verification-before-completion
Compare original and translation side by side
🇺🇸
Original
English🇨🇳
Translation
ChineseVerification Before Completion
完工前验证
NO COMPLETION CLAIMS WITHOUT FRESH VERIFICATION EVIDENCE
无最新验证证据，不得做出任何完工声明
Core Protocol
核心协议
Evidence before claims, always. If you haven't run the verification command in this message, you cannot claim it passes.
BEFORE any completion claim:
1. IDENTIFY: What verification command proves this claim?
2. RUN: Execute the FULL command (fresh, complete)
3. READ: Full output, check exit code, count failures
4. VERIFY: Does output confirm the claim?
- NO → State actual status with evidence
- YES → State claim WITH evidence
5. ONLY THEN: Make the claim永远先举证，后声明。如果你没有运行本文档中规定的验证命令，就不能宣称验证通过。
BEFORE any completion claim:
1. IDENTIFY: What verification command proves this claim?
2. RUN: Execute the FULL command (fresh, complete)
3. READ: Full output, check exit code, count failures
4. VERIFY: Does output confirm the claim?
- NO → State actual status with evidence
- YES → State claim WITH evidence
5. ONLY THEN: Make the claimCommand Selection
命令选择
When multiple verification options exist (mono-repo, multiple suites):
- Run the most specific command that covers the changed code
- When uncertain, run the broadest command (full test suite > single file)
- Lint ≠ build ≠ test — each verifies different claims
当存在多个验证选项时（如单体仓库、多测试套件场景）：
- 运行覆盖改动代码的最具体的命令
- 不确定时，运行覆盖范围最广的命令（全量测试套件 > 单文件测试）
- Lint ≠ build ≠ test —— 三者分别验证不同的声明
Evidence Format
证据格式
✅ Ran: npm test
Exit: 0
Result: 47 passed, 0 failed
"All tests pass."
❌ "Tests should pass now" (no command output)✅ Ran: npm test
Exit: 0
Result: 47 passed, 0 failed
"All tests pass."
❌ "Tests should pass now" (no command output)Verification Requirements by Claim Type
按声明类型划分的验证要求
| Claim | Required Evidence | Insufficient |
|---|---|---|
| Tests pass | Test output: 0 failures | Previous run, "should pass" |
| Linter clean | Linter output: 0 errors | Partial check, extrapolation |
| Build succeeds | Build exit code: 0 | Linter passing |
| Bug fixed | Original symptom test passes | Code changed |
| Regression test | Red-green cycle verified | Single green |
| Agent completed | VCS diff shows changes | Agent "success" report |
| Requirements met | Line-by-line checklist | Tests passing |
| 声明类型 | 所需证据 | 无效举证 |
|---|---|---|
| 测试通过 | 测试输出：0个失败 | 之前的运行结果、"should pass" |
| Linter检查无异常 | Linter输出：0个错误 | 部分检查、推断结果 |
| 构建成功 | 构建退出码：0 | Linter检查通过 |
| Bug已修复 | 原故障复现用例测试通过 | 代码已修改 |
| 回归测试通过 | 红-绿流程已验证 | 单次运行通过 |
| Agent执行完成 | VCS diff显示变更 | Agent的"success"报告 |
| 需求已满足 | 逐条核对的检查清单 | 测试通过 |
Red Flags — STOP
危险信号 —— 立即停止
- Words: "should", "probably", "seems to"
- Satisfaction before verification: "Great!", "Perfect!", "Done!"
- About to commit/push/PR without verification
- Trusting agent success reports
- Partial verification
- ANY wording implying success without verification output
- 措辞："should"、"probably"、"seems to"
- 验证前就表达满意："Great!"、"Perfect!"、"Done!"
- 未经验证就要提交/推送代码/发起PR
- 轻信Agent的成功报告
- 部分验证
- 任何暗示成功但无验证输出的表述
Rationalization Prevention
避免合理化借口
| Excuse | Response |
|---|---|
| "Should work now" | Run the verification |
| "I'm confident" | Confidence ≠ evidence |
| "Just this once" | No exceptions |
| "Linter passed" | Linter ≠ build |
| "Agent said success" | Verify independently |
| "Partial check enough" | Partial proves nothing |
| 借口 | 回应 |
|---|---|
| "Should work now" | 执行验证 |
| "I'm confident" | 信心≠证据 |
| "Just this once" | 没有例外 |
| "Linter passed" | Linter≠build |
| "Agent said success" | 独立验证 |
| "Partial check enough" | 部分验证证明不了任何问题 |
Key Patterns
核心模式
Tests:
✅ [Run test] → [See: 34/34 pass] → "All tests pass"
❌ "Should pass now"Regression (TDD):
✅ Write → Run (pass) → Revert fix → Run (MUST FAIL) → Restore → Run (pass)
❌ "Wrote regression test" (no red-green)Requirements:
✅ Re-read plan → Checklist each item → Report gaps or completion
❌ "Tests pass, phase complete"Agent delegation:
✅ Agent reports → Check VCS diff → Verify changes → Report actual state
❌ Trust agent report测试：
✅ [Run test] → [See: 34/34 pass] → "All tests pass"
❌ "Should pass now"回归测试（TDD）：
✅ Write → Run (pass) → Revert fix → Run (MUST FAIL) → Restore → Run (pass)
❌ "Wrote regression test" (no red-green)需求核对：
✅ Re-read plan → Checklist each item → Report gaps or completion
❌ "Tests pass, phase complete"Agent委托任务：
✅ Agent reports → Check VCS diff → Verify changes → Report actual state
❌ Trust agent report