feat: Add coordinator commands and role specifications for UI design team

- Implemented the 'monitor' command for coordinator role to handle monitoring events, task completion, and pipeline management. - Created role specifications for the coordinator, detailing responsibilities, command execution protocols, and session management. - Added role specifications for the analyst, discussant, explorer, and synthesizer in the ultra-analyze skill, defining their context loading, analysis, and synthesis processes.
2026-03-06 16:31:12 +08:00 · 2026-03-03 23:35:41 +08:00
parent a7ed0365f7
commit 26bda9c634
188 changed files with 9332 additions and 3512 deletions
--- a/.claude/skills/team-tech-debt/roles/assessor/role.md
+++ b/.claude/skills/team-tech-debt/roles/assessor/role.md
@@ -58,11 +58,9 @@ Before every SendMessage, log via `mcp__ccw-tools__team_msg`:
 ```
 mcp__ccw-tools__team_msg({
  operation: "log",
-  team: <session-id>,  // MUST be session ID (e.g., TD-xxx-date), NOT team name. Extract from Session: field in task description.
+  session_id: <session-id>,
  from: "assessor",
-  to: "coordinator",
  type: <message-type>,
-  summary: "[assessor] <task-prefix> complete: <task-subject>",
  ref: <artifact-path>
 })
 ```
@@ -70,7 +68,7 @@ mcp__ccw-tools__team_msg({
 **CLI fallback** (when MCP unavailable):

 ```
-Bash("ccw team log --team <session-id> --from assessor --to coordinator --type <message-type> --summary \"[assessor] ...\" --ref <artifact-path> --json")
+Bash("ccw team log --session-id <session-id> --from assessor --type <message-type> --ref <artifact-path> --json")
 ```

 ---
@@ -88,13 +86,13 @@ Standard task discovery flow: TaskList -> filter by prefix `TDEVAL-*` + owner ma
 | Input | Source | Required |
 |-------|--------|----------|
 | Session folder | task.description (regex: `session:\s*(.+)`) | Yes |
-| Shared memory | `<session-folder>/shared-memory.json` | Yes |
-| Debt inventory | shared-memory.debt_inventory OR `<session-folder>/scan/debt-inventory.json` | Yes |
+| Shared memory | `<session-folder>/.msg/meta.json` | Yes |
+| Debt inventory | meta.json:debt_inventory OR `<session-folder>/scan/debt-inventory.json` | Yes |

 **Loading steps**:

 1. Extract session path from task description
-2. Read shared-memory.json
+2. Read .msg/meta.json
 3. Load debt_inventory from shared memory or fallback to debt-inventory.json file
 4. If debt_inventory is empty -> report empty assessment and exit

@@ -156,7 +154,7 @@ Delegate to `commands/evaluate.md` if available, otherwise execute inline.
 **Save outputs**:

 1. Write `<session-folder>/assessment/priority-matrix.json`
-2. Update shared-memory.json with `priority_matrix` summary and evaluated `debt_inventory`
+2. Update .msg/meta.json with `priority_matrix` summary and evaluated `debt_inventory`

 ### Phase 5: Report to Coordinator

--- a/.claude/skills/team-tech-debt/roles/coordinator/commands/dispatch.md
+++ b/.claude/skills/team-tech-debt/roles/coordinator/commands/dispatch.md
@@ -102,9 +102,8 @@ const chainValid = chainTasks.length === pipeline.length

 if (!chainValid) {
  mcp__ccw-tools__team_msg({
-    operation: "log", team: sessionId, from: "coordinator",  // team must be session ID (e.g., TD-xxx-date), NOT team name
-    to: "user", type: "error",
-    summary: `[coordinator] 任务链创建不完整: ${chainTasks.length}/${pipeline.length}`
+    operation: "log", session_id: sessionId, from: "coordinator",  // team must be session ID (e.g., TD-xxx-date), NOT team name
+    type: "error",
  })
 }
 ```
--- a/.claude/skills/team-tech-debt/roles/coordinator/commands/monitor.md
+++ b/.claude/skills/team-tech-debt/roles/coordinator/commands/monitor.md
@@ -47,7 +47,7 @@ const STAGE_WORKER_MAP = {
 ### Step 1: Context Preparation

 ```javascript
-const sharedMemory = JSON.parse(Read(`${sessionFolder}/shared-memory.json`))
+const sharedMemory = JSON.parse(Read(`${sessionFolder}/.msg/meta.json`))

 let fixVerifyIteration = 0
 const MAX_FIX_VERIFY_ITERATIONS = 3
@@ -76,9 +76,8 @@ for (const stageTask of pipelineTasks) {

  if (!workerConfig) {
    mcp__ccw-tools__team_msg({
-      operation: "log", team: sessionId  // MUST be session ID (e.g., TD-xxx-date), NOT team name, from: "coordinator",
-      to: "user", type: "error",
-      summary: `[coordinator] 未知阶段前缀: ${stagePrefix}，跳过`
+      operation: "log", session_id: sessionId, from: "coordinator",
+      type: "error",
    })
    continue
  }
@@ -87,15 +86,14 @@ for (const stageTask of pipelineTasks) {
  TaskUpdate({ taskId: stageTask.id, status: 'in_progress' })

  mcp__ccw-tools__team_msg({
-    operation: "log", team: sessionId  // MUST be session ID (e.g., TD-xxx-date), NOT team name, from: "coordinator",
+    operation: "log", session_id: sessionId, from: "coordinator",
    to: workerConfig.role, type: "task_unblocked",
-    summary: `[coordinator] 启动阶段: ${stageTask.subject} → ${workerConfig.role}`
  })

  // 3. 同步 spawn worker — 阻塞直到 worker 返回（Stop-Wait 核心）
  //    Task() 本身就是等待机制，无需 sleep/poll
  const workerResult = Task({
-    subagent_type: "general-purpose",
+    subagent_type: "team-worker",
    description: `Spawn ${workerConfig.role} worker for ${stageTask.subject}`,
    team_name: teamName,
    name: workerConfig.role,
@@ -111,9 +109,8 @@ for (const stageTask of pipelineTasks) {
    handleStageFailure(stageTask, taskState, workerConfig, autoYes)
  } else {
    mcp__ccw-tools__team_msg({
-      operation: "log", team: sessionId  // MUST be session ID (e.g., TD-xxx-date), NOT team name, from: "coordinator",
-      to: "user", type: "quality_gate",
-      summary: `[coordinator] 阶段完成: ${stageTask.subject}`
+      operation: "log", session_id: sessionId, from: "coordinator",
+      type: "quality_gate",
    })
  }

@@ -127,9 +124,8 @@ for (const stageTask of pipelineTasks) {
    }

    mcp__ccw-tools__team_msg({
-      operation: "log", team: sessionId  // MUST be session ID (e.g., TD-xxx-date), NOT team name, from: "coordinator",
-      to: "user", type: "plan_approval",
-      summary: `[coordinator] 治理方案已生成，等待审批`
+      operation: "log", session_id: sessionId, from: "coordinator",
+      type: "plan_approval",
    })

    if (!autoYes) {
@@ -166,9 +162,8 @@ for (const stageTask of pipelineTasks) {
        continue  // 跳到下一阶段（即刚插入的修订任务）
      } else if (planDecision === "终止") {
        mcp__ccw-tools__team_msg({
-          operation: "log", team: sessionId  // MUST be session ID (e.g., TD-xxx-date), NOT team name, from: "coordinator",
-          to: "user", type: "shutdown",
-          summary: `[coordinator] 用户终止流水线（方案审批阶段）`
+          operation: "log", session_id: sessionId, from: "coordinator",
+          type: "shutdown",
        })
        break  // 退出 pipeline 循环
      }
@@ -189,14 +184,13 @@ for (const stageTask of pipelineTasks) {

    // 存入 shared memory
    sharedMemory.worktree = { path: worktreePath, branch: branchName }
-    Write(`${sessionFolder}/shared-memory.json`, JSON.stringify(sharedMemory, null, 2))
+    Write(`${sessionFolder}/.msg/meta.json`, JSON.stringify(sharedMemory, null, 2))

    worktreeCreated = true

    mcp__ccw-tools__team_msg({
-      operation: "log", team: sessionId  // MUST be session ID (e.g., TD-xxx-date), NOT team name, from: "coordinator",
-      to: "user", type: "worktree_created",
-      summary: `[coordinator] Worktree 已创建: ${worktreePath} (branch: ${branchName})`
+      operation: "log", session_id: sessionId, from: "coordinator",
+      type: "worktree_created",
    })
  }

@@ -231,32 +225,22 @@ function buildWorkerPrompt(stageTask, workerConfig, sessionFolder, taskDescripti
 - 禁止在主工作树中修改任何文件`
  }

-  return `你是 team "${teamName}" 的 ${workerConfig.role.toUpperCase()}。
+  return `## Role Assignment
+role: ${workerConfig.role}
+role_spec: .claude/skills/team-tech-debt/role-specs/${workerConfig.role}.md
+session: ${sessionFolder}
+session_id: ${sessionId}
+team_name: ${teamName}
+requirement: ${stageTask.description || taskDescription}
+inner_loop: false

-## ⚠️ 首要指令（MUST）
-你的所有工作必须通过调用 Skill 获取角色定义后执行，禁止自行发挥：
-Skill(skill="team-tech-debt", args="${workerConfig.skillArgs}")
-此调用会加载你的角色定义（role.md）、可用命令（commands/*.md）和完整执行逻辑。
-
-## 当前任务
- 任务 ID: ${stageTask.id}
- 任务: ${stageTask.subject}
- 描述: ${stageTask.description || taskDescription}
- Session: ${sessionFolder}
+## Current Task
+- Task ID: ${stageTask.id}
+- Task: ${stageTask.subject}
+- Task Prefix: ${stagePrefix}
 ${worktreeSection}
-## 角色准则（强制）
- 你只能处理 ${stagePrefix}-* 前缀的任务
- 所有输出必须带 [${workerConfig.role}] 标识前缀
- 仅与 coordinator 通信，不得直接联系其他 worker
-
-## 消息总线（必须）
-每次 SendMessage 前，先调用 mcp__ccw-tools__team_msg 记录。
-
-## 工作流程（严格按顺序）
-1. 调用 Skill(skill="team-tech-debt", args="${workerConfig.skillArgs}") 获取角色定义和执行逻辑
-2. 按 role.md 中的 5-Phase 流程执行
-3. team_msg log + SendMessage 结果给 coordinator
-4. TaskUpdate({ taskId: "${stageTask.id}", status: "completed" })`
+Read role_spec file to load Phase 2-4 domain instructions.
+Execute built-in Phase 1 -> role-spec Phase 2-4 -> built-in Phase 5.`
 }
 ```

@@ -266,9 +250,8 @@ ${worktreeSection}
 function handleStageFailure(stageTask, taskState, workerConfig, autoYes) {
  if (autoYes) {
    mcp__ccw-tools__team_msg({
-      operation: "log", team: sessionId  // MUST be session ID (e.g., TD-xxx-date), NOT team name, from: "coordinator",
-      to: "user", type: "error",
-      summary: `[coordinator] [auto] 阶段 ${stageTask.subject} 未完成 (status=${taskState.status})，自动跳过`
+      operation: "log", session_id: sessionId, from: "coordinator",
+      type: "error",
    })
    TaskUpdate({ taskId: stageTask.id, status: 'deleted' })
    return 'skip'
@@ -292,7 +275,7 @@ function handleStageFailure(stageTask, taskState, workerConfig, autoYes) {
    // 重新 spawn worker（递归单次）
    TaskUpdate({ taskId: stageTask.id, status: 'in_progress' })
    const retryResult = Task({
-      subagent_type: "general-purpose",
+      subagent_type: "team-worker",
      description: `Retry ${workerConfig.role} worker for ${stageTask.subject}`,
      team_name: teamName,
      name: workerConfig.role,
@@ -309,9 +292,8 @@ function handleStageFailure(stageTask, taskState, workerConfig, autoYes) {
    return 'skip'
  } else {
    mcp__ccw-tools__team_msg({
-      operation: "log", team: sessionId  // MUST be session ID (e.g., TD-xxx-date), NOT team name, from: "coordinator",
-      to: "user", type: "shutdown",
-      summary: `[coordinator] 用户终止流水线，当前阶段: ${stageTask.subject}`
+      operation: "log", session_id: sessionId, from: "coordinator",
+      type: "shutdown",
    })
    return 'abort'
  }
@@ -322,7 +304,7 @@ function handleStageFailure(stageTask, taskState, workerConfig, autoYes) {

 ```javascript
 function evaluateValidationResult(sessionFolder) {
-  const latestMemory = JSON.parse(Read(`${sessionFolder}/shared-memory.json`))
+  const latestMemory = JSON.parse(Read(`${sessionFolder}/.msg/meta.json`))
  const debtBefore = latestMemory.debt_score_before || 0
  const debtAfter = latestMemory.debt_score_after || 0
  const regressions = latestMemory.validation_results?.regressions || 0
@@ -333,9 +315,8 @@ function evaluateValidationResult(sessionFolder) {
  else if (!improved) status = 'CONDITIONAL'

  mcp__ccw-tools__team_msg({
-    operation: "log", team: sessionId  // MUST be session ID (e.g., TD-xxx-date), NOT team name, from: "coordinator",
-    to: "user", type: "quality_gate",
-    summary: `[coordinator] 质量门控: ${status} (债务分 ${debtBefore} → ${debtAfter}, 回归 ${regressions})`
+    operation: "log", session_id: sessionId, from: "coordinator",
+    type: "quality_gate",
  })

  return regressions > 0
@@ -346,7 +327,7 @@ function evaluateValidationResult(sessionFolder) {

 ```javascript
 // 汇总所有结果
-const finalSharedMemory = JSON.parse(Read(`${sessionFolder}/shared-memory.json`))
+const finalSharedMemory = JSON.parse(Read(`${sessionFolder}/.msg/meta.json`))
 const allFinalTasks = TaskList()
 const workerTasks = allFinalTasks.filter(t => t.owner && t.owner !== 'coordinator')

@@ -387,18 +368,16 @@ EOF
 )"`)

  mcp__ccw-tools__team_msg({
-    operation: "log", team: sessionId  // MUST be session ID (e.g., TD-xxx-date), NOT team name, from: "coordinator",
-    to: "user", type: "pr_created",
-    summary: `[coordinator] PR 已创建: branch ${branch}`
+    operation: "log", session_id: sessionId, from: "coordinator",
+    type: "pr_created",
  })

  // Cleanup worktree
  Bash(`git worktree remove "${wtPath}" 2>/dev/null || true`)
 } else if (finalSharedMemory.worktree && !finalSharedMemory.validation_results?.passed) {
  mcp__ccw-tools__team_msg({
-    operation: "log", team: sessionId  // MUST be session ID (e.g., TD-xxx-date), NOT team name, from: "coordinator",
-    to: "user", type: "quality_gate",
-    summary: `[coordinator] 验证未通过，worktree 保留于 ${finalSharedMemory.worktree.path}，请手动检查`
+    operation: "log", session_id: sessionId, from: "coordinator",
+    type: "quality_gate",
  })
 }

--- a/.claude/skills/team-tech-debt/roles/coordinator/role.md
+++ b/.claude/skills/team-tech-debt/roles/coordinator/role.md
@@ -29,18 +29,56 @@

 ---

+## Command Execution Protocol
+
+When coordinator needs to execute a command (dispatch, monitor):
+
+1. **Read the command file**: `roles/coordinator/commands/<command-name>.md`
+2. **Follow the workflow** defined in the command file (Phase 2-4 structure)
+3. **Commands are inline execution guides** -- NOT separate agents or subprocesses
+4. **Execute synchronously** -- complete the command workflow before proceeding
+
+Example:
+```
+Phase 3 needs task dispatch
+  -> Read roles/coordinator/commands/dispatch.md
+  -> Execute Phase 2 (Context Loading)
+  -> Execute Phase 3 (Task Chain Creation)
+  -> Execute Phase 4 (Validation)
+  -> Continue to Phase 4
+```
+
+---
+
 ## Entry Router

-When coordinator is invoked, first detect the invocation type:
+When coordinator is invoked, detect invocation type:

 | Detection | Condition | Handler |
 |-----------|-----------|---------|
-| Worker callback | Message contains `[role-name]` tag from a known worker role | -> handleCallback: auto-advance pipeline |
-| Status check | Arguments contain "check" or "status" | -> handleCheck: output execution graph, no advancement |
-| Manual resume | Arguments contain "resume" or "continue" | -> handleResume: check worker states, advance pipeline |
-| New session | None of the above | -> Phase 0 (Session Resume Check) |
+| Worker callback | Message contains role tag [scanner], [assessor], [planner], [executor], [validator] | -> handleCallback |
+| Status check | Arguments contain "check" or "status" | -> handleCheck |
+| Manual resume | Arguments contain "resume" or "continue" | -> handleResume |
+| Pipeline complete | All tasks have status "completed" | -> handleComplete |
+| Interrupted session | Active/paused session exists | -> Phase 0 (Session Resume Check) |
+| New session | None of above | -> Phase 1 |

-For callback/check/resume: load `commands/monitor.md` and execute the appropriate handler, then STOP.
+For callback/check/resume/complete: load `commands/monitor.md` and execute matched handler, then STOP.
+
+### Router Implementation
+
+1. **Load session context** (if exists):
+   - Scan `.workflow/.team/TD-*/.msg/meta.json` for active/paused sessions
+   - If found, extract session folder path, status, and pipeline mode
+
+2. **Parse $ARGUMENTS** for detection keywords:
+   - Check for role name tags in message content
+   - Check for "check", "status", "resume", "continue" keywords
+
+3. **Route to handler**:
+   - For monitor handlers: Read `commands/monitor.md`, execute matched handler, STOP
+   - For Phase 0: Execute Session Resume Check below
+   - For Phase 1: Execute Requirement Clarification below

 ---

@@ -86,11 +124,9 @@ Before every SendMessage, log via `mcp__ccw-tools__team_msg`:
 ```
 mcp__ccw-tools__team_msg({
  operation: "log",
-  team: <session-id>,  // MUST be session ID (e.g., TD-xxx-date), NOT team name. Extract from Session: field in task description.
+  session_id: <session-id>,
  from: "coordinator",
-  to: "user",
  type: <message-type>,
-  summary: "[coordinator] <summary>",
  ref: <artifact-path>
 })
 ```
@@ -98,7 +134,7 @@ mcp__ccw-tools__team_msg({
 **CLI fallback** (when MCP unavailable):

 ```
-Bash("ccw team log --team <session-id> --from coordinator --to user --type <message-type> --summary \"[coordinator] ...\" --json")
+Bash("ccw team log --session-id <session-id> --from coordinator --type <message-type> --json")
 ```

 ---
@@ -188,7 +224,7 @@ Bash("ccw team log --team <session-id> --from coordinator --to user --type <mess
    └── issues.md
 ```

-3. Initialize shared-memory.json:
+3. Initialize .msg/meta.json:

 | Field | Initial Value |
 |-------|---------------|
@@ -308,7 +344,7 @@ Session: <session-folder>
 **Worktree Creation** (before TDFIX):

 1. Create worktree: `git worktree add <path> -b <branch>`
-2. Update shared-memory.json with worktree info
+2. Update .msg/meta.json with worktree info
 3. Notify user via team_msg

 **Fix-Verify Loop** (when TDVAL finds regressions):
--- a/.claude/skills/team-tech-debt/roles/executor/role.md
+++ b/.claude/skills/team-tech-debt/roles/executor/role.md
@@ -61,11 +61,9 @@ Before every SendMessage, log via `mcp__ccw-tools__team_msg`:
 ```
 mcp__ccw-tools__team_msg({
  operation: "log",
-  team: <session-id>,  // MUST be session ID (e.g., TD-xxx-date), NOT team name. Extract from Session: field in task description.
+  session_id: <session-id>,
  from: "executor",
-  to: "coordinator",
  type: <message-type>,
-  summary: "[executor] <task-prefix> complete: <task-subject>",
  ref: <artifact-path>
 })
 ```
@@ -73,7 +71,7 @@ mcp__ccw-tools__team_msg({
 **CLI fallback** (when MCP unavailable):

 ```
-Bash("ccw team log --team <session-id> --from executor --to coordinator --type <message-type> --summary \"[executor] ...\" --ref <artifact-path> --json")
+Bash("ccw team log --session-id <session-id> --from executor --type <message-type> --ref <artifact-path> --json")
 ```

 ---
@@ -91,13 +89,13 @@ Standard task discovery flow: TaskList -> filter by prefix `TDFIX-*` + owner mat
 | Input | Source | Required |
 |-------|--------|----------|
 | Session folder | task.description (regex: `session:\s*(.+)`) | Yes |
-| Shared memory | `<session-folder>/shared-memory.json` | Yes |
+| Shared memory | `<session-folder>/.msg/meta.json` | Yes |
 | Remediation plan | `<session-folder>/plan/remediation-plan.json` | Yes |

 **Loading steps**:

 1. Extract session path from task description
-2. Read shared-memory.json for worktree info:
+2. Read .msg/meta.json for worktree info:

 | Field | Description |
 |-------|-------------|
@@ -194,7 +192,7 @@ Execute tech debt cleanup for <batch-type> items.
 2. Run lint check -> record PASS/FAIL
 3. Update fix_results.self_validation
 4. Write `<session-folder>/fixes/fix-log.json`
-5. Update shared-memory.json with fix_results
+5. Update .msg/meta.json with fix_results

 ### Phase 5: Report to Coordinator

--- a/.claude/skills/team-tech-debt/roles/planner/role.md
+++ b/.claude/skills/team-tech-debt/roles/planner/role.md
@@ -58,11 +58,9 @@ Before every SendMessage, log via `mcp__ccw-tools__team_msg`:
 ```
 mcp__ccw-tools__team_msg({
  operation: "log",
-  team: <session-id>,  // MUST be session ID (e.g., TD-xxx-date), NOT team name. Extract from Session: field in task description.
+  session_id: <session-id>,
  from: "planner",
-  to: "coordinator",
  type: <message-type>,
-  summary: "[planner] <task-prefix> complete: <task-subject>",
  ref: <artifact-path>
 })
 ```
@@ -70,7 +68,7 @@ mcp__ccw-tools__team_msg({
 **CLI fallback** (when MCP unavailable):

 ```
-Bash("ccw team log --team <session-id> --from planner --to coordinator --type <message-type> --summary \"[planner] ...\" --ref <artifact-path> --json")
+Bash("ccw team log --session-id <session-id> --from planner --type <message-type> --ref <artifact-path> --json")
 ```

 ---
@@ -88,13 +86,13 @@ Standard task discovery flow: TaskList -> filter by prefix `TDPLAN-*` + owner ma
 | Input | Source | Required |
 |-------|--------|----------|
 | Session folder | task.description (regex: `session:\s*(.+)`) | Yes |
-| Shared memory | `<session-folder>/shared-memory.json` | Yes |
+| Shared memory | `<session-folder>/.msg/meta.json` | Yes |
 | Priority matrix | `<session-folder>/assessment/priority-matrix.json` | Yes |

 **Loading steps**:

 1. Extract session path from task description
-2. Read shared-memory.json for debt_inventory
+2. Read .msg/meta.json for debt_inventory
 3. Read priority-matrix.json for quadrant groupings
 4. Group items by priority quadrant:

@@ -157,7 +155,7 @@ Delegate to `commands/create-plan.md` if available, otherwise execute inline.

 1. Write `<session-folder>/plan/remediation-plan.md` (markdown format)
 2. Write `<session-folder>/plan/remediation-plan.json` (machine-readable)
-3. Update shared-memory.json with `remediation_plan` summary
+3. Update .msg/meta.json with `remediation_plan` summary

 ### Phase 5: Report to Coordinator

--- a/.claude/skills/team-tech-debt/roles/scanner/role.md
+++ b/.claude/skills/team-tech-debt/roles/scanner/role.md
@@ -58,11 +58,9 @@ Before every SendMessage, log via `mcp__ccw-tools__team_msg`:
 ```
 mcp__ccw-tools__team_msg({
  operation: "log",
-  team: <session-id>,  // MUST be session ID (e.g., TD-xxx-date), NOT team name. Extract from Session: field in task description.
+  session_id: <session-id>,
  from: "scanner",
-  to: "coordinator",
  type: <message-type>,
-  summary: "[scanner] <task-prefix> complete: <task-subject>",
  ref: <artifact-path>
 })
 ```
@@ -70,7 +68,7 @@ mcp__ccw-tools__team_msg({
 **CLI fallback** (when MCP unavailable):

 ```
-Bash("ccw team log --team <session-id> --from scanner --to coordinator --type <message-type> --summary \"[scanner] ...\" --ref <artifact-path> --json")
+Bash("ccw team log --session-id <session-id> --from scanner --type <message-type> --ref <artifact-path> --json")
 ```

 ---
@@ -89,12 +87,12 @@ Standard task discovery flow: TaskList -> filter by prefix `TDSCAN-*` + owner ma
 |-------|--------|----------|
 | Scan scope | task.description (regex: `scope:\s*(.+)`) | No (default: `**/*`) |
 | Session folder | task.description (regex: `session:\s*(.+)`) | Yes |
-| Shared memory | `<session-folder>/shared-memory.json` | Yes |
+| Shared memory | `<session-folder>/.msg/meta.json` | Yes |

 **Loading steps**:

 1. Extract session path from task description
-2. Read shared-memory.json for team context
+2. Read .msg/meta.json for team context
 3. Detect project type and framework:

 | Detection | Method |
@@ -182,7 +180,7 @@ For each finding, create entry:

 **Save outputs**:

-1. Update shared-memory.json with `debt_inventory` and `debt_score_before`
+1. Update .msg/meta.json with `debt_inventory` and `debt_score_before`
 2. Write `<session-folder>/scan/debt-inventory.json`:

 | Field | Description |
--- a/.claude/skills/team-tech-debt/roles/validator/role.md
+++ b/.claude/skills/team-tech-debt/roles/validator/role.md
@@ -59,11 +59,9 @@ Before every SendMessage, log via `mcp__ccw-tools__team_msg`:
 ```
 mcp__ccw-tools__team_msg({
  operation: "log",
-  team: <session-id>,  // MUST be session ID (e.g., TD-xxx-date), NOT team name. Extract from Session: field in task description.
+  session_id: <session-id>,
  from: "validator",
-  to: "coordinator",
  type: <message-type>,
-  summary: "[validator] <task-prefix> complete: <task-subject>",
  ref: <artifact-path>
 })
 ```
@@ -71,7 +69,7 @@ mcp__ccw-tools__team_msg({
 **CLI fallback** (when MCP unavailable):

 ```
-Bash("ccw team log --team <session-id> --from validator --to coordinator --type <message-type> --summary \"[validator] ...\" --ref <artifact-path> --json")
+Bash("ccw team log --session-id <session-id> --from validator --type <message-type> --ref <artifact-path> --json")
 ```

 ---
@@ -89,13 +87,13 @@ Standard task discovery flow: TaskList -> filter by prefix `TDVAL-*` + owner mat
 | Input | Source | Required |
 |-------|--------|----------|
 | Session folder | task.description (regex: `session:\s*(.+)`) | Yes |
-| Shared memory | `<session-folder>/shared-memory.json` | Yes |
+| Shared memory | `<session-folder>/.msg/meta.json` | Yes |
 | Fix log | `<session-folder>/fixes/fix-log.json` | No |

 **Loading steps**:

 1. Extract session path from task description
-2. Read shared-memory.json for:
+2. Read .msg/meta.json for:

 | Field | Description |
 |-------|-------------|
@@ -198,7 +196,7 @@ Delegate to `commands/verify.md` if available, otherwise execute inline.
 **Save outputs**:

 1. Write `<session-folder>/validation/validation-report.json`
-2. Update shared-memory.json with `validation_results` and `debt_score_after`
+2. Update .msg/meta.json with `validation_results` and `debt_score_after`

 ### Phase 5: Report to Coordinator