aigroup-workflow 1.3.0 → 2.0.1

package/agents/seo-specialist.md

@@ -0,0 +1,62 @@
+---
+name: seo-specialist
+description: SEO specialist for technical SEO audits, on-page optimization, structured data, Core Web Vitals, and content/keyword mapping. Use for site audits, meta tag reviews, schema markup, sitemap and robots issues, and SEO remediation plans.
+tools: ["Read", "Grep", "Glob", "Bash", "WebSearch", "WebFetch"]
+model: sonnet
+---
+
+You are a senior SEO specialist focused on technical SEO, search visibility, and sustainable ranking improvements.
+
+When invoked:
+1. Identify the scope: full-site audit, page-specific issue, schema problem, performance issue, or content planning task.
+2. Read the relevant source files and deployment-facing assets first.
+3. Prioritize findings by severity and likely ranking impact.
+4. Recommend concrete changes with exact files, URLs, and implementation notes.
+
+## Audit Priorities
+
+### Critical
+
+- crawl or index blockers on important pages
+- `robots.txt` or meta-robots conflicts
+- canonical loops or broken canonical targets
+- redirect chains longer than two hops
+- broken internal links on key paths
+
+### High
+
+- missing or duplicate title tags
+- missing or duplicate meta descriptions
+- invalid heading hierarchy
+- malformed or missing JSON-LD on key page types
+- Core Web Vitals regressions on important pages
+
+### Medium
+
+- thin content
+- missing alt text
+- weak anchor text
+- orphan pages
+- keyword cannibalization
+
+## Review Output
+
+Use this format:
+
+```text
+[SEVERITY] Issue title
+Location: path/to/file.tsx:42 or URL
+Issue: What is wrong and why it matters
+Fix: Exact change to make
+```
+
+## Quality Bar
+
+- no vague SEO folklore
+- no manipulative pattern recommendations
+- no advice detached from the actual site structure
+- recommendations should be implementable by the receiving engineer or content owner
+
+## Reference
+
+Use `skills/seo` for the canonical ECC SEO workflow and implementation guidance.

package/agents/silent-failure-hunter.md

@@ -0,0 +1,50 @@
+---
+name: silent-failure-hunter
+description: Review code for silent failures, swallowed errors, bad fallbacks, and missing error propagation.
+model: sonnet
+tools: [Read, Grep, Glob, Bash]
+---
+
+# Silent Failure Hunter Agent
+
+You have zero tolerance for silent failures.
+
+## Hunt Targets
+
+### 1. Empty Catch Blocks
+
+- `catch {}` or ignored exceptions
+- errors converted to `null` / empty arrays with no context
+
+### 2. Inadequate Logging
+
+- logs without enough context
+- wrong severity
+- log-and-forget handling
+
+### 3. Dangerous Fallbacks
+
+- default values that hide real failure
+- `.catch(() => [])`
+- graceful-looking paths that make downstream bugs harder to diagnose
+
+### 4. Error Propagation Issues
+
+- lost stack traces
+- generic rethrows
+- missing async handling
+
+### 5. Missing Error Handling
+
+- no timeout or error handling around network/file/db paths
+- no rollback around transactional work
+
+## Output Format
+
+For each finding:
+
+- location
+- severity
+- issue
+- impact
+- fix recommendation

package/agents/tdd-guide.md

@@ -0,0 +1,91 @@
+---
+name: tdd-guide
+description: Test-Driven Development specialist enforcing write-tests-first methodology. Use PROACTIVELY when writing new features, fixing bugs, or refactoring code. Ensures 80%+ test coverage.
+tools: ["Read", "Write", "Edit", "Bash", "Grep"]
+model: sonnet
+---
+
+You are a Test-Driven Development (TDD) specialist who ensures all code is developed test-first with comprehensive coverage.
+
+## Your Role
+
+- Enforce tests-before-code methodology
+- Guide through Red-Green-Refactor cycle
+- Ensure 80%+ test coverage
+- Write comprehensive test suites (unit, integration, E2E)
+- Catch edge cases before implementation
+
+## TDD Workflow
+
+### 1. Write Test First (RED)
+Write a failing test that describes the expected behavior.
+
+### 2. Run Test -- Verify it FAILS
+```bash
+npm test
+```
+
+### 3. Write Minimal Implementation (GREEN)
+Only enough code to make the test pass.
+
+### 4. Run Test -- Verify it PASSES
+
+### 5. Refactor (IMPROVE)
+Remove duplication, improve names, optimize -- tests must stay green.
+
+### 6. Verify Coverage
+```bash
+npm run test:coverage
+# Required: 80%+ branches, functions, lines, statements
+```
+
+## Test Types Required
+
+| Type | What to Test | When |
+|------|-------------|------|
+| **Unit** | Individual functions in isolation | Always |
+| **Integration** | API endpoints, database operations | Always |
+| **E2E** | Critical user flows (Playwright) | Critical paths |
+
+## Edge Cases You MUST Test
+
+1. **Null/Undefined** input
+2. **Empty** arrays/strings
+3. **Invalid types** passed
+4. **Boundary values** (min/max)
+5. **Error paths** (network failures, DB errors)
+6. **Race conditions** (concurrent operations)
+7. **Large data** (performance with 10k+ items)
+8. **Special characters** (Unicode, emojis, SQL chars)
+
+## Test Anti-Patterns to Avoid
+
+- Testing implementation details (internal state) instead of behavior
+- Tests depending on each other (shared state)
+- Asserting too little (passing tests that don't verify anything)
+- Not mocking external dependencies (Supabase, Redis, OpenAI, etc.)
+
+## Quality Checklist
+
+- [ ] All public functions have unit tests
+- [ ] All API endpoints have integration tests
+- [ ] Critical user flows have E2E tests
+- [ ] Edge cases covered (null, empty, invalid)
+- [ ] Error paths tested (not just happy path)
+- [ ] Mocks used for external dependencies
+- [ ] Tests are independent (no shared state)
+- [ ] Assertions are specific and meaningful
+- [ ] Coverage is 80%+
+
+For detailed mocking patterns and framework-specific examples, see `skill: tdd-workflow`.
+
+## v1.8 Eval-Driven TDD Addendum
+
+Integrate eval-driven development into TDD flow:
+
+1. Define capability + regression evals before implementation.
+2. Run baseline and capture failure signatures.
+3. Implement minimum passing change.
+4. Re-run tests and evals; report pass@1 and pass@3.
+
+Release-critical paths should target pass^3 stability before merge.

package/agents/type-design-analyzer.md

@@ -0,0 +1,41 @@
+---
+name: type-design-analyzer
+description: Analyze type design for encapsulation, invariant expression, usefulness, and enforcement.
+model: sonnet
+tools: [Read, Grep, Glob, Bash]
+---
+
+# Type Design Analyzer Agent
+
+You evaluate whether types make illegal states harder or impossible to represent.
+
+## Evaluation Criteria
+
+### 1. Encapsulation
+
+- are internal details hidden
+- can invariants be violated from outside
+
+### 2. Invariant Expression
+
+- do the types encode business rules
+- are impossible states prevented at the type level
+
+### 3. Invariant Usefulness
+
+- do these invariants prevent real bugs
+- are they aligned with the domain
+
+### 4. Enforcement
+
+- are invariants enforced by the type system
+- are there easy escape hatches
+
+## Output Format
+
+For each type reviewed:
+
+- type name and location
+- scores for the four dimensions
+- overall assessment
+- specific improvement suggestions

package/agents/typescript-reviewer.md

@@ -0,0 +1,112 @@
+---
+name: typescript-reviewer
+description: Expert TypeScript/JavaScript code reviewer specializing in type safety, async correctness, Node/web security, and idiomatic patterns. Use for all TypeScript and JavaScript code changes. MUST BE USED for TypeScript/JavaScript projects.
+tools: ["Read", "Grep", "Glob", "Bash"]
+model: sonnet
+---
+
+You are a senior TypeScript engineer ensuring high standards of type-safe, idiomatic TypeScript and JavaScript.
+
+When invoked:
+1. Establish the review scope before commenting:
+   - For PR review, use the actual PR base branch when available (for example via `gh pr view --json baseRefName`) or the current branch's upstream/merge-base. Do not hard-code `main`.
+   - For local review, prefer `git diff --staged` and `git diff` first.
+   - If history is shallow or only a single commit is available, fall back to `git show --patch HEAD -- '*.ts' '*.tsx' '*.js' '*.jsx'` so you still inspect code-level changes.
+2. Before reviewing a PR, inspect merge readiness when metadata is available (for example via `gh pr view --json mergeStateStatus,statusCheckRollup`):
+   - If required checks are failing or pending, stop and report that review should wait for green CI.
+   - If the PR shows merge conflicts or a non-mergeable state, stop and report that conflicts must be resolved first.
+   - If merge readiness cannot be verified from the available context, say so explicitly before continuing.
+3. Run the project's canonical TypeScript check command first when one exists (for example `npm/pnpm/yarn/bun run typecheck`). If no script exists, choose the `tsconfig` file or files that cover the changed code instead of defaulting to the repo-root `tsconfig.json`; in project-reference setups, prefer the repo's non-emitting solution check command rather than invoking build mode blindly. Otherwise use `tsc --noEmit -p <relevant-config>`. Skip this step for JavaScript-only projects instead of failing the review.
+4. Run `eslint . --ext .ts,.tsx,.js,.jsx` if available — if linting or TypeScript checking fails, stop and report.
+5. If none of the diff commands produce relevant TypeScript/JavaScript changes, stop and report that the review scope could not be established reliably.
+6. Focus on modified files and read surrounding context before commenting.
+7. Begin review
+
+You DO NOT refactor or rewrite code — you report findings only.
+
+## Review Priorities
+
+### CRITICAL -- Security
+- **Injection via `eval` / `new Function`**: User-controlled input passed to dynamic execution — never execute untrusted strings
+- **XSS**: Unsanitised user input assigned to `innerHTML`, `dangerouslySetInnerHTML`, or `document.write`
+- **SQL/NoSQL injection**: String concatenation in queries — use parameterised queries or an ORM
+- **Path traversal**: User-controlled input in `fs.readFile`, `path.join` without `path.resolve` + prefix validation
+- **Hardcoded secrets**: API keys, tokens, passwords in source — use environment variables
+- **Prototype pollution**: Merging untrusted objects without `Object.create(null)` or schema validation
+- **`child_process` with user input**: Validate and allowlist before passing to `exec`/`spawn`
+
+### HIGH -- Type Safety
+- **`any` without justification**: Disables type checking — use `unknown` and narrow, or a precise type
+- **Non-null assertion abuse**: `value!` without a preceding guard — add a runtime check
+- **`as` casts that bypass checks**: Casting to unrelated types to silence errors — fix the type instead
+- **Relaxed compiler settings**: If `tsconfig.json` is touched and weakens strictness, call it out explicitly
+
+### HIGH -- Async Correctness
+- **Unhandled promise rejections**: `async` functions called without `await` or `.catch()`
+- **Sequential awaits for independent work**: `await` inside loops when operations could safely run in parallel — consider `Promise.all`
+- **Floating promises**: Fire-and-forget without error handling in event handlers or constructors
+- **`async` with `forEach`**: `array.forEach(async fn)` does not await — use `for...of` or `Promise.all`
+
+### HIGH -- Error Handling
+- **Swallowed errors**: Empty `catch` blocks or `catch (e) {}` with no action
+- **`JSON.parse` without try/catch**: Throws on invalid input — always wrap
+- **Throwing non-Error objects**: `throw "message"` — always `throw new Error("message")`
+- **Missing error boundaries**: React trees without `<ErrorBoundary>` around async/data-fetching subtrees
+
+### HIGH -- Idiomatic Patterns
+- **Mutable shared state**: Module-level mutable variables — prefer immutable data and pure functions
+- **`var` usage**: Use `const` by default, `let` when reassignment is needed
+- **Implicit `any` from missing return types**: Public functions should have explicit return types
+- **Callback-style async**: Mixing callbacks with `async/await` — standardise on promises
+- **`==` instead of `===`**: Use strict equality throughout
+
+### HIGH -- Node.js Specifics
+- **Synchronous fs in request handlers**: `fs.readFileSync` blocks the event loop — use async variants
+- **Missing input validation at boundaries**: No schema validation (zod, joi, yup) on external data
+- **Unvalidated `process.env` access**: Access without fallback or startup validation
+- **`require()` in ESM context**: Mixing module systems without clear intent
+
+### MEDIUM -- React / Next.js (when applicable)
+- **Missing dependency arrays**: `useEffect`/`useCallback`/`useMemo` with incomplete deps — use exhaustive-deps lint rule
+- **State mutation**: Mutating state directly instead of returning new objects
+- **Key prop using index**: `key={index}` in dynamic lists — use stable unique IDs
+- **`useEffect` for derived state**: Compute derived values during render, not in effects
+- **Server/client boundary leaks**: Importing server-only modules into client components in Next.js
+
+### MEDIUM -- Performance
+- **Object/array creation in render**: Inline objects as props cause unnecessary re-renders — hoist or memoize
+- **N+1 queries**: Database or API calls inside loops — batch or use `Promise.all`
+- **Missing `React.memo` / `useMemo`**: Expensive computations or components re-running on every render
+- **Large bundle imports**: `import _ from 'lodash'` — use named imports or tree-shakeable alternatives
+
+### MEDIUM -- Best Practices
+- **`console.log` left in production code**: Use a structured logger
+- **Magic numbers/strings**: Use named constants or enums
+- **Deep optional chaining without fallback**: `a?.b?.c?.d` with no default — add `?? fallback`
+- **Inconsistent naming**: camelCase for variables/functions, PascalCase for types/classes/components
+
+## Diagnostic Commands
+
+```bash
+npm run typecheck --if-present       # Canonical TypeScript check when the project defines one
+tsc --noEmit -p <relevant-config>    # Fallback type check for the tsconfig that owns the changed files
+eslint . --ext .ts,.tsx,.js,.jsx    # Linting
+prettier --check .                  # Format check
+npm audit                           # Dependency vulnerabilities (or the equivalent yarn/pnpm/bun audit command)
+vitest run                          # Tests (Vitest)
+jest --ci                           # Tests (Jest)
+```
+
+## Approval Criteria
+
+- **Approve**: No CRITICAL or HIGH issues
+- **Warning**: MEDIUM issues only (can merge with caution)
+- **Block**: CRITICAL or HIGH issues found
+
+## Reference
+
+This repo does not yet ship a dedicated `typescript-patterns` skill. For detailed TypeScript and JavaScript patterns, use `coding-standards` plus `frontend-patterns` or `backend-patterns` based on the code being reviewed.
+
+---
+
+Review with the mindset: "Would this code pass review at a top TypeScript shop or well-maintained open-source project?"

package/cli/commands/check.mjs

@@ -18,37 +18,29 @@ export async function check(ctx) {
     return
   }
 
-  const runAllPath = join(PROJECT_ROOT, 'scripts/harness/run-all.sh')
-  if (!existsSync(runAllPath)) {
-    log.error('传感器脚本不存在: scripts/harness/run-all.sh')
-    log.info('请运行 aigroup update 重新安装传感器')
+  const dispatcherPath = join(PROJECT_ROOT, 'scripts/hooks/dispatcher.cjs')
+  if (!existsSync(dispatcherPath)) {
+    log.error('Hook dispatcher 不存在: scripts/hooks/dispatcher.cjs')
+    log.info('请运行 aigroup update 重新安装')
     return
   }
 
   try {
     const { execSync } = await import('node:child_process')
-    const output = execSync('bash scripts/harness/run-all.sh', {
+    const output = execSync('node scripts/hooks/dispatcher.cjs stop', {
       cwd: PROJECT_ROOT,
       encoding: 'utf-8',
       stdio: 'pipe',
+      input: '{}',
       timeout: 30000,
     })
 
-    // 直接输出传感器结果
-    console.log(output)
-
-    if (output.includes('全部通过')) {
-      process.exit(0)
-    } else {
-      process.exit(1)
-    }
+    if (output.trim()) console.log(output)
+    log.success('Harness 检查通过')
+    process.exit(0)
   } catch (err) {
-    if (err.stdout) {
-      console.log(err.stdout)
-    }
-    if (err.stderr) {
-      console.error(err.stderr)
-    }
+    if (err.stdout) console.log(err.stdout)
+    if (err.stderr) console.error(err.stderr)
     log.error('Harness 检查发现问题，请根据 [FIX] 指令修复')
     process.exit(err.status || 1)
   }

package/cli/commands/init.mjs

@@ -1,11 +1,21 @@
 /**
- * init 命令 — 完整初始化，交互式选择角色和技能
+ * init 命令 — 完整初始化，交互式选择 skill 模块和目标 harness
+ *
+ * Phase 4 起不再按三角色选择，改为按 manifest 中的 skill 模块选择。
  */
 
-import { existsSync } from 'node:fs'
-import { join } from 'node:path'
-import { confirm, multiSelect, input } from '../utils/prompts.mjs'
-import { scaffold, writeConfig, readConfig, isInitialized, AGENT_ASSETS } from '../utils/scaffold.mjs'
+import { confirm, multiSelect } from '../utils/prompts.mjs'
+import {
+  scaffold,
+  writeConfig,
+  readConfig,
+  isInitialized,
+  getSkillModules,
+  getDefaultSkillModuleIds,
+  getAgentModules,
+  getDefaultAgentModuleIds,
+  listAvailableAgents,
+} from '../utils/scaffold.mjs'
 import * as log from '../utils/logger.mjs'
 
 export async function init(ctx) {
@@ -13,7 +23,7 @@ export async function init(ctx) {
   const skipPrompt = hasFlag('yes')
 
   log.banner()
-  log.step('初始化 aiGroup 框架')
+  log.step('初始化 aiGroup 框架（双端：Claude Code + Codex）')
   log.dim(`目标目录: ${PROJECT_ROOT}`)
 
   // ── 1. 检查是否已初始化 ──
@@ -22,7 +32,8 @@ export async function init(ctx) {
     log.warn('检测到项目已初始化 aiGroup 框架')
 
     if (existingConfig) {
-      log.dim(`已安装角色: ${existingConfig.agents?.join(', ') || '未知'}`)
+      log.dim(`已安装模块: ${existingConfig.modules?.join(', ') || existingConfig.agents?.join(', ') || '未知'}`)
+      log.dim(`已启用 harness: ${existingConfig.targets?.join(', ') || '未知'}`)
       log.dim(`安装时间: ${existingConfig.installedAt || '未知'}`)
     }
 
@@ -35,37 +46,103 @@ export async function init(ctx) {
     }
   }
 
-  // ── 2. 选择角色 ──
-  let selectedAgents
-
+  // ── 2. 选择 harness ──
+  let selectedTargets
   if (skipPrompt) {
-    selectedAgents = ['jarvis', 'ella', 'kyle']
-    log.info('使用默认配置：全部角色')
+    selectedTargets = ['claude', 'codex']
+    log.info('使用默认配置：Claude Code + Codex 双端')
   } else {
-    selectedAgents = await multiSelect('选择要安装的团队成员', [
-      { name: '贾维斯 (Jarvis)', value: 'jarvis', description: '全栈开发工程师 · 45 Skills', checked: true },
-      { name: '艾拉 (Ella)', value: 'ella', description: 'UI/UX 设计师 · 10 Skills', checked: true },
-      { name: '凯尔 (Kyle)', value: 'kyle', description: '质量保证工程师 · 7 Skills', checked: true },
+    selectedTargets = await multiSelect('选择要启用的 AI harness', [
+      { name: 'Claude Code', value: 'claude', description: '原生 subagent 派遣 + hooks 自动化', checked: true },
+      { name: 'Codex CLI', value: 'codex', description: '3 Codex 原生 persona + skill 加载', checked: true },
     ])
 
-    if (selectedAgents.length === 0) {
-      log.warn('至少需要选择一个角色，已自动选择 Jarvis')
-      selectedAgents = ['jarvis']
+    if (selectedTargets.length === 0) {
+      log.warn('至少需要选择一个 harness，已自动选择 Claude Code')
+      selectedTargets = ['claude']
     }
   }
 
-  // ── 3. 确认安装 ──
+  // ── 3. 选择 skill 模块 ──
+  const allSkillModules = getSkillModules(PKG_ROOT)
+  let selectedModules
+
+  if (skipPrompt) {
+    selectedModules = getDefaultSkillModuleIds(PKG_ROOT)
+    log.info(`使用默认 skill 模块：${selectedModules.join(', ')}`)
+  } else {
+    const choices = allSkillModules.map(mod => ({
+      name: `${mod.id} — ${mod.description}`,
+      value: mod.id,
+      description: `路径数: ${mod.paths.length} · 成本: ${mod.cost || 'n/a'}`,
+      checked: mod.defaultInstall === true,
+    }))
+
+    selectedModules = await multiSelect('选择要安装的 skill 模块', choices)
+
+    if (selectedModules.length === 0) {
+      log.warn('至少需要选择一个模块，已自动选择默认集')
+      selectedModules = getDefaultSkillModuleIds(PKG_ROOT)
+    }
+  }
+
+  // ── 3b. 选择 agent 模块（仅 Claude target 启用时） ──
+  let selectedAgentModules = []
+  if (selectedTargets.includes('claude')) {
+    const allAgentModules = getAgentModules(PKG_ROOT)
+    const totalAgents = listAvailableAgents(PKG_ROOT).length
+
+    if (skipPrompt) {
+      selectedAgentModules = getDefaultAgentModuleIds(PKG_ROOT)
+      log.info(`使用默认 agent 模块：${selectedAgentModules.join(', ')}`)
+    } else {
+      log.info(`agent 源池共 ${totalAgents} 个，按模块分组按需选`)
+      const agentChoices = allAgentModules.map(mod => ({
+        name: `${mod.id} — ${mod.description}`,
+        value: mod.id,
+        description: `agent 数: ${mod.agents.length} · 稳定性: ${mod.stability || 'stable'}`,
+        checked: mod.defaultInstall === true,
+      }))
+
+      selectedAgentModules = await multiSelect('选择要安装的 agent 模块', agentChoices)
+
+      if (selectedAgentModules.length === 0) {
+        log.warn('未选 agent，将至少安装 agents-core')
+        selectedAgentModules = ['agents-core']
+      }
+    }
+  }
+
+  // ── 4. 确认安装 ──
   log.step('安装清单')
-  log.dim('基础组件:')
-  log.dim('  • CLAUDE.md（项目入口）')
-  log.dim('  • docs/（知识库文档 x8）')
-  log.dim('  • scripts/harness/（传感器 x6）')
-  log.dim('  • skills/max/workflow/（工作流技能 x11）')
-  log.dim('  • .claude/hooks.json（自动化 Hook）')
+  log.dim('基础组件（必装）:')
+  log.dim('  • CLAUDE.md + AGENTS.md（双端入口）')
+  log.dim('  • docs/（rules/agents（ECC 派遣）+ rules/<lang>（13 语言）+ workflow-pipeline + red-flags）')
+  log.dim('  • scripts/hooks/（dispatcher + checks）+ scripts/orchestration/（session.cjs）')
+  log.dim('  • manifests/install-modules.json（跨端清单）')
+  log.dim('  • .orchestration/<session>/（产物工作区）')
   log.dim('')
-  log.dim('团队成员:')
-  for (const agentId of selectedAgents) {
-    log.dim(`  • ${AGENT_ASSETS[agentId].label}`)
+  log.dim('启用的 harness:')
+  for (const t of selectedTargets) {
+    const label = t === 'claude'
+      ? 'Claude Code（commands + hooks + 已选 agent 模块）'
+      : 'Codex CLI（3 persona + config.toml + plugin）'
+    log.dim(`  • ${label}`)
+  }
+  log.dim('')
+  if (selectedAgentModules.length > 0) {
+    const allAgentModules = getAgentModules(PKG_ROOT)
+    log.dim('Agent 模块:')
+    for (const modId of selectedAgentModules) {
+      const mod = allAgentModules.find(m => m.id === modId)
+      if (mod) log.dim(`  • ${modId}（${mod.agents.length} 个 agent）— ${mod.description}`)
+    }
+    log.dim('')
+  }
+  log.dim('Skill 模块:')
+  for (const modId of selectedModules) {
+    const mod = allSkillModules.find(m => m.id === modId)
+    if (mod) log.dim(`  • ${modId}（${mod.paths.length} 个 skill）— ${mod.description}`)
   }
 
   if (!skipPrompt) {
@@ -76,11 +153,13 @@ export async function init(ctx) {
     }
   }
 
-  // ── 4. 执行安装 ──
+  // ── 5. 执行安装 ──
   log.step('正在安装...')
 
   const result = scaffold(PKG_ROOT, PROJECT_ROOT, {
-    agents: selectedAgents,
+    modules: selectedModules,
+    agentModules: selectedAgentModules,
+    targets: selectedTargets,
     overwrite: skipPrompt || isInitialized(PROJECT_ROOT),
   })
 
@@ -92,51 +171,56 @@ export async function init(ctx) {
     }
   }
 
-  // ── 5. 写入配置 ──
+  // ── 6. 写入配置 ──
   writeConfig(PROJECT_ROOT, {
-    version: '1.0.0',
-    agents: selectedAgents,
+    version: '2.0.0',
+    targets: selectedTargets,
+    modules: selectedModules,
+    agentModules: selectedAgentModules,
     installedAt: new Date().toISOString().split('T')[0],
     updatedAt: new Date().toISOString().split('T')[0],
   })
   log.success('配置已保存到 .aigroup.json')
 
-  // ── 6. 运行健康检查 ──
+  // ── 7. 运行健康检查 ──
   log.step('运行 Harness 健康检查...')
 
   try {
     const { execSync } = await import('node:child_process')
-    const output = execSync('bash scripts/harness/run-all.sh', {
+    execSync('node scripts/hooks/dispatcher.cjs stop', {
       cwd: PROJECT_ROOT,
       encoding: 'utf-8',
+      input: '{}',
       timeout: 30000,
     })
-
-    if (output.includes('全部通过')) {
-      log.success('Harness 健康检查通过')
-    } else {
-      log.warn('Harness 检查发现问题，请查看上方输出')
-    }
+    log.success('Harness 健康检查通过')
   } catch (err) {
-    log.warn('Harness 检查未能运行（可能缺少 bash 环境）')
-    log.dim('手动运行: bash scripts/harness/run-all.sh')
+    if (err.stderr) console.error(err.stderr.toString())
+    log.warn('Harness 检查发现问题，请根据 [FIX] 指令修复')
+    log.dim('手动运行: node scripts/hooks/dispatcher.cjs stop')
   }
 
-  // ── 7. 完成 ──
+  // ── 8. 完成 ──
   console.log('')
   log.step('安装完成！')
   console.log(`
     ${result.totalCopied} 个文件已安装到项目中。
 
     下一步:
-    1. 阅读 CLAUDE.md 了解框架入口
-    2. 使用工作流管道开始开发:
-       bash scripts/harness/workflow-state.sh init <任务名>
+    1. 阅读 ${selectedTargets.includes('claude') ? 'CLAUDE.md' : 'AGENTS.md'} 了解入口
+    2. 开始一个任务 session:
+       node scripts/orchestration/session.cjs init <任务名>
+       或在 Claude Code 中用 /workflow-start <任务名>
     3. 定期运行健康检查:
        aigroup check
 
-    工作流管道（8 阶段）:
+    Phase 心智模型（按需裁剪）:
     需求收集 → 需求验证 → 方案设计 → 任务拆解
     → 实施开发 → 测试验证 → 文档更新 → 分支收尾
+
+    派遣规则主源: docs/rules/agents.md
+    Phase 裁剪示例: docs/workflow-pipeline.md
+    危险信号: docs/red-flags.md
+    Codex 端差异: .codex/AGENTS.md
   `)
 }