@fitlab-ai/agent-infra 0.6.5 → 0.7.1

package/templates/.agents/skills/review-analysis/reference/report-template.zh-CN.md

@@ -0,0 +1,91 @@
+# 审查报告模板
+
+编写 `review-analysis.md` 或 `review-analysis-r{N}.md` 时使用本模板。
+
+## 输出模板
+
+```markdown
+# 代码审查报告
+
+- **审查轮次**：第 {review-round} 轮
+- **产物文件**：`{review-artifact}`
+- **审查输入**：
+  - `{code-artifact}`
+  - `{code-artifact}`（如存在）
+
+## 状态核对
+
+> 粘贴状态核对命令原文；每条命令以 `$ ` 开头。
+
+## 审查摘要
+
+- **审查者**：{reviewer-name}
+- **审查时间**：{timestamp}
+- **审查范围**：{file-count and major modules}
+- **总体结论**：{通过 / 需要修改 / 拒绝}
+- **发现（AI 可处理）**：0 阻塞项，0 主要，0 次要 / **env-blocked**：0
+
+## 问题清单
+
+### 阻塞项（必须修复）
+
+#### 1. {问题标题}
+**文件**：`{file-path}:{line-number}`
+**说明**：{details}
+**修复建议**：{fix suggestion}
+
+### 主要问题（建议修复）
+
+#### 1. {问题标题}
+**文件**：`{file-path}:{line-number}`
+**说明**：{details}
+**修复建议**：{fix suggestion}
+
+### 次要问题（可选改进）
+
+#### 1. {改进点}
+**文件**：`{file-path}:{line-number}`
+**建议**：{improvement suggestion}
+
+## 环境性遗留
+
+> AI agent 在本执行环境无法闭环的项；不参与下一轮 refine。维护者在 PR description 中以「待人工验证」清单承接。
+
+#### 1. {环境性项标题}
+**文件**：`{file-path}:{line-number}`（如适用）
+**说明**：{details}
+**所需环境**：{e.g. Docker 沙箱 / macOS host / 特权 root / 第三方账号}
+**待人工执行的验证步骤**：{steps for the human verifier}
+
+> 如本轮无 env-blocked 项，保留段落标题并写「（无）」。
+
+
+## 证据原文
+
+> 每条“我验证了 X”断言都要配对对应 tool output 原文；gate 仅校验本段存在和至少一行 `$ `。
+
+- 断言：{verified claim}
+```text
+$ {command}
+{raw output}
+```
+
+## 亮点
+
+- {what went well}
+
+## 与方案一致性
+
+- [ ] 实现与技术方案一致
+- [ ] 没有意外的范围扩张
+
+## 结论与建议
+
+### 审查决定
+- [ ] 通过
+- [ ] 需要修改
+- [ ] 拒绝
+
+### 下一步
+{recommended next step}
+```

package/templates/.agents/skills/review-analysis/reference/review-criteria.en.md

@@ -0,0 +1,47 @@
+# Review Criteria
+
+Read this file before reviewing requirement analysis artifacts or classifying finding severity.
+
+## Requirement Analysis Review
+
+Follow the `analysis-review` step in `.agents/workflows/feature-development.yaml`.
+
+**Required review areas**:
+- [ ] Requirement scope, goals, and non-goals are clear
+- [ ] Acceptance criteria are verifiable
+- [ ] Affected areas, dependencies, and constraints are sufficiently identified
+- [ ] Risks, edge cases, and open questions are recorded
+- [ ] The design stage has enough input to proceed
+- [ ] The analysis matches the original Issue or user request
+
+**Common anti-examples**:
+- Treating implementation design as requirement analysis and locking in technical details too early
+- Restating the Issue without adding impact scope, risks, or acceptance criteria
+- Presenting uncertain information as fact without marking assumptions or open questions
+
+## Common Review Principles
+
+1. **Strict but fair**: identify issues and acknowledge solid work
+2. **Specific**: cite exact file paths and line numbers
+3. **Actionable**: suggest a concrete fix
+4. **Severity-based**: clearly distinguish blockers, major issues, and minor issues
+
+## Environment-Blocked Classification
+
+Some findings cannot be closed by an AI agent in the current execution environment, for example:
+
+- Missing Docker / sandbox access for end-to-end validation
+- Missing a specific OS for macOS-only behavior
+- Missing third-party accounts / OAuth
+- Missing privileged operations such as root, sudo, or special network access
+
+**Decision tree**: "Can the AI agent close this item independently without changing the environment?"
+- Yes -> blocker / major / minor, based on risk
+- No -> **env-blocked** (a meta-category, not part of severity ordering)
+
+Where env-blocked items go:
+- Record them in an independent review report section named "Environment-Blocked Findings"
+- Include them at the end of the numeric summary, for example `(+ 1 env-blocked)`
+- Do **not** include them in the code-task fix loop; maintainers carry them in the PR description under manual verification
+
+Also inspect the latest requirement analysis artifact and `task.md` Activity Log so the report reflects the full analysis context.

package/templates/.agents/skills/review-analysis/reference/review-criteria.zh-CN.md

@@ -0,0 +1,47 @@
+# 审查标准
+
+在审查需求分析或划分问题严重程度之前先读取本文件。
+
+## 执行需求分析审查
+
+遵循 `.agents/workflows/feature-development.yaml` 中的 `analysis-review` 步骤。
+
+**必查范围**：
+- [ ] 需求范围、目标和非目标是否清晰
+- [ ] 验收标准是否可验证
+- [ ] 受影响区域、依赖和约束是否识别充分
+- [ ] 风险、边界情况和开放问题是否记录
+- [ ] 后续设计阶段是否有足够输入
+- [ ] 与原始 Issue / 用户需求是否一致
+
+**常见反例**：
+- 把实现方案当作需求分析，提前锁定技术细节
+- 只复述 Issue 文案，没有补充影响范围、风险和验收标准
+- 对无法确认的信息直接下结论，没有标记假设或开放问题
+
+## 通用审查原则
+
+1. **严格但公正**：既要指出问题，也要承认做得好的部分
+2. **具体**：引用准确的文件路径和行号
+3. **可执行**：给出明确可落地的修复建议
+4. **按严重程度分类**：明确区分 blocker、major 和 minor
+
+## 环境性遗留分类
+
+某些发现项是 AI agent 在本执行环境**无法闭环**的，例如：
+
+- 缺 Docker / 沙箱而无法跑端到端验证
+- 缺特定 OS（macOS-only 行为）
+- 缺第三方账号 / OAuth
+- 缺特权操作（root、sudo、特殊网络）
+
+**分类决策树**：「AI agent 能否在不改环境的前提下独立闭环这一项？」
+- 是 -> blocker / major / minor 之一（按风险定档）
+- 否 -> **env-blocked**（元类目，不参与严重程度排序）
+
+env-blocked 项的去向：
+- 写入 review 报告独立段落「环境性遗留」
+- 在数字摘要末尾附带显示（如 `(+ 1 env-blocked)`）
+- **不**进入 code-task 修复循环；维护者在 PR description 中以「待人工验证」清单形式承接
+
+同时检查最新需求分析产物和 `task.md` Activity Log，确保报告反映完整的分析上下文。

package/templates/.agents/skills/{review-task → review-code}/SKILL.en.md

@@ -1,11 +1,11 @@
 ---
-name: review-task
-description: "Review a task implementation and output a code review report"
+name: review-code
+description: "Review code implementation and output a code review report"
 ---
 
 # Code Review
 
-Review the latest implementation round and produce `review.md` or `review-r{N}.md`.
+Review the latest code round and produce `review-code.md` or `review-code-r{N}.md`.
 
 ## Boundary / Critical Rules
 
@@ -36,23 +36,27 @@ tail .agents/workspace/active/{task-id}/task.md
 
 Before the state check is complete, do not make external-state assertions such as "the code is unchanged", "tests passed", or "there are no other references", including in reasoning. This gate is only a structural floor; evidence pairing and authenticity still require the report template and review discipline.
 
+## Task id short ref
+
+> If `{task-id}` begins with `#`, follow the "SKILL parameter resolver" section of `.agents/rules/task-short-id.md`; treat `{task-id}` as the resolved full `TASK-YYYYMMDD-HHMMSS` form for every downstream command.
+
 ## Steps
 
 ### 1. Verify Prerequisites
 
 Require:
 - `.agents/workspace/active/{task-id}/task.md`
-- at least one implementation artifact: `implementation.md` or `implementation-r{N}.md`
+- at least one code artifact: `code.md` or `code-r{N}.md`
 
 ### 2. Determine Review Round
 
 Scan the task directory and record:
 - `{review-round}`
-- `{review-artifact}` as `review.md` or `review-r{N}.md`
+- `{review-artifact}` as `review-code.md` or `review-code-r{N}.md`
 
 ### 3. Read Implementation and Refinement Context
 
-Read the highest-round implementation artifact and, if present, the highest-round refinement artifact.
+Read the highest-round code artifact and, if present, the highest-round fix artifact.
 
 ### 4. Perform the Review
 
@@ -91,7 +95,7 @@ If task.md contains a valid `issue_number`, perform these sync actions (skip and
 Run the verification gate to confirm the task artifact and sync state are valid:
 
 ```bash
-node .agents/scripts/validate-artifact.js gate review-task .agents/workspace/active/{task-id} {review-artifact} --format text
+node .agents/scripts/validate-artifact.js gate review-code .agents/workspace/active/{task-id} {review-artifact} --format text
 ```
 
 Handle the result as follows:
@@ -105,6 +109,8 @@ Keep the gate output in your reply as fresh evidence. Do not claim completion wi
 
 > Execute this step only after the verification gate passes.
 
+> **Important — branch labels are not values for the verdict field**. The four labels below are user-output template categories (scenarios A/B/C/D), **not** values for the `**Overall Verdict**:` field. The field accepts exactly one of the three canonical values (`Approved` / `Changes Requested` / `Rejected`, or zh-CN `通过` / `需要修改` / `拒绝`); combined phrases like `Approved with issues` will be rejected by the verify gate.
+
 Choose exactly one branch based on the findings:
 - no blockers, no major, no minor -> approved with no issues
 - no blockers, but major or minor findings -> approved with issues
@@ -127,11 +133,11 @@ Include all TUI command formats in the next-step output. If `.agents/.airc.json`
 
 ## Notes
 
-- Round 1 uses `review.md`; later rounds use `review-r{N}.md`
+- Round 1 uses `review-code.md`; later rounds use `review-code-r{N}.md`
 - Always cite concrete file paths and line numbers in findings
 - Review severity must distinguish blockers, major issues, and minor issues
 
 ## Error Handling
 
 - Task not found: `Task {task-id} not found`
-- Missing implementation report: `Implementation report not found, please run the implement-task skill first`
+- Missing code report: `Code report not found, please run the code-task skill first`

package/templates/.agents/skills/{review-task → review-code}/SKILL.zh-CN.md

@@ -1,11 +1,11 @@
 ---
-name: review-task
-description: "审查任务实现并输出代码审查报告"
+name: review-code
+description: "审查代码实现并输出代码审查报告"
 ---
 
 # 代码审查
 
-审查最新实现轮次，并产出 `review.md` 或 `review-r{N}.md`。
+审查最新代码轮次，并产出 `review-code.md` 或 `review-code-r{N}.md`。
 
 ## 行为边界 / 关键规则
 
@@ -36,19 +36,22 @@ tail .agents/workspace/active/{task-id}/task.md
 
 状态核对完成前，禁止任何关于外部状态的断言（例如“代码没变”“测试已通过”“没有其他引用”），包括思考阶段。本门禁只提供结构下限；逐条证据配对和真实性仍需按报告模板与审查要求核对。
 
-## 执行步骤
+## 任务入参短号别名
+
+> 如果 `{task-id}` 入参以 `#` 开头，先读取 `.agents/rules/task-short-id.md` 的「SKILL 入参解析」段执行解析；后续命令视 `{task-id}` 为解析后的全长 `TASK-YYYYMMDD-HHMMSS` 形式。
 
+## 执行步骤
 ### 1. 验证前置条件
 
 要求存在：
 - `.agents/workspace/active/{task-id}/task.md`
-- 至少一个实现产物：`implementation.md` 或 `implementation-r{N}.md`
+- 至少一个实现产物：`code.md` 或 `code-r{N}.md`
 
 ### 2. 确定审查轮次
 
 扫描任务目录并记录：
 - `{review-round}`
-- 作为本轮产物的 `{review-artifact}`，格式为 `review.md` 或 `review-r{N}.md`
+- 作为本轮产物的 `{review-artifact}`，格式为 `review-code.md` 或 `review-code-r{N}.md`
 
 ### 3. 阅读实现与修复上下文
 
@@ -75,7 +78,11 @@ tail .agents/workspace/active/{task-id}/task.md
 date "+%Y-%m-%d %H:%M:%S%:z"
 ```
 
-更新 task.md，并追加：
+- `current_step`：code-review
+- `assigned_to`：{当前代理}
+- `updated_at`：{当前时间}
+- `agent_infra_version`：按 `.agents/rules/version-stamp.md` 取值
+- 追加：
 `- {YYYY-MM-DD HH:mm:ss±HH:MM} — **Code Review (Round {N})** by {agent} — Verdict: {Approved/Changes Requested/Rejected}, blockers: {n}, major: {n}, minor: {n}[ (+ {n} env-blocked)] → {artifact-filename}`
 
 env-blocked = 0 时省略括号部分；env-blocked > 0 时附加 ` (+ {n} env-blocked)`。
@@ -91,7 +98,7 @@ env-blocked = 0 时省略括号部分；env-blocked > 0 时附加 ` (+ {n} env-b
 运行完成校验，确认任务产物和同步状态符合规范：
 
 ```bash
-node .agents/scripts/validate-artifact.js gate review-task .agents/workspace/active/{task-id} {review-artifact} --format text
+node .agents/scripts/validate-artifact.js gate review-code .agents/workspace/active/{task-id} {review-artifact} --format text
 ```
 
 处理结果：
@@ -105,6 +112,8 @@ node .agents/scripts/validate-artifact.js gate review-task .agents/workspace/act
 
 > 仅在校验通过后执行本步骤。
 
+> **重要：分支名 ≠ 字段值**。以下 4 个标签是用户输出模板的分类（场景 A/B/C/D），**不是**产物 `**总体结论**：` 字段的取值。产物字段只取 3 个规范值之一（`通过` / `需要修改` / `拒绝`，或 EN 对应 `Approved` / `Changes Requested` / `Rejected`）；写成 `通过但有问题`、`通过 / 需要修改` 等组合短语会被 verify gate 拦下。
+
 必须先判断结果，再只选择一个输出分支：
 - 无 blocker、major、minor -> 通过且无问题
 - 无 blocker，但有 major 或 minor -> 通过但有问题
@@ -127,11 +136,11 @@ env-blocked 的数量不参与分支选择，仅在数字摘要末尾附带显
 
 ## 注意事项
 
-- 首轮审查使用 `review.md`，后续轮次使用 `review-r{N}.md`
+- 首轮审查使用 `review-code.md`，后续轮次使用 `review-code-r{N}.md`
 - 所有问题都要引用具体文件路径和行号
 - 严重程度必须区分 blocker、major、minor
 
 ## 错误处理
 
 - 任务未找到：`Task {task-id} not found`
-- 缺少实现报告：`Implementation report not found, please run the implement-task skill first`
+- 缺少实现报告：`Code report not found, please run the code-task skill first`

package/templates/.agents/skills/{review-task → review-code}/config/verify.en.json

@@ -1,5 +1,5 @@
 {
-  "skill": "review-task",
+  "skill": "review-code",
   "checks": {
     "task-meta": {
       "required_fields": [
@@ -12,21 +12,23 @@
         "agent_infra_version",
         "current_step",
         "assigned_to"
-      ]
+      ],
+      "expected_step": "code-review"
     },
     "artifact": {
-      "file_pattern": "review.md|review-r{N}.md",
+      "file_pattern": "review-code.md|review-code-r{N}.md",
       "required_sections": [
         "Review Summary",
         "Findings",
         "Environment-Blocked Findings",
-        "Conclusion and Recommendation",
+        "Conclusion and Recommendations",
         "State Check",
         "Evidence"
       ],
       "required_patterns": [
         "^### Approval Decision$",
-        "^\\$ "
+        "^\\$ ",
+        "^- \\*\\*Overall Verdict\\*\\*[:：]\\s*(?:通过|需要修改|拒绝|Approved|Changes Requested|Rejected)\\s*$"
       ],
       "freshness_minutes": 30
     },

package/templates/.agents/skills/{review-task → review-code}/config/verify.zh-CN.json

@@ -1,5 +1,5 @@
 {
-  "skill": "review-task",
+  "skill": "review-code",
   "checks": {
     "task-meta": {
       "required_fields": [
@@ -12,10 +12,11 @@
         "agent_infra_version",
         "current_step",
         "assigned_to"
-      ]
+      ],
+      "expected_step": "code-review"
     },
     "artifact": {
-      "file_pattern": "review.md|review-r{N}.md",
+      "file_pattern": "review-code.md|review-code-r{N}.md",
       "required_sections": [
         "审查摘要",
         "问题清单",
@@ -26,7 +27,8 @@
       ],
       "required_patterns": [
         "^### 审查决定$",
-        "^\\$ "
+        "^\\$ ",
+        "^- \\*\\*总体结论\\*\\*[:：]\\s*(?:通过|需要修改|拒绝|Approved|Changes Requested|Rejected)\\s*$"
       ],
       "freshness_minutes": 30
     },

package/templates/.agents/skills/{review-task → review-code}/reference/output-templates.en.md

@@ -2,6 +2,8 @@
 
 Read this file before presenting the final review result to the user.
 
+> This file describes the four **user reply** categories (Branches A/B/C/D) used in the "Inform User" step. It is **not** the value of the review-code artifact's `**Overall Verdict**:` field — that field is fixed to one of three canonical tokens (`Approved` / `Changes Requested` / `Rejected`, or zh-CN `通过` / `需要修改` / `拒绝`). Do not mix the two.
+
 ## Choose Exactly One Output Branch
 
 Apply these rules in order (**note: env-blocked counts do not participate in selection**):
@@ -30,7 +32,7 @@ Next step - commit the code:
   - Codex CLI: $commit
 
 [When env-blocked > 0, append this final line:]
-Reminder: env-blocked findings must be carried in the PR description as a "manual verification required" checklist and should not trigger /refine-task.
+Reminder: env-blocked findings must be carried in the PR description as a "manual verification required" checklist and should not trigger /code-task.
 ```
 
 ### Branch B: Approved with Findings
@@ -40,18 +42,18 @@ Task {task-id} review completed. Verdict: approved.
 - Blockers: 0 | Major: {n} | Minor: {n}[ | env-blocked: {n} (outside AI repair scope)]
 - Review report: .agents/workspace/active/{task-id}/{review-artifact}
 
-Next step - refine before commit (recommended):
-  - Claude Code / OpenCode: /refine-task {task-id}
-  - Gemini CLI: /agent-infra:refine-task {task-id}
-  - Codex CLI: $refine-task {task-id}
+Next step - fix before commit (recommended):
+  - Claude Code / OpenCode: /code-task {task-id}
+  - Gemini CLI: /agent-infra:code-task {task-id}
+  - Codex CLI: $code-task {task-id}
 
-Or commit directly (skip refinement):
+Or commit directly (skip fix):
   - Claude Code / OpenCode: /commit
   - Gemini CLI: /agent-infra:commit
   - Codex CLI: $commit
 
 [When env-blocked > 0, append this final line:]
-Reminder: env-blocked findings must be carried in the PR description as a "manual verification required" checklist and should not trigger /refine-task.
+Reminder: env-blocked findings must be carried in the PR description as a "manual verification required" checklist and should not trigger /code-task.
 ```
 
 ### Branch C: Changes Requested
@@ -62,26 +64,28 @@ Task {task-id} review completed. Verdict: changes requested.
 - Review report: .agents/workspace/active/{task-id}/{review-artifact}
 
 Next step - fix the findings:
-  - Claude Code / OpenCode: /refine-task {task-id}
-  - Gemini CLI: /agent-infra:refine-task {task-id}
-  - Codex CLI: $refine-task {task-id}
+  - Claude Code / OpenCode: /code-task {task-id}
+  - Gemini CLI: /agent-infra:code-task {task-id}
+  - Codex CLI: $code-task {task-id}
 
 [When env-blocked > 0, append this final line:]
-Reminder: env-blocked findings must be carried in the PR description as a "manual verification required" checklist and should not trigger /refine-task.
+Reminder: env-blocked findings must be carried in the PR description as a "manual verification required" checklist and should not trigger /code-task.
 ```
 
 ### Branch D: Rejected
 
 ```text
-Task {task-id} review completed. Verdict: rejected, major rework required.
+Task {task-id} review completed. Verdict: rejected, re-design the technical plan.
 - Blockers: {n} | Major: {n} | Minor: {n}[ | env-blocked: {n} (outside AI repair scope)]
 - Review report: .agents/workspace/active/{task-id}/{review-artifact}
 
-Next step - re-implement:
-  - Claude Code / OpenCode: /implement-task {task-id}
-  - Gemini CLI: /agent-infra:implement-task {task-id}
-  - Codex CLI: $implement-task {task-id}
+Next step - re-design the technical plan:
+  - Claude Code / OpenCode: /plan-task {task-id}
+  - Gemini CLI: /agent-infra:plan-task {task-id}
+  - Codex CLI: $plan-task {task-id}
+
+> Note: Rejected means the implementation direction needs to be reworked end-to-end, not patched locally. `code-task/scripts/detect-mode.js` branch #7 refuses a direct `/code-task` and requires a fresh plan first.
 
 [When env-blocked > 0, append this final line:]
-Reminder: env-blocked findings must be carried in the PR description as a "manual verification required" checklist and should not trigger /refine-task.
+Reminder: env-blocked findings must be carried in the PR description as a "manual verification required" checklist and should not trigger /code-task.
 ```

package/templates/.agents/skills/{review-task → review-code}/reference/output-templates.zh-CN.md

@@ -2,6 +2,8 @@
 
 在向用户汇报最终审查结论之前先读取本文件。
 
+> 本文件描述的是**用户回执文本**的 4 个分类（场景 A/B/C/D），用于「向用户汇报结论」步骤。它**不是** review-code 产物的 `**总体结论**：` 字段值——字段值固定为 3 个规范 token（`通过` / `需要修改` / `拒绝`，或 EN 对应 `Approved` / `Changes Requested` / `Rejected`）。两者不可混用。
+
 ## 选择唯一输出场景
 
 按以下顺序判断（**注意：env-blocked 数量不参与判断**）：
@@ -30,7 +32,7 @@
   - Codex CLI：$commit
 
 [当 env-blocked > 0 时，在最后附加一行：]
-提醒：env-blocked 项需在 PR description 的「待人工验证」清单中承接，不应触发 /refine-task。
+提醒：env-blocked 项需在 PR description 的「待人工验证」清单中承接，不应触发 /code-task。
 ```
 
 ### 场景 B：通过但有问题
@@ -41,9 +43,9 @@
 - 审查报告：.agents/workspace/active/{task-id}/{review-artifact}
 
 下一步 - 修复问题后提交（推荐）：
-  - Claude Code / OpenCode：/refine-task {task-id}
-  - Gemini CLI：/agent-infra:refine-task {task-id}
-  - Codex CLI：$refine-task {task-id}
+  - Claude Code / OpenCode：/code-task {task-id}
+  - Gemini CLI：/agent-infra:code-task {task-id}
+  - Codex CLI：$code-task {task-id}
 
 或直接提交（跳过修复）：
   - Claude Code / OpenCode：/commit
@@ -51,7 +53,7 @@
   - Codex CLI：$commit
 
 [当 env-blocked > 0 时，在最后附加一行：]
-提醒：env-blocked 项需在 PR description 的「待人工验证」清单中承接，不应触发 /refine-task。
+提醒：env-blocked 项需在 PR description 的「待人工验证」清单中承接，不应触发 /code-task。
 ```
 
 ### 场景 C：需要修改
@@ -62,26 +64,28 @@
 - 审查报告：.agents/workspace/active/{task-id}/{review-artifact}
 
 下一步 - 修复问题：
-  - Claude Code / OpenCode：/refine-task {task-id}
-  - Gemini CLI：/agent-infra:refine-task {task-id}
-  - Codex CLI：$refine-task {task-id}
+  - Claude Code / OpenCode：/code-task {task-id}
+  - Gemini CLI：/agent-infra:code-task {task-id}
+  - Codex CLI：$code-task {task-id}
 
 [当 env-blocked > 0 时，在最后附加一行：]
-提醒：env-blocked 项需在 PR description 的「待人工验证」清单中承接，不应触发 /refine-task。
+提醒：env-blocked 项需在 PR description 的「待人工验证」清单中承接，不应触发 /code-task。
 ```
 
 ### 场景 D：拒绝
 
 ```text
-任务 {task-id} 代码审查完成。结论：拒绝，需要重大返工。
+任务 {task-id} 代码审查完成。结论：拒绝，需要重新设计方案。
 - 阻塞项：{n} | 主要问题：{n} | 次要问题：{n}[ | 环境性遗留：{n}（不在 AI 修复范围）]
 - 审查报告：.agents/workspace/active/{task-id}/{review-artifact}
 
-下一步 - 重新实现：
-  - Claude Code / OpenCode：/implement-task {task-id}
-  - Gemini CLI：/agent-infra:implement-task {task-id}
-  - Codex CLI：$implement-task {task-id}
+下一步 - 重新设计技术方案：
+  - Claude Code / OpenCode：/plan-task {task-id}
+  - Gemini CLI：/agent-infra:plan-task {task-id}
+  - Codex CLI：$plan-task {task-id}
+
+> 注意：Rejected 表示实现方向需要整体重做，不是局部修复。`code-task/scripts/detect-mode.js` 分支 #7 会拒绝直接 `/code-task`，要求先重新方案设计。
 
 [当 env-blocked > 0 时，在最后附加一行：]
-提醒：env-blocked 项需在 PR description 的「待人工验证」清单中承接，不应触发 /refine-task。
+提醒：env-blocked 项需在 PR description 的「待人工验证」清单中承接，不应触发 /code-task。
 ```

package/templates/.agents/skills/{review-task → review-code}/reference/report-template.en.md

@@ -1,6 +1,6 @@
 # Review Report Template
 
-Use this template when writing `review.md` or `review-r{N}.md`.
+Use this template when writing `review-code.md` or `review-code-r{N}.md`.
 
 ## Output Template
 
@@ -9,9 +9,8 @@ Use this template when writing `review.md` or `review-r{N}.md`.
 
 - **Review Round**: Round {review-round}
 - **Artifact File**: `{review-artifact}`
-- **Implementation Input**:
-  - `{implementation-artifact}`
-  - `{refinement-artifact}` (if present)
+- **Review Input**:
+  - `{code-artifact}`
 
 ## State Check
 
@@ -22,7 +21,7 @@ Use this template when writing `review.md` or `review-r{N}.md`.
 - **Reviewer**: {reviewer-name}
 - **Review Time**: {timestamp}
 - **Scope**: {file-count and major modules}
-- **Overall Verdict**: {Approved / Changes Requested / Rejected}
+- **Overall Verdict**: {Approved / Changes Requested / Rejected} (pick exactly one; combined phrases will fail the verify gate)
 - **Findings (AI-actionable)**: 0 blockers, 0 majors, 0 minors / **env-blocked**: 0
 
 ## Findings
@@ -49,7 +48,7 @@ Use this template when writing `review.md` or `review-r{N}.md`.
 
 ## Environment-Blocked Findings
 
-> Items the AI agent cannot close in the current execution environment; they do not participate in the next refine round. Maintainers carry them in the PR description as a "manual verification required" checklist.
+> Items the AI agent cannot close in the current execution environment; they do not participate in the next code round. Maintainers carry them in the PR description as a "manual verification required" checklist.
 
 #### 1. {environment-blocked finding title}
 **File**: `{file-path}:{line-number}` (if applicable)