead of `role_file`)
+7. **Register roles** in team-session.json#roles (with `role_spec` path instead of `role_file`)
 
-9. **Initialize shared infrastructure**:
+8. **Initialize shared infrastructure**:
    - `wisdom/learnings.md`, `wisdom/decisions.md`, `wisdom/issues.md` (empty with headers)
    - `explorations/cache-index.json` (`{ "entries": [] }`)
    - `discussions/` (empty directory)
 
-10. **Initialize pipeline metadata** via team_msg:
+9. **Initialize pipeline metadata** via team_msg:
 ```typescript
 // 使用 team_msg 将 pipeline 元数据写入 .msg/meta.json
 // 注意: 此处为动态角色，执行时需将 <placeholders> 替换为 task-analysis.json 中生成的实际角色列表
@@ -265,7 +259,14 @@ mcp__ccw-tools__team_msg({
 })
 ```
 
-11. **Write team-session.json** with: session_id, task_description, status="active", roles, pipeline (empty), active_workers=[], completion_action="interactive", created_at
+10. **Write team-session.json** with: session_id, task_description, status="active", roles, pipeline (empty), active_workers=[], completion_action="interactive", created_at
+
+11. **Check `needs_research` flag** from task-analysis.json:
+    - If `true`: Spawn researcher worker (role-spec now exists from step 6) to gather codebase context
+      - Wait for researcher callback
+      - Merge research findings into task context
+      - Update task-analysis.json with enriched context
+    - If `false`: Skip, proceed to Phase 3
 
 **Success**: Session created, role-spec files generated, shared infrastructure initialized.
 

package/.claude/skills/team-coordinate/specs/pipelines.md

@@ -38,18 +38,20 @@ Phase 3-N: monitor.md
 
 ## Dependency Graph Structure
 
-task-analysis.json encodes the pipeline:
+task-analysis.json encodes the pipeline as adjacency list (task ID -> blockedBy array):
 
 ```json
 {
   "dependency_graph": {
-    "RESEARCH-001": { "role": "researcher", "blockedBy": [], "priority": "P0" },
-    "IMPL-001":     { "role": "developer",  "blockedBy": ["RESEARCH-001"], "priority": "P1" },
-    "TEST-001":     { "role": "tester",     "blockedBy": ["IMPL-001"], "priority": "P2" }
+    "RESEARCH-001": [],
+    "IMPL-001": ["RESEARCH-001"],
+    "TEST-001": ["IMPL-001"]
   }
 }
 ```
 
+Role mapping comes from `task-analysis.json#capabilities[].tasks[]`, not from the dependency graph itself.
+
 ## Role-Worker Map
 
 Dynamic — loaded from session role-specs at runtime:
@@ -64,6 +66,7 @@ Role-spec files contain YAML frontmatter:
 role: <role-name>
 prefix: <PREFIX>
 inner_loop: <true|false>
+output_tag: "[<role-name>]"
 message_types:
   success: <type>
   error: error

package/.claude/skills/team-coordinate/specs/role-spec-template.md

@@ -11,6 +11,7 @@ Template used by coordinator to generate lightweight worker role-spec files at r
 role: <role_name>
 prefix: <PREFIX>
 inner_loop: <true|false>
+output_tag: "[<role_name>]"
 CLI tools: [<CLI tool-names>]
 message_types:
   success: <prefix>_complete

package/.claude/skills/team-lifecycle-v4/SKILL.md

@@ -40,7 +40,7 @@ Skill(skill="team-lifecycle-v4", args="task description")
 | analyst | [roles/analyst/role.md](roles/analyst/role.md) | RESEARCH-* | false |
 | writer | [roles/writer/role.md](roles/writer/role.md) | DRAFT-* | true |
 | planner | [roles/planner/role.md](roles/planner/role.md) | PLAN-* | true |
-| executor | [roles/executor/role.md](roles/executor/role.md) | IMPL-* | true |
+| executor | [roles/executor/role.md](roles/executor/role.md) | IMPL-* | dynamic |
 | tester | [roles/tester/role.md](roles/tester/role.md) | TEST-* | false |
 | reviewer | [roles/reviewer/role.md](roles/reviewer/role.md) | REVIEW-*, QUALITY-*, IMPROVE-* | false |
 | supervisor | [roles/supervisor/role.md](roles/supervisor/role.md) | CHECKPOINT-* | false |

package/.claude/skills/team-lifecycle-v4/roles/coordinator/commands/dispatch.md

@@ -34,8 +34,20 @@ RoleSpec: ~  or <project>/.claude/skills/team-lifecycle-v4/roles/<role>/role.md
 
 ## InnerLoop Flag Rules
 
-- true: Role has 2+ serial same-prefix tasks (writer: DRAFT-001->004)
-- false: Role has 1 task, or tasks are parallel
+- true: Role has 2+ serial same-prefix tasks (writer: DRAFT-001->004) where each blockedBy the previous
+- false: Role has 1 task, or tasks are parallel (no mutual blockedBy)
+
+### Parallel Detection for IMPL Tasks
+
+When creating IMPL-{1..N} tasks from PLAN-001 output:
+
+1. Read plan.json → extract `tasks[]` with their `depends_on` fields
+2. Build dependency graph among IMPL tasks only
+3. Classify:
+   - **Serial chain**: IMPL-002 blockedBy IMPL-001 → both get `InnerLoop: true`, single worker
+   - **Parallel set**: IMPL-001..N all blockedBy PLAN-001 only (no mutual deps) → each gets `InnerLoop: false`, separate workers
+   - **Mixed DAG**: Some parallel, some serial → group into independent chains, each chain gets one worker with `InnerLoop: true`; independent chains spawn in parallel
+4. Set `InnerLoop` in each task description accordingly
 
 ## CHECKPOINT Task Rules
 

package/.claude/skills/team-lifecycle-v4/roles/coordinator/commands/monitor.md

@@ -36,9 +36,29 @@ Worker completed. Process and advance.
    - CHECKPOINT-* with verdict "warn" -> log risks to wisdom, proceed normally
    - CHECKPOINT-* with verdict "pass" -> proceed normally
    - QUALITY-001 -> display quality gate, pause for user commands
-   - PLAN-001 -> read plan.json complexity, create dynamic IMPL tasks per specs/pipelines.md routing
+   - PLAN-001 -> dynamicImplDispatch (see below)
 6. -> handleSpawnNext
 
+### dynamicImplDispatch (PLAN-001 callback)
+
+When PLAN-001 completes, coordinator creates IMPL tasks based on complexity:
+
+1. Read `<session>/plan/plan.json` → extract `complexity`, `tasks[]`
+2. Route by complexity (per specs/pipelines.md §6):
+
+| Complexity | Action |
+|------------|--------|
+| Low (1-2 modules) | Create single IMPL-001, blockedBy: [PLAN-001], InnerLoop: true |
+| Medium (3-4 modules) | Create IMPL-{1..N}, each blockedBy: [PLAN-001] only, InnerLoop: false |
+| High (5+ modules) | Create IMPL-{1..N} with DAG deps from plan.json, InnerLoop per dispatch rules |
+
+3. For each IMPL task: TaskCreate with structured description (dispatch.md template)
+4. Set blockedBy:
+   - **Parallel tasks**: blockedBy: [PLAN-001] (or [CHECKPOINT-003] if supervision enabled)
+   - **Serial chain within DAG**: blockedBy includes upstream IMPL task IDs
+5. Update team-session.json: `pipeline.tasks_total`, `pipeline.impl_topology: "single"|"parallel"|"dag"`
+6. Log via team_msg: `{ type: "state_update", data: { impl_count: N, topology: "..." } }`
+
 ## handleCheck
 
 Read-only status report, then STOP.
@@ -71,7 +91,9 @@ Find ready tasks, spawn workers, STOP.
 2. No ready + work in progress -> report waiting, STOP
 3. No ready + nothing in progress -> handleComplete
 4. Has ready -> for each:
-   a. Check if inner loop role with active worker -> skip (worker picks up)
+   a. Check inner_loop: parse task description `InnerLoop:` field (NOT role.md default)
+      - InnerLoop: true AND same-role worker already active -> skip (worker picks up next task)
+      - InnerLoop: false OR no active same-role worker -> spawn new worker
    b. **CHECKPOINT-* task** -> wake resident supervisor (see below)
    c. Other tasks -> standard spawn:
       - TaskUpdate -> in_progress

package/.claude/skills/team-lifecycle-v4/roles/executor/role.md

@@ -1,7 +1,7 @@
 ---
 role: executor
 prefix: IMPL
-inner_loop: true
+inner_loop: dynamic
 message_types:
   success: impl_complete
   progress: impl_progress
@@ -12,6 +12,8 @@ message_types:
 
 Code implementation worker with dual execution modes.
 
+> **inner_loop: dynamic** — Dispatch sets per-task: `true` for serial IMPL chains (IMPL-001→002→003 with inter-dependencies), `false` for parallel IMPL sets (independent modules). When false, each IMPL task gets its own worker.
+
 ## Identity
 - Tag: [executor] | Prefix: IMPL-*
 - Responsibility: Implement code from plan tasks via agent or CLI delegation

package/.claude/skills/team-perf-opt/SKILL.md

@@ -90,7 +90,7 @@ Execute built-in Phase 1 (task discovery) -> role Phase 2-4 -> built-in Phase 5
 })
 ```
 
-**Inner Loop roles** (optimizer): Set `inner_loop: true`.
+**Inner Loop roles** (optimizer): Set `inner_loop` dynamically — `true` for single mode, `false` for fan-out/independent (parallel branches).
 **Single-task roles** (profiler, strategist, benchmarker, reviewer): Set `inner_loop: false`.
 
 ## User Commands

package/.claude/skills/team-perf-opt/roles/optimizer/role.md

@@ -1,7 +1,7 @@
 ---
 role: optimizer
 prefix: IMPL
-inner_loop: true
+inner_loop: dynamic
 additional_prefixes: [FIX]
 message_types:
   success: impl_complete
@@ -11,6 +11,8 @@ message_types:
 
 # Code Optimizer
 
+> **inner_loop: dynamic** — Dispatch sets per-task: `true` for single mode (one IMPL task with iterative fix cycles), `false` for fan-out/independent modes (IMPL-B01..N run as separate parallel workers). When false, each branch gets its own worker.
+
 Implement optimization changes following the strategy plan. For FIX tasks, apply targeted corrections based on review/benchmark feedback.
 
 ## Modes

package/.claude/skills/team-perf-opt/specs/team-config.json

@@ -65,10 +65,10 @@
       "type": "code_generation",
       "description": "Implements optimization changes following the strategy plan",
       "role_spec": "roles/optimizer/role.md",
-      "inner_loop": true,
+      "inner_loop": "dynamic",
       "frontmatter": {
         "prefix": "IMPL",
-        "inner_loop": true,
+        "inner_loop": "dynamic",
         "additional_prefixes": ["FIX"],
         "discuss_rounds": [],
         "delegates_to": [],

package/.claude/skills/team-quality-assurance/SKILL.md

@@ -38,7 +38,7 @@ Skill(skill="team-quality-assurance", args="task description")
 | scout | [roles/scout/role.md](roles/scout/role.md) | SCOUT-* | false |
 | strategist | [roles/strategist/role.md](roles/strategist/role.md) | QASTRAT-* | false |
 | generator | [roles/generator/role.md](roles/generator/role.md) | QAGEN-* | false |
-| executor | [roles/executor/role.md](roles/executor/role.md) | QARUN-* | true |
+| executor | [roles/executor/role.md](roles/executor/role.md) | QARUN-* | dynamic |
 | analyst | [roles/analyst/role.md](roles/analyst/role.md) | QAANA-* | false |
 
 ## Role Router

package/.claude/skills/team-quality-assurance/roles/coordinator/commands/dispatch.md

@@ -87,8 +87,10 @@ SCOUT-002 (scout): Regression scan after fixes
 
 ## InnerLoop Flag Rules
 
-- true: executor roles (run-fix cycles)
-- false: scout, strategist, generator, analyst roles
+- **executor**: dynamic per pipeline mode:
+  - Discovery/Testing: `true` (serial layer chain, single executor handles GC loops)
+  - Full: `false` for parallel QARUN tasks (QARUN-L1-001 and QARUN-L2-001 have independent blockedBy, each gets own worker)
+- **scout, strategist, generator, analyst**: always false
 
 ## Dependency Validation
 

package/.claude/skills/team-quality-assurance/roles/coordinator/commands/monitor.md

@@ -132,10 +132,12 @@ Find ready tasks, spawn workers, STOP.
 | SCOUT-* | scout | false |
 | QASTRAT-* | strategist | false |
 | QAGEN-* | generator | false |
-| QARUN-* | executor | true |
+| QARUN-* | executor | dynamic |
 | QAANA-* | analyst | false |
 
-   b. Check if inner loop role with active worker -> skip (worker picks up next task)
+   b. Check inner_loop: parse task description `InnerLoop:` field (NOT role.md default)
+      - InnerLoop: true AND same-role worker already active -> skip (worker picks up next task)
+      - InnerLoop: false OR no active same-role worker -> spawn new worker
    c. TaskUpdate -> in_progress
    d. team_msg log -> task_unblocked
    e. Spawn team-worker:

package/.claude/skills/team-quality-assurance/roles/executor/role.md

@@ -1,7 +1,7 @@
 ---
 role: executor
 prefix: QARUN
-inner_loop: true
+inner_loop: dynamic
 additional_prefixes: [QARUN-gc]
 message_types:
   success: tests_passed
@@ -12,6 +12,8 @@ message_types:
 
 # Test Executor
 
+> **inner_loop: dynamic** — Dispatch sets per-task: `true` for serial layer chains (discovery/testing mode), `false` for parallel layer execution (full mode where QARUN-L1-001 and QARUN-L2-001 run independently). When false, each QARUN task gets its own worker.
+
 Run test suites, collect coverage data, and perform automatic fix cycles when tests fail. Implements the execution side of the Generator-Executor (GC) loop.
 
 ## Phase 2: Environment Detection

package/.claude/skills/team-testing/SKILL.md

@@ -37,7 +37,7 @@ Skill(skill="team-testing", args="task description")
 | coordinator | [roles/coordinator/role.md](roles/coordinator/role.md) | — | — |
 | strategist | [roles/strategist/role.md](roles/strategist/role.md) | STRATEGY-* | false |
 | generator | [roles/generator/role.md](roles/generator/role.md) | TESTGEN-* | true |
-| executor | [roles/executor/role.md](roles/executor/role.md) | TESTRUN-* | true |
+| executor | [roles/executor/role.md](roles/executor/role.md) | TESTRUN-* | dynamic |
 | analyst | [roles/analyst/role.md](roles/analyst/role.md) | TESTANA-* | false |
 
 ## Role Router

package/.claude/skills/team-testing/roles/coordinator/commands/dispatch.md

@@ -84,8 +84,11 @@ TESTANA-001 (analyst): Defect pattern analysis, quality report
 
 ## InnerLoop Flag Rules
 
-- true: generator, executor roles (GC loop iterations)
-- false: strategist, analyst roles
+- **generator**: always true (GC loop iterations within a single layer)
+- **executor**: dynamic per pipeline mode:
+  - Targeted/Standard: `true` (serial layer chain, single executor handles GC loops)
+  - Comprehensive: `false` for parallel TESTRUN tasks (TESTRUN-001 and TESTRUN-002 have independent blockedBy, each gets own worker)
+- **strategist, analyst**: always false
 
 ## Dependency Validation
 

package/.claude/skills/team-testing/roles/coordinator/commands/monitor.md

@@ -27,7 +27,7 @@ Event-driven pipeline coordination. Beat model: coordinator wake -> process -> s
 |--------|------|-----------|------------|
 | STRATEGY-* | strategist | `~  or <project>/.claude/skills/team-testing/roles/strategist/role.md` | false |
 | TESTGEN-* | generator | `~  or <project>/.claude/skills/team-testing/roles/generator/role.md` | true |
-| TESTRUN-* | executor | `~  or <project>/.claude/skills/team-testing/roles/executor/role.md` | true |
+| TESTRUN-* | executor | `~  or <project>/.claude/skills/team-testing/roles/executor/role.md` | dynamic |
 | TESTANA-* | analyst | `~  or <project>/.claude/skills/team-testing/roles/analyst/role.md` | false |
 
 ## handleCallback
@@ -136,7 +136,9 @@ Find ready tasks, spawn workers, STOP.
 3. No ready + nothing in progress -> handleComplete
 4. Has ready -> for each ready task:
    a. Determine role from prefix (use Role-Worker Map)
-   b. Check if inner loop role (generator/executor) with active worker -> skip (worker picks up next task)
+   b. Check inner_loop: parse task description `InnerLoop:` field (NOT role.md default)
+      - InnerLoop: true AND same-role worker already active -> skip (worker picks up next task)
+      - InnerLoop: false OR no active same-role worker -> spawn new worker
    c. TaskUpdate -> in_progress
    d. team_msg log -> task_unblocked
    e. Spawn team-worker:

package/.claude/skills/team-testing/roles/executor/role.md

@@ -1,7 +1,7 @@
 ---
 role: executor
 prefix: TESTRUN
-inner_loop: true
+inner_loop: dynamic
 message_types:
   success: tests_passed
   failure: tests_failed
@@ -11,6 +11,8 @@ message_types:
 
 # Test Executor
 
+> **inner_loop: dynamic** — Dispatch sets per-task: `true` for serial GC loops (single layer pipeline), `false` for parallel layer execution (comprehensive pipeline where TESTRUN-001 and TESTRUN-002 run independently). When false, each TESTRUN task gets its own worker.
+
 Execute tests, collect coverage, attempt auto-fix for failures. Acts as the Critic in the Generator-Critic loop. Reports pass rate and coverage for coordinator GC decisions.
 
 ## Phase 2: Context Loading

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "claude-code-workflow",
-  "version": "7.2.26",
+  "version": "7.2.27",
   "description": "JSON-driven multi-agent development framework with intelligent CLI orchestration (Gemini/Qwen/Codex), context-first architecture, and automated workflow execution",
   "type": "module",
   "main": "ccw/dist/index.js",