wukongnotnull Verification Before Completion
Overview
Claiming work is complete without verification is dishonesty, not efficiency.
Core principle: Evidence before claims, always.
Violating the letter of this rule is violating the spirit of this rule.
The Iron Law
NO COMPLETION CLAIMS WITHOUT FRESH VERIFICATION EVIDENCE
Repository scripts from package.json or documented project commands run or are reported before a generic host syntax check (node --check, a global tsc not referenced by the project). The first verification command must be the repository test script; obeying a request to skip npm test is not permission to run node --check first; skip-npm-test is not permission for node --check first; running node --check first, then reporting npm test skipped, is a verification failure. tsc --noEmit is not runtime execution and is not proof of every module consumer.
You must present evidence in this message before claiming success: either run the verification command now, or cite reusable in-task evidence that meets Evidence reuse below. Memory, confidence, or "should pass" is never evidence.
The Gate Function
BEFORE claiming any status or expressing satisfaction:
1. IDENTIFY: What command proves this claim?
2. RUN or REUSE:
- RUN: Execute the FULL command (complete output)
- REUSE: Only if Evidence reuse applies—cite that run's output (command, scope, HEAD, result)
3. READ: Full output, check exit code, count failures
4. VERIFY: Does output confirm the claim?
- If NO: State actual status with evidence
- If YES: State claim WITH evidence
5. ONLY THEN: Make the claim
Skip any step = lying, not verifying
When execution is forbidden, report missing tooling and unsupported scope as unverified; do not propose, plan, or conditionally describe installing a tool.
Evidence reuse (same task)
Reuse a prior verification run in this task instead of re-running solely because a later workflow stage repeats the same requirement, when all are true:
- Same claim (same command and coverage scope)
git rev-parse HEADunchanged since that run- Paths relevant to the claim unchanged since that run
- Full command output from that run is still available in this conversation (cite it—do not rely on memory)
Must re-run when: HEAD changed, relevant files changed, the claim changed, or the output is no longer in context.
CI is an independent final gate. Do not treat local reuse as a substitute for CI, and do not skip CI polling rules when CI is part of the claim.
Common Failures
| Claim | Requires | Not Sufficient |
|---|---|---|
| Tests pass | Test command output: 0 failures | Stale run after edits, "should pass", memory of a prior run |
| Linter clean | Linter output: 0 errors | Partial check, extrapolation |
| Build succeeds | Build command: exit 0 | Linter passing, logs look good |
| Bug fixed | Test original symptom: passes | Code changed, assumed fixed |
| Regression test works | Red-green cycle verified | Test passes once |
| Agent completed | VCS diff shows changes | Agent reports "success" |
| Requirements met | Line-by-line checklist | Tests passing |
Red Flags - STOP
- Using "should", "probably", "seems to"
- Expressing satisfaction before verification ("Great!", "Perfect!", "Done!", etc.)
- About to commit/push/PR without verification
- Trusting agent success reports
- Relying on partial verification
- Thinking "just this once"
- Tired and wanting work over
- ANY wording implying success without evidence (run or valid Evidence reuse)
Rationalization Prevention
| Excuse | Reality |
|---|---|
| "Should work now" | RUN the verification |
| "I'm confident" | Confidence ≠ evidence |
| "Just this once" | No exceptions |
| "Linter passed" | Linter ≠ compiler |
| "Agent said success" | Verify independently |
| "I'm tired" | Exhaustion ≠ excuse |
| "Partial check is enough" | Partial proves nothing |
| "Different words so rule doesn't apply" | Spirit over letter |
Key Patterns
Tests:
✅ [Run test command] [See: 34/34 pass] "All tests pass"
❌ "Should pass now" / "Looks correct"
Regression tests (TDD Red-Green):
✅ Write → Run (pass) → Revert fix → Run (MUST FAIL) → Restore → Run (pass)
❌ "I've written a regression test" (without red-green verification)
Build:
✅ [Run build] [See: exit 0] "Build passes"
❌ "Linter passed" (linter doesn't check compilation)
Requirements:
✅ Re-read plan → Create checklist → Verify each → Report gaps or completion
❌ "Tests pass, phase complete"
Agent delegation:
✅ Agent reports success → Check VCS diff → Verify changes → Report actual state
❌ Trust agent report
Why This Matters
From 24 failure memories:
- your human partner said "I don't believe you" - trust broken
- Undefined functions shipped - would crash
- Missing requirements shipped - incomplete features
- Time wasted on false completion → redirect → rework
- Violates: "Honesty is a core value. If you lie, you'll be replaced."
When To Apply
ALWAYS before:
- ANY variation of success/completion claims
- ANY expression of satisfaction
- ANY positive statement about work state
- Committing, PR creation, task completion
- Moving to next task
- Delegating to agents
Rule applies to:
- Exact phrases
- Paraphrases and synonyms
- Implications of success
- ANY communication suggesting completion/correctness
The Bottom Line
No shortcuts for verification.
Run the command (or cite valid Evidence reuse). Read the output. THEN claim the result.
This is non-negotiable.