@xulthekl/team-flow 0.67.0 → 0.69.0

package/.claude/always/phase-guard.md

@@ -1,3 +1,3 @@
-# team-flow v0.67.0 | 阶段: {{state}} | 工作流: {{workflow}}
+# team-flow v0.69.0 | 阶段: {{state}} | 工作流: {{workflow}}
 当前阶段允许的操作由 workflow-start 路由规则定义。
 禁止跨越 DP gate 进入下一阶段。变更范围以 execution-contract.md 的 Intent Lock 为准。

package/.claude-plugin/marketplace.json

@@ -9,7 +9,7 @@
     {
       "name": "team-flow",
       "description": "8-state spec workflow + compound global compounding + architecture-design (4A/DDD) + local HTML prototype + product-level orchestration + bootstrap + e2e + session handoff + workflow feedback + independent business analysis. 28 skills + 17 agents with embedded TDD, SDD, code review, debugging, delta spec sync, and design-system-driven prototyping.",
-      "version": "0.67.0",
+      "version": "0.69.0",
       "source": "./",
       "author": {
         "name": "LT",

package/.claude-plugin/plugin.json

@@ -1,6 +1,6 @@
 {
   "name": "team-flow",
-  "version": "0.67.0",
+  "version": "0.69.0",
   "description": "Unified workflow plugin: team-flow (spec-driven dev: TDD/SDD/code-review/debugging) + compound-engineering core subset (brainstorm/plan/compound/strategy/ideate/proof, global compounding) + architecture-design (4A+DDD incremental design & global compounding) + prototype (local HTML prototype, zero external deps) + e2e (Playwright E2E, AC-driven) + workflow-orchestrator (product-level workflow orchestration) + workflow-bootstrap (existing project onboarding) + session-handoff (context transfer) + workflow-feedback (issue tracking) + business-analysis (independent requirement/scenario artifact) + design-system (design tokens + component contract + AI primer + showcase) + test-strategy (test strategy design) + project-initialize (new service onboarding) + jarvis (team-flow decision agent, opt-in). 28 skills + 17 agents, one install.",
   "source": "./",
   "author": {

package/.codex-plugin/plugin.json

@@ -1,6 +1,6 @@
 {
   "name": "team-flow",
-  "version": "0.67.0",
+  "version": "0.69.0",
   "description": "Spec-first workflow that bridges OpenSpec-style planning and Superpowers-style execution discipline.",
   "author": {
     "name": "MageByte",

package/.cursor-plugin/marketplace.json

@@ -5,7 +5,7 @@
   },
   "metadata": {
     "description": "Unified workflow plugin marketplace for Cursor (team-flow: team-flow + compound + architecture-design + prototype).",
-    "version": "0.67.0"
+    "version": "0.69.0"
   },
   "plugins": [
     {

package/.cursor-plugin/plugin.json

@@ -2,7 +2,7 @@
   "name": "team-flow",
   "displayName": "team-flow",
   "description": "Unified workflow plugin: team-flow (spec-driven dev: TDD/SDD/code-review/debugging) + compound-engineering core subset (brainstorm/plan/compound/strategy/ideate/proof, global compounding) + architecture-design (4A+DDD incremental design & global compounding) + prototype (local HTML prototype, zero external deps) + e2e (Playwright E2E, AC-driven) + workflow-orchestrator (product-level workflow orchestration) + workflow-bootstrap (existing project onboarding) + session-handoff (context transfer) + workflow-feedback (issue tracking) + business-analysis (independent requirement/scenario artifact) + jarvis (team-flow decision agent, opt-in). 28 skills + 17 agents, one install.",
-  "version": "0.67.0",
+  "version": "0.69.0",
   "author": {
     "name": "LT",
     "url": "https://github.com/LT"

package/.github/plugin/marketplace.json

@@ -6,13 +6,13 @@
   },
   "metadata": {
     "description": "Unified workflow plugins and skills for AI coding agents (team-flow: team-flow + compound + architecture-design + prototype).",
-    "version": "0.67.0"
+    "version": "0.69.0"
   },
   "plugins": [
     {
       "name": "team-flow",
       "description": "Unified workflow with planning artifacts, execution contracts, TDD, review gates, systematic debugging, delta spec sync, architecture-design, independent business analysis, and local HTML prototyping.",
-      "version": "0.67.0",
+      "version": "0.69.0",
       "source": ".",
       "author": {
         "name": "LT",

package/CHANGELOG.md

@@ -4,6 +4,56 @@ All notable changes to `team-flow` will be documented in this file.
 
 The format loosely follows Keep a Changelog.
 
+## [0.69.0] - 2026-09-30
+
+### Added（mermaid 语法快速验证：最小闭环——脚本 + 双 reviewer 接入 + 仓库回归；来源 = LT 实测 PRD mermaid 渲染失败）
+
+**验证脚本（唯一实现）**
+- 新增 `scripts/validate-mermaid.mjs`：提取 md 中全部 ```mermaid fence → `mermaid.parse()` 逐个校验（jsdom 提供 DOM，单图 <20ms）。四态契约与 `tf prd check-clarity` 同构 + 用法错误参照其 exit 2 惯例：`STATUS: PASS`（exit 0）/ `FAIL`（exit 1，stdout 必带 `file:line`）/ `SKIP`（exit 0，**仅限**依赖不可用且安装失败——LT 裁定「先尝试安装、装败才降级」）/ `ERROR`（exit 2，用法错误：无参数/路径不存在/传入目录）。顶层异常兜底保证任何场景必有 STATUS 行。
+- **依赖策略**：`mermaid ^12.0.0` + `jsdom ^26.0.0` 入 `dependencies`（用户装插件即带上）；运行时缺依赖 → 先 `npm install`（限时 90s）→ 装败才 WARN 降级 SKIP。
+- **实现陷阱（脚本头注已记）**：Node 同进程内失败的 dynamic import 会缓存为失败（实测安装后重试无效）——必须先 `createRequire` 文件系统级 resolve 探测（不进 ESM 缓存），装完再 import。
+
+**Reviewer 接入（判级：语法错误 = 机械客观缺陷，Critical）**
+- `agents/prd-completeness-reviewer.md`：Phase 1 新增第 3 步 mermaid 机械校验（FAIL=Critical 挂 D6 名下；SKIP=依赖降级不判级；ERROR/无 STATUS=环境错误不判级、不造 Critical）；Phase 2 步骤 3-8 顺延 4-9；6 维清单 D6 行补 (c) mermaid 归属；FAIL 判据扩展；报告模板增 `Mermaid check` Metadata + D6-(c) 占位；「回 Phase 1.3」歧义改写为「回 ce-brainstorm Phase 1.3/Phase 3」。
+- `agents/architecture-reviewer.md`：Phase 1 新增第 4 步 mermaid 机械校验（A1 名下，Critical；路径基于 Inputs 的 `${architecture_dir}`/`${product_snapshot_path}` 拼接，防相对 cwd 假 Critical；domains/ 用 `--dir` 单独跑）；Phase 2 步骤 4-6 顺延 5-7；A1 维度行与报告 Metadata 同步。
+
+**测试（`npm test` 1419 → 1437）**
+- 新增 `tests/lib/validate-mermaid.test.mjs`（18 测试）：fence 提取（含未闭合/非 mermaid fence 不误提）/ ensureDeps 降级路径注入（禁装/装败/装成三态）/ 正负例对照（坏图必须 FAIL、好图必须 PASS）/ CLI 四态 exit code / **skills/ 全量目录扫描回归**（存量 5 fence 基线，新增 fence 文件自动纳管，非硬编码清单）。
+- 评审：plugin-validator PASS（0C+3W）、skill-reviewer PASS_WITH_WARNINGS（0C+3M+7m），全部发现已修复后收口。
+
+## [0.68.0] - 2026-09-30
+
+### Added（security-baseline 企业安全基线集成：四层全量落地；设计 = 工作区 `docs/plan/security-baseline-integration-design.md` v1.3 + P3 修正，P1.5 完整档三轮闭合 0 Critical）
+
+**L1 基线双载体（单一真相源）**
+- 新增 `skills/ce-brainstorm/references/security-baseline.md`（44 项企业安全设计控制点人类可读权威 + verdict→门禁映射）+ `security-baseline.json`（机器可读，`baseline_version` + 逐项 trigger/locus/severity）——测试断言 md↔json 44 行逐项对齐。**企业 xlsx 原件不入本仓**（脱敏，来源指针留 workspace 设计文档）。
+
+**Scope Deriver（范围推导，唯一实现）**
+- 新增 `scripts/lib/security-scope.mjs`：gitChangedFiles（base_sha 锚定）+ 路径启发式 + spec/arch 关键词 → 10 类触发类别 + 适用项；**排除 change 目录自身**（realpath 归一防 macOS /var 符号链接）；推导结果落盘 `<change-dir>/.security-scope.json`（含 `scope_hash`，预像 = 规范化触发集+适用集）。
+- 新增 CLI `tf security scope <change-dir> [--json]` + `tf security baseline`（`scripts/lib/cmd-security.mjs`，COMMANDS + HELP 双注册）。LLM/人从不手写 scope JSON——对账是脚本 vs 脚本（设计 §二.6）。
+
+**L2 守卫双维度（guard 33→35 维）**
+- 新增 `scripts/guard/checks/security-baseline.mjs`（重档 full/hotfix/planned）+ `security-baseline-light.mjs`（轻档 quick/lightweight；tweak 豁免）。判定序：存量分档（无 `schema_version` → WARN 软着陆）→ 现场推导落盘 → 无触发静默 PASS（留痕）→ skip 短路（`security_scope_hash` 不匹配即失效）→ 档位分流（重档查 `.security-verification.json` 完备性：适用集 ⊆ items、缺席=uncovered、must uncovered=FAIL / should=WARN、not-applicable reason ≥10 字符或含序号）→ infra 项交接检查（`security/handoff.md` transition 前置）。
+- guard.mjs 四表分挂（基础 TRANSITION / WORKFLOW hotfix / QUICK ×2 / PLANNED）；state 三环三键（BUILTIN_DEFAULTS + writeState + SETTABLE_FIELDS：`security_baseline_skipped/_skip_reason/security_scope_hash`）。
+- 反向验证通过：临时移除维度 → 单测 14 红 / 恢复 → 19 绿。
+
+**L3/L4/L5 判据送达（三通道 + 时序前置）**
+- L3 code-reviewer 三处同步（agents Output Contract / SKILL Step 2.5 / prompt 模板内联 `[SECURITY_SCOPE_JSON]` 占位）；派发侧 workflow-start SKILL + routing-rules 加 `tf security scope` 前置与 dispatch 传参。
+- L4 spec-writer design.md「适用触发类别确认」小节 + planned 主代理分支指引（planned 无 spec-writer）；security-sentinel **双副本**（ce-plan + ce-compound）同步增引基线。
+- L5 release-archivist 三分支 handoff 时序前置（legacy ①b / planned ④b / direct ⓪，各在 transition 之前）+ 跨 change 台账 `.team-flow/security-todos.md`；**planned verification 生产者 = 最终审查（P3 修正，planned 不派 code-reviewer）**；hotfix 重档归属 + tweak L5 豁免注记。
+- `doc-consistency.test.mjs` 新增 19 条安全基线注入锚点 + 三分支时序断言（规则送到执行者/派发者，机械守护）。
+
+### Changed
+- 维度计数横展 33→35 共 12 处（guard-dimensions 头部映射 / 使用说明矩阵与出路表 / test-matrix / e2e skill 描述等）；`docs/team-flow 使用说明` 新增 security-baseline 维度行 + 门禁出路行。
+- `code-reviewer` "6-step" 计数宣称去数字化（实际已 9 步）；`report_path` 交叉核验措辞改「写入者自约束」（当前无机械对账，不虚称）。
+
+### Fixed
+- 非 git 目录跑 `tf security scope` 的 stderr `fatal:` 泄漏（stdio 收窄，只给结构化 `error=no-baseline` 提示）。
+
+### Testing
+- 新增 `tests/lib/guard-security-baseline.test.mjs` 19 例（存量软着陆正反例 / 推导留痕 / skip 三态 / verdict 映射 / 完备性对账 / infra 交接 / 三环写入 / 双载体一致性 / 四档分流）；doc-consistency +15；e2e P7 planned 夹具按新流程补 scope+verification。
+- `npm test` 1383→**1419** + `test:e2e` **103** 全绿；`check-versions` PASS；`lint:skills` 本迭代引入 error 清零（余 7 存量）；`tf doctor` All checks passed；P4 双门禁 plugin-validator **PASS** / skill-reviewer **PASS_WITH_WARNINGS**（Major/Minor 全修，遗留见 Roadmap P2-72/73）。
+
 ## [0.67.0] - 2026-09-25
 
 ### Added（agent-governance 治理演进全量：P0–P2 七批次；设计 = 工作区 `teamflow-agent-governance-design-memo.md` v0.5 + 实施计划 v1.2，P1.5 标准档两轮 + 收官验证 0 Critical）

package/GEMINI.md

@@ -8,7 +8,7 @@ The workflow is self-contained and does not require OpenSpec or Superpowers at r
 
 
 <!-- team-flow-phase-guard-start -->
-# team-flow v0.67.0 | 阶段: {{state}} | 工作流: {{workflow}}
+# team-flow v0.69.0 | 阶段: {{state}} | 工作流: {{workflow}}
 当前阶段允许的操作由 workflow-start 路由规则定义。
 禁止跨越 DP gate 进入下一阶段。变更范围以 execution-contract.md 的 Intent Lock 为准。
 <!-- team-flow-phase-guard-end -->

package/INSTALL.md

@@ -7,7 +7,7 @@
 - [Fission-AI/OpenSpec](https://github.com/Fission-AI/OpenSpec) — 规划引擎（Schema 验证、Delta Spec、工件解析）
 - [obra/superpowers](https://github.com/obra/superpowers) — 执行纪律（TDD 铁律、SDD、系统化调试、代码审查）
 
-当前发布版本：**v0.67.0**。
+当前发布版本：**v0.69.0**。
 
 ---
 

package/README.md

@@ -1,6 +1,6 @@
 # team-flow
 
-> 当前版本：`v0.67.0`
+> 当前版本：`v0.69.0`
 
 > 统一插件：**team-flow**（spec 驱动开发）+ **compound-engineering 核心子集**（全局复利）+ **architecture-design**（4A+DDD 增量设计）+ **prototype**（本地 HTML 原型）+ **e2e**（AC 驱动 E2E）+ **workflow-orchestrator**（产品级编排）+ **workflow-bootstrap**（既有项目接入）。一次安装，十三套能力协同（详见下文「十三套能力」）。
 

package/agents/architecture-reviewer.md

@@ -50,7 +50,7 @@ If change_brief_path or architecture_dir is missing or unreadable **in change mo
 
 | Dim | Name | Baseline Source | Check Content | Severity |
 |-----|------|----------------|---------------|----------|
-| A1 | 产出完整性 | architecture-design 结构化输出 | `architecture.md` / `database.md` / `api.md` 文件存在且非空 | Critical |
+| A1 | 产出完整性 | architecture-design 结构化输出 | `architecture.md` / `database.md` / `api.md` 文件存在且非空 + 内含 mermaid fence 语法可 parse（Phase 1 第 4 步机械校验） | Critical |
 | A2 | SQL 制品完整性 | `database.md` 中引用的 SQL 路径 | `sql/ddl/*.sql` / `sql/migration/*.sql` 文件存在且语法可检查 | Critical |
 | A3 | 模板合规性 | `architecture-design/templates/` | 产出文件结构与模板一致（YAML frontmatter + 必要章节） | Important |
 | A4 | 需求覆盖 | change-brief + plan | 每个业务需求 → 对应的架构设计覆盖（聚合/BC/API/DB） | Critical |
@@ -84,11 +84,21 @@ Mechanical verification, no LLM semantic judgment needed:
      - api.md → templates/api.md (sections: Command, Read, Query, frontmatter api_contract_manager)
    - Missing required section = Important finding
 
+4. **Mermaid 图语法机械校验（v0.69.0，A1 名下）**:
+   - `node ${CLAUDE_PLUGIN_ROOT}/scripts/validate-mermaid.mjs <文件列表>`（**路径基于 Inputs 传入的目录参数拼接，不是相对 cwd 的字面路径**——传错路径脚本会 `STATUS: ERROR` exit 2，将产生假 Critical/假评审失败）:
+     - change 模式：`${architecture_dir}/architecture.md ${architecture_dir}/database.md ${architecture_dir}/api.md`（三件套逐文件显式传入；**不要**把目录本身传给脚本）
+     - product 模式：`${product_snapshot_path}` 单文件；`domains/` 下多个 .md 用 `--dir <domains目录>` **单独再跑一次**
+     - 脚本自带依赖自愈（缺则先装、装败降级，安装最多阻塞约 90s——依赖装入插件包 node_modules，不触碰审查制品，不违反 Iron Law）
+   - 末行 `STATUS: FAIL`（exit 1）→ 每个 `file:line` 命中 = **Critical finding**（架构图含 mermaid（context map/时序/状态/ER），语法错误渲染必失败；附行号与 parse 错误）。**FAIL 但 stdout 无任何 `file:line` 命中 = 异常输出，按环境错误处理，不得凭空造 Critical。**
+   - 末行 `STATUS: SKIP` → 依赖降级（缺依赖且安装失败），不判级，报告 Metadata 记 `Mermaid check: SKIPPED（依赖不可用）`；不得因 SKIP 判 FAIL
+   - 末行 `STATUS: PASS` → 记 `Mermaid check: PASS (n fences)`
+   - 末行 `STATUS: ERROR`（exit 2，用法错误：路径不对/传了目录）**或无 STATUS 行**（脚本不存在/崩溃）→ **环境错误，不判级**：Metadata 记 `Mermaid check: ERROR (<原因>)`，会话输出通道向派发方提一行（如 `${CLAUDE_PLUGIN_ROOT} 未解析`）；不得记为 SKIPPED，不得判 FAIL
+
 ### Phase 2: Deep-check (LLM Semantic Comparison, A4/A5/A6)
 
 Dimensions requiring semantic understanding, marked as "advisory, false positives can be overridden":
 
-4. **A4 需求覆盖** (v0.29.0 §37 增强：双对照源 + 子实体 CRUD 检查):
+5. **A4 需求覆盖** (v0.29.0 §37 增强：双对照源 + 子实体 CRUD 检查):
    - **对照源 1（现有）**：Read change-brief.md → extract all requirement items (scope, AC, technical direction)
    - **对照源 2（v0.29.0 新增）**：Read `requirement/vN/prd.md` → extract feature list (e.g., F001_P0_P1 ~ P0_PN)
    - Read plan.md → extract relevant technical design sections
@@ -107,7 +117,7 @@ Dimensions requiring semantic understanding, marked as "advisory, false positive
    - Uncovered requirement = Critical finding
    - Build coverage matrix table (MUST include columns for both brief source AND PRD source)
 
-5. **A5 基线一致性**:
+6. **A5 基线一致性**:
    - Read global `ARCHITECTURE.md` → check naming conventions, BC boundaries
    - Read global `PHYSICAL-MODEL.md` → check table naming patterns, field conventions
    - Read global `API-INDEX.md` → check API routing patterns
@@ -118,7 +128,7 @@ Dimensions requiring semantic understanding, marked as "advisory, false positive
      - API endpoint conflicts with API-INDEX → Critical
      - BC boundary contradictions → Critical
 
-6. **A6 conventions 合规**:
+7. **A6 conventions 合规**:
    - Read `team-flow.config.json` → `conventions` section
    - Load applicable convention files:
      - `conventions.database` → check DB naming rules, primary key strategy, audit fields
@@ -156,6 +166,7 @@ Aggregate all findings and determine verdict.
 - **Change Brief**: {change_brief_path}
 - **Architecture Dir**: {architecture_dir}
 - **Global Arch Dir**: {global_arch_dir}
+- **Mermaid check**: {PASS (n fences) | FAIL (n errors) | SKIPPED（依赖不可用） | ERROR (&lt;原因&gt;)}
 - **Review round**: {N}
 - **Reviewer**: architecture-reviewer agent (independent)
 - **Timestamp**: {ISO 8601}

package/agents/code-reviewer.md

@@ -12,7 +12,7 @@ skills:
 
 You are an independent Code Reviewer. You review code changes for quality, spec compliance, architecture soundness, and implementation completeness. You write the review report to disk and return a summary.
 
-**Your preloaded Skill contains the detailed methodology** (6-step review process, calibration rules, severity definitions, critical rules). Follow it for HOW. This prompt defines WHO you are and WHAT you must deliver.
+**Your preloaded Skill contains the detailed methodology** (step-by-step review process, calibration rules, severity definitions, critical rules). Follow it for HOW. This prompt defines WHO you are and WHAT you must deliver.
 
 ## Iron Law
 
@@ -37,8 +37,15 @@ Produce a structured review report with the following sections:
 2. **Verdict**: PASS / PASS_WITH_WARNINGS / FAIL
 3. **Findings table**: severity, category, file, line, description, suggestion
 4. **Spec compliance matrix**: spec requirement → implementation status
-5. **Summary**: key strengths, critical issues, recommendations
-6. **Report File**: path to the written report file + confirmation
+5. **Security Baseline 核验**（security-baseline-integration-design v1.3）: 逐条 verdict
+   - 适用子集 = 派发时 dispatch prompt 显式传入的 `.security-scope.json` **code-locus 适用项**（**不要自行推导**；缺传参时先跑 `tf security scope <change-dir>` 取）。
+   - 每项 verdict ∈ `satisfied | not-applicable | uncovered`；`not-applicable` 必须带 reason（≥10 字符或含控制点序号，否则视同 uncovered）；must 项 uncovered = Critical。
+   - 核验完成**必须写盘** `<change-dir>/.security-verification.json`：
+     `{"items":[{"id":<序号>,"verdict":"...","reason":"..."}], "report_path":"<本报告路径>", "round":<n>}`
+   - `report_path` **写为 receipt `--report` 同一路径**（写入者自约束——当前无机械对账，勿声称已核验）；guard 只读该 JSON，不解析本报告 markdown。
+   - 仅末 wave 产一份；**planned 档不派本 agent**（其 JSON 由 release-archivist 最终审查产，见其 SKILL ④）。
+6. **Summary**: key strengths, critical issues, recommendations
+7. **Report File**: path to the written report file + confirmation
 
 Your preloaded Skill provides the full report template and formatting guidelines. Write the report to disk, then return summary + file path.
 
@@ -54,7 +61,7 @@ Your preloaded Skill defines severity levels (Critical / Important / Minor) and
 ## Red Lines
 
 **DO:**
-- Follow the preloaded Skill's 6-step review methodology
+- Follow the preloaded Skill's review methodology
 - Read specs and design BEFORE reading implementation — establish requirements baseline
 - Cite specific file:line for every finding
 - Distinguish spec violations (Critical) from style issues (Minor)

package/agents/prd-completeness-reviewer.md

@@ -41,7 +41,7 @@ If `prd_path` is missing or unreadable, report `FAIL` with reason `INPUT_ERROR`.
 | D3 | 边界与非功能 | 空/错/异常状态、性能/兼容约束 | Important |
 | D4 | 术语一致性 | 与 CONCEPTS.md / §6 业务术语一致 | Minor |
 | D5 | 范围闭环 | in/out scope 明确，无悬空功能 | Important |
-| D6 | §8.4 信息齐备性与业务可读形态 | **（a）信息齐备性**：逐功能模块核对业务信息是否**可定位**（不核对"正文里有没有该维度标题"）；§7↔§8.4 交叉核对无悬空功能。**（b）形态核验（v0.62.0 G7）**：按 6 条判据核验产出形态是否符合规范（见下方 D6 执行细则）。**基准 = `prd-84-authoring-spec.md`（唯一权威，不是模板 §8.4）** | Critical（核心信息缺失 / 悬空功能）/ Important（辅助信息缺失、**形态核验命中**） |
+| D6 | §8.4 信息齐备性与业务可读形态 | **（a）信息齐备性**：逐功能模块核对业务信息是否**可定位**（不核对"正文里有没有该维度标题"）；§7↔§8.4 交叉核对无悬空功能。**（b）形态核验（v0.62.0 G7）**：按 6 条判据核验产出形态是否符合规范（见下方 D6 执行细则）。**（c）mermaid fence 语法机械校验（Phase 1 第 3 步）**：parse 失败 = Critical。**基准 = `prd-84-authoring-spec.md`（唯一权威，不是模板 §8.4）** | Critical（核心信息缺失 / 悬空功能 / mermaid 语法错误）/ Important（辅助信息缺失、**形态核验命中**） |
 
 ## Review Process
 
@@ -49,33 +49,38 @@ If `prd_path` is missing or unreadable, report `FAIL` with reason `INPUT_ERROR`.
 
 1. Read the PRD fully. Locate the functional requirement sections (用户故事 / 功能清单 / 系统功能), acceptance criteria, scope (in/out), and glossary (§6 业务术语).
 2. Use `grep` to enumerate requirement items and check for the presence of AC markers / actor markers / scope markers — this grounds the per-item review.
+3. **Mermaid 语法机械校验（v0.69.0）**：`node ${CLAUDE_PLUGIN_ROOT}/scripts/validate-mermaid.mjs <prd_path>`（脚本自带依赖自愈：缺则先装、装败降级，安装最多阻塞约 90s——依赖装入插件包 node_modules，不触碰任何评审制品，不违反 Iron Law）。
+   - 末行 `STATUS: FAIL`（exit 1）→ 每个 `file:line` 命中记 **Critical**（D6 名下，描述注明「mermaid 语法错误，渲染必失败」，附行号与 parse 错误）——语法失败是机械判定的客观缺陷，非语义裁量，无误报面。**FAIL 但 stdout 无任何 `file:line` 命中 = 异常输出，按下方环境错误处理，不得凭空造 Critical。**
+   - 末行 `STATUS: SKIP` → 依赖降级（缺依赖且安装失败），**不判级**，在报告 Metadata 记 `Mermaid check: SKIPPED（依赖不可用）`；不得因 SKIP 判 FAIL。
+   - 末行 `STATUS: PASS` → 记 `Mermaid check: PASS (n fences)`，无 finding。
+   - 末行 `STATUS: ERROR`（exit 2，用法错误：路径不对/传了目录）**或无 STATUS 行**（脚本不存在/崩溃）→ **环境错误，不判级**：Metadata 记 `Mermaid check: ERROR (<原因>)`，同时在会话输出通道向派发方提一行（如 `${CLAUDE_PLUGIN_ROOT} 未解析`）；不得记为 SKIPPED（依赖问题），不得判 FAIL。
 
 ### Phase 2: Per-Dimension Deep Check（LLM 语义判断）
 
-3. **D1 用户故事完整性**（Critical）：For each functional requirement, check it has:
+4. **D1 用户故事完整性**（Critical）：For each functional requirement, check it has:
    - **actors**（谁触发/谁参与）— explicit or unambiguously inferable
    - **流程**（关键步骤/交互路径）
    - **结果**（完成态/输出/系统响应）
    Missing any of the three for a requirement = Critical finding (cite §X.X + requirement id).
 
-4. **D2 验收标准**（Critical）：For each functional requirement, check there is at least one **verifiable** acceptance criterion or success signal (testable condition, observable outcome, measurable threshold).
+5. **D2 验收标准**（Critical）：For each functional requirement, check there is at least one **verifiable** acceptance criterion or success signal (testable condition, observable outcome, measurable threshold).
    - AC present but vague/unverifiable ("系统应表现良好") = Critical.
    - AC entirely missing = Critical.
 
-5. **D3 边界与非功能**（Important）：Check whether the PRD addresses:
+6. **D3 边界与非功能**（Important）：Check whether the PRD addresses:
    - 边界状态：空态 / 错误态 / 异常 / 并发 / 极值
    - 非功能约束：性能 / 兼容性 / 安全 / 可用性（where relevant to the product）
    Missing edge-state coverage for a core flow, or no non-functional constraints where they clearly matter = Important.
 
-6. **D4 术语一致性**（Minor）：Compare terms used in the PRD against CONCEPTS.md (if provided) and the PRD's own §6 业务术语. Same concept named differently, or undefined jargon used = Minor.
+7. **D4 术语一致性**（Minor）：Compare terms used in the PRD against CONCEPTS.md (if provided) and the PRD's own §6 业务术语. Same concept named differently, or undefined jargon used = Minor.
 
-7. **D5 范围闭环**（Important）：
+8. **D5 范围闭环**（Important）：
    - in scope and out scope explicitly declared?
    - Any "悬空功能" — a feature mentioned in scope but with no actors/AC/implementation path (dangling)?
    - Any out-of-scope item that other requirements implicitly depend on?
    Missing scope declaration or dangling feature = Important.
 
-8. **D6 §8.4 信息齐备性与业务可读形态**：Read the **spec file** FIRST — `spec_path`
+9. **D6 §8.4 信息齐备性与业务可读形态**：Read the **spec file** FIRST — `spec_path`
    （默认 `${CLAUDE_PLUGIN_ROOT}/skills/ce-brainstorm/references/prd-84-authoring-spec.md`）
    is the **single authority**——never judge against your own expectations,
    and never against the template skeleton（模板只承载骨架与槽位）.
@@ -123,9 +128,9 @@ Aggregate findings → final verdict per the Judgment Criteria.
 |---------|-----------|--------|
 | **PASS** | Critical=0 且 Important=0 | 可进入冻结 / 下游 plan |
 | **PASS_WITH_WARNINGS** | Critical=0 且 Important>0 | 警告项交人工裁定，不阻断 |
-| **FAIL** | Critical>0 | 必须回 Phase 1.3/Phase 3 补充后重新评审 |
+| **FAIL** | Critical>0 | 必须回 ce-brainstorm Phase 1.3（澄清）/ Phase 3（撰写）补充后重新评审——注意是 ce-brainstorm 的阶段号，非本 agent 的 Phase 编号 |
 
-**FAIL 仅由 Critical 触发**（D1/D2 缺失；D6 核心维度缺失、D6 悬空功能）。Important（D3/D5/D6 辅助维度）误报不触发 FAIL。Minor（D4/D6 可读性）仅记录。
+**FAIL 仅由 Critical 触发**（D1/D2 缺失；D6 核心维度缺失、D6 悬空功能；D6 mermaid 语法错误——Phase 1 第 3 步机械判定）。Important（D3/D5/D6 辅助维度）误报不触发 FAIL。Minor（D4/D6 可读性）仅记录。
 
 ## Output Format
 
@@ -139,6 +144,7 @@ Aggregate findings → final verdict per the Judgment Criteria.
 ## Metadata
 - **PRD**: {prd_path}
 - **CONCEPTS**: {concepts_path or "N/A"}
+- **Mermaid check**: {PASS (n fences) | FAIL (n errors) | SKIPPED（依赖不可用） | ERROR (&lt;原因&gt;)}
 - **Review round**: {N}
 - **Reviewer**: prd-completeness-reviewer agent (independent)
 - **Timestamp**: {ISO 8601}
@@ -184,6 +190,9 @@ Aggregate findings → final verdict per the Judgment Criteria.
 | 6 维度清单未写入正文 | {是/否} | {Important/—} | |
 [逐功能模块检查：功能形态 | 适用维度覆盖 | NA 标注 | 悬空功能 | 状态]
 
+#### D6-(c) Mermaid 语法机械校验（Phase 1 第 3 步）
+{PASS (n fences) | FAIL (n errors，逐条 file:line + parse 错误) | SKIPPED（依赖不可用） | ERROR (&lt;原因&gt;)}
+
 ## Findings
 | # | Dim | Severity | PRD Source | Requirement | Description | Suggestion |
 |---|-----|----------|-----------|-------------|-------------|------------|

package/docs/README_en.md

@@ -126,7 +126,7 @@ npm install -g team-flow
 
 ### Version
 
-- Current: `v0.67.0`
+- Current: `v0.69.0`
 - v0.9.1 highlights: DP-4 execution-mode recommendations, a portable runtime across 17 platforms, and a raw-package smoke with no plugin-root variable.
 - Self-contained — no OpenSpec or Superpowers runtime required
 - Upstream: [Fission-AI/OpenSpec](https://github.com/Fission-AI/OpenSpec), [obra/superpowers](https://github.com/obra/superpowers)

package/docs/team-flow /344/275/277/347/224/250/350/257/264/346/230/216/357/274/210/347/240/224/345/217/221/345/233/242/351/230/237/347/211/210/357/274/211.md"

@@ -1,6 +1,6 @@
 # team-flow 使用说明（研发团队版）
 
-> 版本锚点：v0.67.0（28 skills + 17 agents）· 更新日期：2026-09-21
+> 版本锚点：v0.69.0（28 skills + 17 agents）· 更新日期：2026-09-21
 > 读者：使用 team-flow 做日常研发的工程师。不需要你懂插件内部实现，只需要照着路径走。
 > 配套文档：安装细节见 [INSTALL.md](../INSTALL.md)；状态机细节见 [state-machine.md](state-machine.md)；决策点细节见 [decision-points.md](decision-points.md)；平台差异见 [platform-matrix.md](platform-matrix.md)。
 
@@ -173,7 +173,7 @@ workflow-start 在初始化时自动推断（`tf runtime infer`），你也可
 | 模式 | 判据（自动推断） | 特点 | 门禁差异（对比 full） |
 |------|----------------|------|--------|
 | **full** | 默认（不满足下面两个） | 全流程：需求探索→架构门→四件套→契约→执行计划→TDD→逐 wave 审查→完整收尾 | 基准：`executing→closing` 挂 10 维 |
-| **hotfix** | ≤2 任务、≤2 文件，且不动 schema/API、不新增模块 | 跳过需求探索和规划制品，最小契约仍需 DP-3 批准 | 入口换一套更轻的维度：`contract-current`+`dp3-approved` 取代 full 的 artifacts-exist / schema-valid / contract-fresh / dp-gate-passed；不查 `test-matrix-ready`。出口 6 维——省 `test-matrix-complete`、`arch-snapshot`、`delegation-status`、`arch-merged`，**但执行计划与逐 wave 审查回执仍要** |
+| **hotfix** | ≤2 任务、≤2 文件，且不动 schema/API、不新增模块 | 跳过需求探索和规划制品，最小契约仍需 DP-3 批准 | 入口换一套更轻的维度：`contract-current`+`dp3-approved` 取代 full 的 artifacts-exist / schema-valid / contract-fresh / dp-gate-passed；不查 `test-matrix-ready`。出口 7 维——省 `test-matrix-complete`、`arch-snapshot`、`delegation-status`、`arch-merged`，**但执行计划、逐 wave 审查回执与 `security-baseline`（v1.3 重档）仍要** |
 | **tweak** | ≤4 任务，且文件全是配置/文档类（无代码文件）、不动 schema/API、不新增模块 | 直接进 approved-for-build，直接编辑 | 入口不查 `execution-plan-ready` / `test-matrix-ready`，但仍查 `artifacts-exist`+`contract-fresh`+`dp-gate-passed`。出口仅 3 维（`tasks-complete`、`tests-passing`、`specs-merged`），省掉其余 7 项 |
 
 **注意三件事**：
@@ -232,7 +232,7 @@ workflow-start 在初始化时自动推断（`tf runtime infer`），你也可
 tf runtime guard check <change-dir> <from-state> <to-state> [--workflow full|hotfix|tweak]
 ```
 
-**full 模式的完整转换矩阵**（**33 个维度** + 1 个 workflow 限制维度；v0.64.0 增 quick/lightweight/planned 轻路径 11 维；agent-governance P1-1 增 **prd-clarity / history-risk** 接活前双维度——**无记录/INDEX 空的冷启动场景**零行为变化；INDEX 积累丰富的项目 history-risk 命中即阻断，属该维 experimental 设计而非回归）：
+**full 模式的完整转换矩阵**（**35 个维度** + 1 个 workflow 限制维度；v0.64.0 增 quick/lightweight/planned 轻路径 11 维；agent-governance P1-1 增 **prd-clarity / history-risk** 接活前双维度——**无记录/INDEX 空的冷启动场景**零行为变化；INDEX 积累丰富的项目 history-risk 命中即阻断，属该维 experimental 设计而非回归）：
 
 | 转换 | 维度 |
 |------|------|
@@ -240,7 +240,7 @@ tf runtime guard check <change-dir> <from-state> <to-state> [--workflow full|hot
 | specifying→bridging | artifacts-exist、schema-valid |
 | bridging→approved-for-build | artifacts-exist、schema-valid、contract-fresh、dp-gate-passed、dp3-approved、**gates-probed**（v0.63.0）、**prd-clarity**、**history-risk**（P1-1） |
 | approved-for-build→executing | artifacts-exist、contract-fresh、dp-gate-passed、execution-plan-ready、test-matrix-ready、**prd-clarity**、**history-risk**（P1-1） |
-| **executing→closing** | **11 维**：**contract-fresh（v0.63.0）**、tasks-complete、tests-passing、specs-merged、execution-plan-ready、execution-reviews-passed、compound-captured、test-matrix-complete、arch-snapshot、delegation-status、arch-merged |
+| **executing→closing** | **12 维**：**contract-fresh（v0.63.0）**、tasks-complete、tests-passing、specs-merged、execution-plan-ready、execution-reviews-passed、compound-captured、test-matrix-complete、arch-snapshot、delegation-status、arch-merged、**security-baseline（v1.3）** |
 | executing↔debugging | debugging 入口无门禁；回 executing 挂 contract-fresh、execution-plan-ready |
 | exploring→bridging / exploring→approved-for-build | 0 维，但**一一对应**：`exploring→bridging` 仅 hotfix 可走、`exploring→approved-for-build` 仅 tweak 可走；full 走或其他组合都直接 FAIL |
 | 7 条回退 + 6 条放弃 | 0 维（回退是合法操作，不需要门禁放行） |
@@ -261,7 +261,9 @@ tf runtime guard check <change-dir> <from-state> <to-state> [--workflow full|hot
 | compound-captured | executing→closing | 缺 `learnings.md`（change 根目录，非空）→ 写它，或 `tf state set <dir> compound_skipped true` |
 | arch-snapshot | executing→closing | 产品级架构快照缺失 → 补快照或物化 SKIPPED 标记 |
 | arch-merged | executing→closing | 架构增量未回写全局台账 → **先跑 `tf arch-merge <change-dir>` 再转换**（v0.53.0 B' 时序）；确无增量可回写时 `tf state set <dir> arch_merge_skipped true` + `arch_merge_skip_reason` |
+| security-baseline（v1.3） | executing→closing | 缺 `.security-verification.json` → 派发 code-reviewer（末 wave / planned 最终审查）产核验 JSON（dispatch 传 `[SECURITY_SCOPE_JSON]`）；命中 infra 项缺 handoff → transition 前写 `security/handoff.md`；整体确不适用 → `tf state set <dir> security_baseline_skipped true` + `security_baseline_skip_reason` + `security_scope_hash`（取 `tf security scope` 输出） |
 | delegation-status | executing→closing | 非 glaf4-delegation 模式直接 PASS；该模式须 `delegation_status=success` |
+| security-baseline / security-baseline-light（v1.3） | executing→closing（重档 full/hotfix/planned；轻档 quick/lightweight；tweak 豁免） | 现场推导 `.security-scope.json`：无适用触发类别=静默 PASS（留痕）；重档须 `.security-verification.json` 逐条 verdict（must uncovered=FAIL、缺席=uncovered）；命中 infra 项须 transition 前写 `security/handoff.md`；skip 出路 `security_baseline_skipped`+`security_baseline_skip_reason`+`security_scope_hash`（三键，hash 变即失效）；存量（无 `schema_version`）WARN 软着陆 |
 | artifacts-exist / schema-valid | specifying→bridging 起 | 四件套缺失或 Validator 不通过（SHALL/MUST、Scenario、跨段冲突） |
 | prd-clarity | 接活前（bridging→approved / approved→executing，quick/lightweight/planned 前门） | 产品级 PRD 清晰度记录为 fail → 回 S2 重跑 `tf prd check-clarity` 修至 PASS 后重建 change；无记录 = 中性放行（存量/direct/hotfix） |
 | history-risk | 同上（experimental） | solutions INDEX 中**按 change 名词根匹配**的条目 N≥3 且最高 severity=critical → 阻断。**出路（改数据源头，无 state 确认通道）**：① 坑已根治 → 按 compound 退役/降档处理相关条目后重建 INDEX；② 误关联 → 调整 change 名避开词根。N<3 / INDEX 空 / 无匹配 = 中性 |
@@ -754,4 +756,4 @@ tf runtime guard check <change-dir> <from> <to> --json
 
 ---
 
-*本文档基于 v0.60.0 源码全量核对产出（2026-09-13 同步），v0.67.0 增量同步 agent-governance 改动（33 维矩阵 / prd-clarity·history-risk 出路 / 复利注入与见习门控，2026-09-25）。发现与实际行为不符，请 `/team-flow:workflow-feedback` 反馈——这正是本插件的演进方式。*
+*本文档基于 v0.60.0 源码全量核对产出（2026-09-13 同步），v0.67.0 增量同步 agent-governance 改动（35 维矩阵——v1.3 增 security-baseline 双维度，2026-09-30；prd-clarity·history-risk 出路 / 复利注入与见习门控，2026-09-25）。发现与实际行为不符，请 `/team-flow:workflow-feedback` 反馈——这正是本插件的演进方式。*

package/gemini-extension.json

@@ -1,6 +1,6 @@
 {
   "name": "team-flow",
   "description": "Unified workflow plugin: team-flow (spec-driven dev) + compound-engineering core subset + architecture-design (4A/DDD) + prototype (local HTML) + business-analysis (independent requirement/scenario artifact) + jarvis (team-flow decision agent, opt-in). 28 skills, one install.",
-  "version": "0.67.0",
+  "version": "0.69.0",
   "contextFileName": "GEMINI.md"
 }

package/hooks/session-start

@@ -1,11 +1,11 @@
 #!/usr/bin/env bash
-# v0.67.0: auto-sync CLI version with plugin version
+# v0.69.0: auto-sync CLI version with plugin version
 set -e
 
 # ═══════════════════════════════════════════════════════════════
 # Plugin version (update this when releasing new versions)
 # ═══════════════════════════════════════════════════════════════
-PLUGIN_VERSION="0.67.0"
+PLUGIN_VERSION="0.69.0"
 
 # ═══════════════════════════════════════════════════════════════
 # Step 1: Auto-sync CLI version with plugin version

package/llms.txt

@@ -3,7 +3,7 @@
 ## Overview
 spec-superflow is a self-contained workflow integration plugin for Claude Code, Cursor, OpenAI Codex CLI/App, GitHub Copilot CLI, Gemini CLI, OpenCode, WorkBuddy, and Trae. It merges spec-driven planning artifacts (proposal, specs, design, tasks) with disciplined execution guardrails (TDD, review gates, controlled handoff) into one unified workflow.
 
-Current version: v0.67.0.
+Current version: v0.69.0.
 
 ## Key Documents
 - README.md: Chinese homepage with full usage guide and FAQ

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@xulthekl/team-flow",
-  "version": "0.67.0",
+  "version": "0.69.0",
   "description": "Unified plugin (28 skills + 17 agents) integrating team-flow, compound-engineering, architecture-design, prototype, design-system, workflow-orchestrator, workflow-bootstrap, e2e, session-handoff, workflow-feedback, business-analysis for multi-agent coding tools.",
   "main": "dist/index.js",
   "types": "dist/index.d.ts",
@@ -50,5 +50,9 @@
   "devDependencies": {
     "js-yaml": "^5.2.3",
     "typescript": "^6.0.3"
+  },
+  "dependencies": {
+    "mermaid": "^12.0.0",
+    "jsdom": "^26.0.0"
   }
 }

package/plugin.json

@@ -1,6 +1,6 @@
 {
   "name": "team-flow",
-  "version": "0.67.0",
+  "version": "0.69.0",
   "description": "Unified workflow plugin: team-flow (spec-driven dev: TDD/SDD/code-review/debugging) + compound-engineering core subset (brainstorm/plan/compound/strategy/ideate/proof, global compounding) + architecture-design (4A+DDD incremental design & global compounding) + prototype (local HTML prototype, zero external deps) + e2e (Playwright E2E, AC-driven) + workflow-orchestrator (product-level workflow orchestration) + workflow-bootstrap (existing project onboarding) + session-handoff (context transfer) + workflow-feedback (issue tracking) + business-analysis (independent requirement/scenario artifact) + design-system (design tokens + component contract + AI primer + showcase) + test-strategy (test strategy design) + project-initialize (new service onboarding) + jarvis (team-flow decision agent, opt-in). 28 skills + 17 agents, one install.",
   "author": {
     "name": "LT"

package/scripts/guard/checks/security-baseline-light.mjs

@@ -0,0 +1,9 @@
+// scripts/guard/checks/security-baseline-light.mjs — 安全基线闸门（轻档：quick/lightweight）
+// 设计：docs/plan/security-baseline-integration-design.md v1.3 §L2
+// 与重档共享全部判定（存量分档 / 推导落盘 / skip 短路 / infra 交接），
+// **省略逐条 verdict 核验**（direct 档无审查 receipt，verification 无生产者——诚实降级 §八.5）。
+import { evaluateSecurityBaseline } from './security-baseline.mjs';
+
+export function checkSecurityBaselineLight(changeDir) {
+  return evaluateSecurityBaseline(changeDir, 'light');
+}