plan-audit

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Chinese

Audits completed work against a plan (WIs + acceptance + tests) and reports gaps, logic errors, and missing coverage with file/line references.

对照计划（工作项+验收标准+测试）审核已完成的工作，并附带文件/行号引用报告差距、逻辑错误和覆盖缺失情况。

Locate the plan
- Prefer
```
docs/codex-plans/<plan>.md
```
  (local, not in repo).
- If unclear, ask for the plan path or the WI list.
Extract audit checklist
- For each WI, list:
  - Goal
  - Acceptance criteria
  - Tests required
  - Touched areas (files/symbols)
Map implementation to WIs
- Use
```
git log
```
  ,
```
git show --stat
```
  ,
```
rg
```
  , and file inspection.
- Record which files/commits satisfy each WI.
Gap & correctness analysis
- Check each acceptance item vs actual behavior.
- Find logic errors, edge-case failures, and incomplete flows.
- Validate test coverage against the “Tests (first)” section.
- If the plan references specs, verify implementation matches those specs.
- If the plan is missing acceptance/tests, record it as a plan-quality gap.
Report findings
- Order by severity: Critical → High → Medium → Low.
- Each finding must include:
  - WI reference
  - File path + line
  - Why it violates the plan
  - Expected behavior per plan

定位计划
- 优先使用本地的
```
docs/codex-plans/<plan>.md
```
  （不在代码仓库中）。
- 若不明确，询问计划路径或工作项列表。
提取审核检查清单
- 针对每个工作项（WI），列出：
  - 目标
  - 验收标准
  - 所需测试
  - 涉及范围（文件/符号）
将实现映射到工作项
- 使用
```
git log
```
  、
```
git show --stat
```
  、
```
rg
```
  和文件检查。
- 记录哪些文件/提交满足每个工作项的要求。
差距与正确性分析
- 对照实际行为检查每个验收项。
- 找出逻辑错误、边缘用例失败和不完整的流程。
- 根据“Tests (first)”部分验证测试覆盖率。
- 若计划引用了规范，验证实现是否符合这些规范。
- 若计划缺少验收标准/测试，记录为计划质量差距。
报告发现结果
- 按严重程度排序：关键→高→中→低。
- 每个发现必须包含：
  - 工作项（WI）引用
  - 文件路径+行号
  - 违反计划的原因
  - 计划要求的预期行为

Findings (ordered by severity)
- ```
File:line
```
  and WI reference
- Impact and suggested fix
Plan Gaps Summary
- WI‑### → missing/partial acceptance items
Test Coverage Gaps
- Missing tests, broken tests, or “test not written”
Notes / Risks
- Any assumptions or unverified areas
Evidence
- Cite concrete evidence for each finding (files/lines/commit IDs).

Do not run tests here unless the user explicitly asks; this is an inspection pass.
Be strict about spec drift: if behavior diverges from plan text, flag it.
If you cannot locate the plan, stop and ask for it.