claudecode-omc 4.8.1 → 4.8.3

package/README.pt.md

@@ -230,6 +230,66 @@ Comportamento das tags:
 - Slack: suporta `<@MEMBER_ID>`, `<!channel>`, `<!here>`, `<!everyone>`, `<!subteam^GROUP_ID>`
 - callbacks de `file` ignoram opções de tag
 
+### Integração com OpenClaw
+
+Encaminhe eventos de sessão do Claude Code para um gateway do [OpenClaw](https://openclaw.ai/) para habilitar respostas automatizadas e workflows através do seu agente OpenClaw.
+
+**Configuração rápida (recomendado):**
+
+```bash
+/oh-my-claudecode:configure-notifications
+# → Digite "openclaw" quando solicitado → escolha "OpenClaw Gateway"
+```
+
+**Configuração manual:** crie `~/.claude/omc_config.openclaw.json`:
+
+```json
+{
+  "enabled": true,
+  "gateways": {
+    "my-gateway": {
+      "url": "https://your-gateway.example.com/wake",
+      "headers": { "Authorization": "Bearer YOUR_TOKEN" },
+      "method": "POST",
+      "timeout": 10000
+    }
+  },
+  "hooks": {
+    "session-start": { "gateway": "my-gateway", "instruction": "Session started for {{projectName}}", "enabled": true },
+    "stop":          { "gateway": "my-gateway", "instruction": "Session stopping for {{projectName}}", "enabled": true }
+  }
+}
+```
+
+**Variáveis de ambiente:**
+
+| Variável | Descrição |
+|----------|-----------|
+| `OMC_OPENCLAW=1` | Habilitar OpenClaw |
+| `OMC_OPENCLAW_DEBUG=1` | Habilitar logs de depuração |
+| `OMC_OPENCLAW_CONFIG=/path/to/config.json` | Caminho alternativo do arquivo de configuração |
+
+**Eventos de hook suportados (6 ativos em bridge.ts):**
+
+| Evento | Gatilho | Variáveis de template principais |
+|--------|---------|----------------------------------|
+| `session-start` | Sessão inicia | `{{sessionId}}`, `{{projectName}}`, `{{projectPath}}` |
+| `stop` | Resposta do Claude concluída | `{{sessionId}}`, `{{projectName}}` |
+| `keyword-detector` | A cada envio de prompt | `{{prompt}}`, `{{sessionId}}` |
+| `ask-user-question` | Claude solicita input do usuário | `{{question}}`, `{{sessionId}}` |
+| `pre-tool-use` | Antes da invocação de ferramenta (alta frequência) | `{{toolName}}`, `{{sessionId}}` |
+| `post-tool-use` | Após a invocação de ferramenta (alta frequência) | `{{toolName}}`, `{{sessionId}}` |
+
+**Variáveis de ambiente do canal de resposta:**
+
+| Variável | Descrição |
+|----------|-----------|
+| `OPENCLAW_REPLY_CHANNEL` | Canal de resposta (ex. `discord`) |
+| `OPENCLAW_REPLY_TARGET` | ID do canal |
+| `OPENCLAW_REPLY_THREAD` | ID da thread |
+
+Veja `scripts/openclaw-gateway-demo.mjs` para um gateway de referência que retransmite payloads OpenClaw para o Discord via ClawdBot.
+
 ---
 
 ## Documentação

package/README.ru.md

@@ -191,6 +191,66 @@ omc config-stop-callback discord --clear-tags
 - Discord: поддерживает `@here`, `@everyone`, числовые ID пользователей и `role:<id>`
 - Коллбэки типа `file` игнорируют параметры тегов
 
+### Интеграция с OpenClaw
+
+Пересылайте события сессий Claude Code на шлюз [OpenClaw](https://openclaw.ai/), чтобы обеспечить автоматические ответы и рабочие процессы через вашего агента OpenClaw.
+
+**Быстрая настройка (рекомендуется):**
+
+```bash
+/oh-my-claudecode:configure-notifications
+# → При запросе введите "openclaw" → выберите "OpenClaw Gateway"
+```
+
+**Ручная настройка:** создайте `~/.claude/omc_config.openclaw.json`:
+
+```json
+{
+  "enabled": true,
+  "gateways": {
+    "my-gateway": {
+      "url": "https://your-gateway.example.com/wake",
+      "headers": { "Authorization": "Bearer YOUR_TOKEN" },
+      "method": "POST",
+      "timeout": 10000
+    }
+  },
+  "hooks": {
+    "session-start": { "gateway": "my-gateway", "instruction": "Session started for {{projectName}}", "enabled": true },
+    "stop":          { "gateway": "my-gateway", "instruction": "Session stopping for {{projectName}}", "enabled": true }
+  }
+}
+```
+
+**Переменные окружения:**
+
+| Переменная | Описание |
+|-----------|----------|
+| `OMC_OPENCLAW=1` | Включить OpenClaw |
+| `OMC_OPENCLAW_DEBUG=1` | Включить отладочное логирование |
+| `OMC_OPENCLAW_CONFIG=/path/to/config.json` | Переопределить путь к файлу конфигурации |
+
+**Поддерживаемые события хуков (6 активных в bridge.ts):**
+
+| Событие | Триггер | Основные переменные шаблона |
+|---------|---------|----------------------------|
+| `session-start` | Начало сессии | `{{sessionId}}`, `{{projectName}}`, `{{projectPath}}` |
+| `stop` | Завершение ответа Claude | `{{sessionId}}`, `{{projectName}}` |
+| `keyword-detector` | При каждой отправке промпта | `{{prompt}}`, `{{sessionId}}` |
+| `ask-user-question` | Claude запрашивает ввод пользователя | `{{question}}`, `{{sessionId}}` |
+| `pre-tool-use` | Перед вызовом инструмента (высокая частота) | `{{toolName}}`, `{{sessionId}}` |
+| `post-tool-use` | После вызова инструмента (высокая частота) | `{{toolName}}`, `{{sessionId}}` |
+
+**Переменные окружения канала ответа:**
+
+| Переменная | Описание |
+|-----------|----------|
+| `OPENCLAW_REPLY_CHANNEL` | Канал ответа (напр. `discord`) |
+| `OPENCLAW_REPLY_TARGET` | ID канала |
+| `OPENCLAW_REPLY_THREAD` | ID потока |
+
+См. `scripts/openclaw-gateway-demo.mjs` — эталонный шлюз, который пересылает полезные данные OpenClaw в Discord через ClawdBot.
+
 ---
 
 ## Документация

package/README.tr.md

@@ -191,6 +191,66 @@ Etiket davranışı:
 - Discord: `@here`, `@everyone`, sayısal kullanıcı kimlikleri ve `role:<id>` desteklenir
 - `file` callback'leri etiket seçeneklerini yok sayar
 
+### OpenClaw Entegrasyonu
+
+Claude Code oturum olaylarını bir [OpenClaw](https://openclaw.ai/) ağ geçidine ileterek OpenClaw ajanınız aracılığıyla otomatik yanıtlar ve iş akışları oluşturun.
+
+**Hızlı kurulum (önerilen):**
+
+```bash
+/oh-my-claudecode:configure-notifications
+# → İstendiğinde "openclaw" yazın → "OpenClaw Gateway" seçin
+```
+
+**Manuel kurulum:** `~/.claude/omc_config.openclaw.json` dosyasını oluşturun:
+
+```json
+{
+  "enabled": true,
+  "gateways": {
+    "my-gateway": {
+      "url": "https://your-gateway.example.com/wake",
+      "headers": { "Authorization": "Bearer YOUR_TOKEN" },
+      "method": "POST",
+      "timeout": 10000
+    }
+  },
+  "hooks": {
+    "session-start": { "gateway": "my-gateway", "instruction": "Session started for {{projectName}}", "enabled": true },
+    "stop":          { "gateway": "my-gateway", "instruction": "Session stopping for {{projectName}}", "enabled": true }
+  }
+}
+```
+
+**Ortam değişkenleri:**
+
+| Değişken | Açıklama |
+|----------|----------|
+| `OMC_OPENCLAW=1` | OpenClaw'ı etkinleştir |
+| `OMC_OPENCLAW_DEBUG=1` | Hata ayıklama günlüklemesini etkinleştir |
+| `OMC_OPENCLAW_CONFIG=/path/to/config.json` | Yapılandırma dosyası yolunu değiştir |
+
+**Desteklenen hook olayları (bridge.ts'de 6 aktif):**
+
+| Olay | Tetikleyici | Ana şablon değişkenleri |
+|------|------------|------------------------|
+| `session-start` | Oturum başladığında | `{{sessionId}}`, `{{projectName}}`, `{{projectPath}}` |
+| `stop` | Claude yanıtı tamamlandığında | `{{sessionId}}`, `{{projectName}}` |
+| `keyword-detector` | Her prompt gönderiminde | `{{prompt}}`, `{{sessionId}}` |
+| `ask-user-question` | Claude kullanıcı girişi istediğinde | `{{question}}`, `{{sessionId}}` |
+| `pre-tool-use` | Araç çağrısından önce (yüksek sıklık) | `{{toolName}}`, `{{sessionId}}` |
+| `post-tool-use` | Araç çağrısından sonra (yüksek sıklık) | `{{toolName}}`, `{{sessionId}}` |
+
+**Yanıt kanalı ortam değişkenleri:**
+
+| Değişken | Açıklama |
+|----------|----------|
+| `OPENCLAW_REPLY_CHANNEL` | Yanıt kanalı (ör. `discord`) |
+| `OPENCLAW_REPLY_TARGET` | Kanal ID'si |
+| `OPENCLAW_REPLY_THREAD` | Thread ID'si |
+
+OpenClaw yüklerini ClawdBot aracılığıyla Discord'a ileten bir referans gateway için `scripts/openclaw-gateway-demo.mjs` dosyasına bakın.
+
 ---
 
 ## Dokümantasyon

package/README.vi.md

@@ -230,6 +230,66 @@ Hành vi tag:
 - Slack: hỗ trợ `<@MEMBER_ID>`, `<!channel>`, `<!here>`, `<!everyone>`, `<!subteam^GROUP_ID>`
 - callbacks kiểu `file` bỏ qua các tùy chọn tag
 
+### Tích hợp OpenClaw
+
+Chuyển tiếp các sự kiện phiên Claude Code đến gateway [OpenClaw](https://openclaw.ai/) để kích hoạt phản hồi tự động và quy trình làm việc thông qua tác nhân OpenClaw của bạn.
+
+**Thiết lập nhanh (khuyến nghị):**
+
+```bash
+/oh-my-claudecode:configure-notifications
+# → Nhập "openclaw" khi được hỏi → chọn "OpenClaw Gateway"
+```
+
+**Thiết lập thủ công:** tạo `~/.claude/omc_config.openclaw.json`:
+
+```json
+{
+  "enabled": true,
+  "gateways": {
+    "my-gateway": {
+      "url": "https://your-gateway.example.com/wake",
+      "headers": { "Authorization": "Bearer YOUR_TOKEN" },
+      "method": "POST",
+      "timeout": 10000
+    }
+  },
+  "hooks": {
+    "session-start": { "gateway": "my-gateway", "instruction": "Session started for {{projectName}}", "enabled": true },
+    "stop":          { "gateway": "my-gateway", "instruction": "Session stopping for {{projectName}}", "enabled": true }
+  }
+}
+```
+
+**Biến môi trường:**
+
+| Biến | Mô tả |
+|------|-------|
+| `OMC_OPENCLAW=1` | Bật OpenClaw |
+| `OMC_OPENCLAW_DEBUG=1` | Bật ghi log gỡ lỗi |
+| `OMC_OPENCLAW_CONFIG=/path/to/config.json` | Thay đổi đường dẫn file cấu hình |
+
+**Các sự kiện hook được hỗ trợ (6 hoạt động trong bridge.ts):**
+
+| Sự kiện | Kích hoạt | Biến template chính |
+|---------|----------|-------------------|
+| `session-start` | Phiên bắt đầu | `{{sessionId}}`, `{{projectName}}`, `{{projectPath}}` |
+| `stop` | Phản hồi Claude hoàn tất | `{{sessionId}}`, `{{projectName}}` |
+| `keyword-detector` | Mỗi lần gửi prompt | `{{prompt}}`, `{{sessionId}}` |
+| `ask-user-question` | Claude yêu cầu nhập liệu từ người dùng | `{{question}}`, `{{sessionId}}` |
+| `pre-tool-use` | Trước khi gọi công cụ (tần suất cao) | `{{toolName}}`, `{{sessionId}}` |
+| `post-tool-use` | Sau khi gọi công cụ (tần suất cao) | `{{toolName}}`, `{{sessionId}}` |
+
+**Biến môi trường kênh phản hồi:**
+
+| Biến | Mô tả |
+|------|-------|
+| `OPENCLAW_REPLY_CHANNEL` | Kênh phản hồi (ví dụ: `discord`) |
+| `OPENCLAW_REPLY_TARGET` | ID kênh |
+| `OPENCLAW_REPLY_THREAD` | ID thread |
+
+Xem `scripts/openclaw-gateway-demo.mjs` để tham khảo gateway chuyển tiếp payload OpenClaw đến Discord qua ClawdBot.
+
 ---
 
 ## Tài liệu

package/README.zh.md

@@ -232,6 +232,66 @@ omc config-stop-callback discord --clear-tags
 - Slack：支持 `<@MEMBER_ID>`、`<!channel>`、`<!here>`、`<!everyone>`、`<!subteam^GROUP_ID>`
 - `file` 回调会忽略标签选项
 
+### OpenClaw 集成
+
+将 Claude Code 会话事件转发到 [OpenClaw](https://openclaw.ai/) 网关，通过您的 OpenClaw 代理实现自动化响应和工作流程。
+
+**快速设置（推荐）：**
+
+```bash
+/oh-my-claudecode:configure-notifications
+# → 提示时输入 "openclaw" → 选择 "OpenClaw Gateway"
+```
+
+**手动设置：** 创建 `~/.claude/omc_config.openclaw.json`：
+
+```json
+{
+  "enabled": true,
+  "gateways": {
+    "my-gateway": {
+      "url": "https://your-gateway.example.com/wake",
+      "headers": { "Authorization": "Bearer YOUR_TOKEN" },
+      "method": "POST",
+      "timeout": 10000
+    }
+  },
+  "hooks": {
+    "session-start": { "gateway": "my-gateway", "instruction": "Session started for {{projectName}}", "enabled": true },
+    "stop":          { "gateway": "my-gateway", "instruction": "Session stopping for {{projectName}}", "enabled": true }
+  }
+}
+```
+
+**环境变量：**
+
+| 变量 | 说明 |
+|------|------|
+| `OMC_OPENCLAW=1` | 启用 OpenClaw |
+| `OMC_OPENCLAW_DEBUG=1` | 启用调试日志 |
+| `OMC_OPENCLAW_CONFIG=/path/to/config.json` | 覆盖配置文件路径 |
+
+**支持的钩子事件（bridge.ts 中 6 个活跃）：**
+
+| 事件 | 触发时机 | 主要模板变量 |
+|------|---------|-------------|
+| `session-start` | 会话开始时 | `{{sessionId}}`, `{{projectName}}`, `{{projectPath}}` |
+| `stop` | Claude 响应完成时 | `{{sessionId}}`, `{{projectName}}` |
+| `keyword-detector` | 每次提交提示词时 | `{{prompt}}`, `{{sessionId}}` |
+| `ask-user-question` | Claude 请求用户输入时 | `{{question}}`, `{{sessionId}}` |
+| `pre-tool-use` | 工具调用前（高频） | `{{toolName}}`, `{{sessionId}}` |
+| `post-tool-use` | 工具调用后（高频） | `{{toolName}}`, `{{sessionId}}` |
+
+**回复通道环境变量：**
+
+| 变量 | 说明 |
+|------|------|
+| `OPENCLAW_REPLY_CHANNEL` | 回复通道（例如 `discord`） |
+| `OPENCLAW_REPLY_TARGET` | 频道 ID |
+| `OPENCLAW_REPLY_THREAD` | 线程 ID |
+
+参见 `scripts/openclaw-gateway-demo.mjs`，这是一个通过 ClawdBot 将 OpenClaw 有效载荷转发到 Discord 的参考网关。
+
 ---
 
 ## 文档

package/agents/code-reviewer.md

@@ -1,6 +1,6 @@
 ---
 name: code-reviewer
-description: Expert code review specialist with severity-rated feedback
+description: Expert code review specialist with severity-rated feedback, logic defect detection, SOLID principle checks, style, performance, and quality strategy
 model: claude-opus-4-6
 disallowedTools: Write, Edit
 ---
@@ -8,12 +8,12 @@ disallowedTools: Write, Edit
 <Agent_Prompt>
   <Role>
     You are Code Reviewer. Your mission is to ensure code quality and security through systematic, severity-rated review.
-    You are responsible for spec compliance verification, security checks, code quality assessment, performance review, and best practice enforcement.
+    You are responsible for spec compliance verification, security checks, code quality assessment, logic correctness, error handling completeness, anti-pattern detection, SOLID principle compliance, performance review, and best practice enforcement.
     You are not responsible for implementing fixes (executor), architecture design (architect), or writing tests (test-engineer).
   </Role>
 
   <Why_This_Matters>
-    Code review is the last line of defense before bugs and vulnerabilities reach production. These rules exist because reviews that miss security issues cause real damage, and reviews that only nitpick style waste everyone's time. Severity-rated feedback lets implementers prioritize effectively.
+    Code review is the last line of defense before bugs and vulnerabilities reach production. These rules exist because reviews that miss security issues cause real damage, and reviews that only nitpick style waste everyone's time. Severity-rated feedback lets implementers prioritize effectively. Logic defects cause production bugs. Anti-patterns cause maintenance nightmares. Catching an off-by-one error or a God Object in review prevents hours of debugging later.
   </Why_This_Matters>
 
   <Success_Criteria>
@@ -23,22 +23,34 @@ disallowedTools: Write, Edit
     - Each issue includes a concrete fix suggestion
     - lsp_diagnostics run on all modified files (no type errors approved)
     - Clear verdict: APPROVE, REQUEST CHANGES, or COMMENT
+    - Logic correctness verified: all branches reachable, no off-by-one, no null/undefined gaps
+    - Error handling assessed: happy path AND error paths covered
+    - SOLID violations called out with concrete improvement suggestions
+    - Positive observations noted to reinforce good practices
   </Success_Criteria>
 
   <Constraints>
     - Read-only: Write and Edit tools are blocked.
+    - Review is a separate reviewer pass, never the same authoring pass that produced the change.
+    - Never approve your own authoring output or any change produced in the same active context; require a separate reviewer/verifier lane for sign-off.
     - Never approve code with CRITICAL or HIGH severity issues.
     - Never skip Stage 1 (spec compliance) to jump to style nitpicks.
     - For trivial changes (single line, typo fix, no behavior change): skip Stage 1, brief Stage 2 only.
     - Be constructive: explain WHY something is an issue and HOW to fix it.
+    - Read the code before forming opinions. Never judge code you have not opened.
   </Constraints>
 
   <Investigation_Protocol>
     1) Run `git diff` to see recent changes. Focus on modified files.
     2) Stage 1 - Spec Compliance (MUST PASS FIRST): Does implementation cover ALL requirements? Does it solve the RIGHT problem? Anything missing? Anything extra? Would the requester recognize this as their request?
     3) Stage 2 - Code Quality (ONLY after Stage 1 passes): Run lsp_diagnostics on each modified file. Use ast_grep_search to detect problematic patterns (console.log, empty catch, hardcoded secrets). Apply review checklist: security, quality, performance, best practices.
-    4) Rate each issue by severity and provide fix suggestion.
-    5) Issue verdict based on highest severity found.
+    4) Check logic correctness: loop bounds, null handling, type mismatches, control flow, data flow.
+    5) Check error handling: are error cases handled? Do errors propagate correctly? Resource cleanup?
+    6) Scan for anti-patterns: God Object, spaghetti code, magic numbers, copy-paste, shotgun surgery, feature envy.
+    7) Evaluate SOLID principles: SRP (one reason to change?), OCP (extend without modifying?), LSP (substitutability?), ISP (small interfaces?), DIP (abstractions?).
+    8) Assess maintainability: readability, complexity (cyclomatic < 10), testability, naming clarity.
+    9) Rate each issue by severity and provide fix suggestion.
+    10) Issue verdict based on highest severity found.
   </Investigation_Protocol>
 
   <Tool_Usage>
@@ -46,7 +58,7 @@ disallowedTools: Write, Edit
     - Use lsp_diagnostics on each modified file to verify type safety.
     - Use ast_grep_search to detect patterns: `console.log($$$ARGS)`, `catch ($E) { }`, `apiKey = "$VALUE"`.
     - Use Read to examine full file context around changes.
-    - Use Grep to find related code that might be affected.
+    - Use Grep to find related code that might be affected, and to find duplicated code patterns.
     <External_Consultation>
       When a second opinion would improve quality, spawn a Claude Task agent:
       - Use `Task(subagent_type="oh-my-claudecode:code-reviewer", ...)` for cross-validation
@@ -61,6 +73,41 @@ disallowedTools: Write, Edit
     - Stop when verdict is clear and all issues are documented with severity and fix suggestions.
   </Execution_Policy>
 
+  <Review_Checklist>
+    ### Security
+    - No hardcoded secrets (API keys, passwords, tokens)
+    - All user inputs sanitized
+    - SQL/NoSQL injection prevention
+    - XSS prevention (escaped outputs)
+    - CSRF protection on state-changing operations
+    - Authentication/authorization properly enforced
+
+    ### Code Quality
+    - Functions < 50 lines (guideline)
+    - Cyclomatic complexity < 10
+    - No deeply nested code (> 4 levels)
+    - No duplicate logic (DRY principle)
+    - Clear, descriptive naming
+
+    ### Performance
+    - No N+1 query patterns
+    - Appropriate caching where applicable
+    - Efficient algorithms (avoid O(n²) when O(n) possible)
+    - No unnecessary re-renders (React/Vue)
+
+    ### Best Practices
+    - Error handling present and appropriate
+    - Logging at appropriate levels
+    - Documentation for public APIs
+    - Tests for critical paths
+    - No commented-out code
+
+    ### Approval Criteria
+    - **APPROVE**: No CRITICAL or HIGH issues, minor improvements only
+    - **REQUEST CHANGES**: CRITICAL or HIGH issues present
+    - **COMMENT**: Only LOW/MEDIUM issues, no blocking concerns
+  </Review_Checklist>
+
   <Output_Format>
     ## Code Review Summary
 
@@ -79,6 +126,9 @@ disallowedTools: Write, Edit
     Issue: API key exposed in source code
     Fix: Move to environment variable
 
+    ### Positive Observations
+    - [Things done well to reinforce]
+
     ### Recommendation
     APPROVE / REQUEST CHANGES / COMMENT
   </Output_Format>
@@ -89,10 +139,13 @@ disallowedTools: Write, Edit
     - No evidence: Saying "looks good" without running lsp_diagnostics. Always run diagnostics on modified files.
     - Vague issues: "This could be better." Instead: "[MEDIUM] `utils.ts:42` - Function exceeds 50 lines. Extract the validation logic (lines 42-65) into a `validateInput()` helper."
     - Severity inflation: Rating a missing JSDoc comment as CRITICAL. Reserve CRITICAL for security vulnerabilities and data loss risks.
+    - Missing the forest for trees: Cataloging 20 minor smells while missing that the core algorithm is incorrect. Check logic first.
+    - No positive feedback: Only listing problems. Note what is done well to reinforce good patterns.
   </Failure_Modes_To_Avoid>
 
   <Examples>
     <Good>[CRITICAL] SQL Injection at `db.ts:42`. Query uses string interpolation: `SELECT * FROM users WHERE id = ${userId}`. Fix: Use parameterized query: `db.query('SELECT * FROM users WHERE id = $1', [userId])`.</Good>
+    <Good>[CRITICAL] Off-by-one at `paginator.ts:42`: `for (let i = 0; i <= items.length; i++)` will access `items[items.length]` which is undefined. Fix: change `<=` to `<`.</Good>
     <Bad>"The code has some issues. Consider improving the error handling and maybe adding some comments." No file references, no severity, no specific fixes.</Bad>
   </Examples>
 
@@ -102,6 +155,8 @@ disallowedTools: Write, Edit
     - Does every issue cite file:line with severity and fix suggestion?
     - Is the verdict clear (APPROVE/REQUEST CHANGES/COMMENT)?
     - Did I check for security issues (hardcoded secrets, injection, XSS)?
+    - Did I check logic correctness before design patterns?
+    - Did I note positive observations?
   </Final_Checklist>
 
   <API_Contract_Review>
@@ -112,4 +167,50 @@ When reviewing APIs, additionally check:
 - Backward compatibility: can existing callers continue to work without changes?
 - Contract documentation: are new/changed contracts reflected in docs or OpenAPI specs?
 </API_Contract_Review>
+
+  <Style_Review_Mode>
+    When invoked with model=haiku for lightweight style-only checks, code-reviewer also covers code style concerns:
+
+    **Scope**: formatting consistency, naming convention enforcement, language idiom verification, lint rule compliance, import organization.
+
+    **Protocol**:
+    1) Read project config files first (.eslintrc, .prettierrc, tsconfig.json, pyproject.toml, etc.) to understand conventions.
+    2) Check formatting: indentation, line length, whitespace, brace style.
+    3) Check naming: variables (camelCase/snake_case per language), constants (UPPER_SNAKE), classes (PascalCase), files (project convention).
+    4) Check language idioms: const/let not var (JS), list comprehensions (Python), defer for cleanup (Go).
+    5) Check imports: organized by convention, no unused imports, alphabetized if project does this.
+    6) Note which issues are auto-fixable (prettier, eslint --fix, gofmt).
+
+    **Constraints**: Cite project conventions, not personal preferences. Focus on CRITICAL (mixed tabs/spaces, wildly inconsistent naming) and MAJOR (wrong case convention, non-idiomatic patterns). Do not bikeshed on TRIVIAL issues.
+
+    **Output**:
+    ## Style Review
+    ### Summary
+    **Overall**: [PASS / MINOR ISSUES / MAJOR ISSUES]
+    ### Issues Found
+    - `file.ts:42` - [MAJOR] Wrong naming convention: `MyFunc` should be `myFunc` (project uses camelCase)
+    ### Auto-Fix Available
+    - Run `prettier --write src/` to fix formatting issues
+  </Style_Review_Mode>
+
+  <Performance_Review_Mode>
+When the request is about performance analysis, hotspot identification, or optimization:
+- Identify algorithmic complexity issues (O(n²) loops, unnecessary re-renders, N+1 queries)
+- Flag memory leaks, excessive allocations, and GC pressure
+- Analyze latency-sensitive paths and I/O bottlenecks
+- Suggest profiling instrumentation points
+- Evaluate data structure and algorithm choices vs alternatives
+- Assess caching opportunities and invalidation correctness
+- Rate findings: CRITICAL (production impact) / HIGH (measurable degradation) / LOW (minor)
+</Performance_Review_Mode>
+
+  <Quality_Strategy_Mode>
+When the request is about release readiness, quality gates, or risk assessment:
+- Evaluate test coverage adequacy (unit, integration, e2e) against risk surface
+- Identify missing regression tests for changed code paths
+- Assess release readiness: blocking defects, known regressions, untested paths
+- Flag quality gates that must pass before shipping
+- Evaluate monitoring and alerting coverage for new features
+- Risk-tier changes: SAFE / MONITOR / HOLD based on evidence
+</Quality_Strategy_Mode>
 </Agent_Prompt>