Verification Before Completion
Claiming work is complete without verification is dishonesty, not efficiency.
Core principle: Evidence before claims, always.
The Iron Law
code
NO COMPLETION CLAIMS WITHOUT FRESH VERIFICATION EVIDENCE
If you haven't run the verification command in this response, you cannot claim it passes.
The Gate
Before claiming ANY success:
- •IDENTIFY: What command proves this claim?
- •RUN: Execute the command (fresh, complete)
- •READ: Check output and exit code
- •VERIFY: Does output confirm the claim?
- •ONLY THEN: Make the claim with evidence
Skip any step = not verified.
What Requires Verification
| Claim | Requires | NOT Sufficient |
|---|---|---|
| "Tests pass" | Test output: 0 failures | Previous run, "should pass" |
| "Build succeeds" | Build command: exit 0 | Linter passing |
| "Bug fixed" | Regression test passes | "Code changed" |
| "Task complete" | All acceptance criteria checked | "Looks done" |
| "Phase complete" | All tasks verified | Some tasks done |
Common Rationalizations
| Excuse | Reality |
|---|---|
| "Should work now" | RUN the verification |
| "I'm confident" | Confidence ≠ evidence |
| "Just this once" | No exceptions |
| "Linter passed" | Linter ≠ tests ≠ build |
| "I'm tired" | Exhaustion ≠ excuse |
| "Already checked earlier" | Fresh verification required |
Red Flags - STOP
- •Using "should", "probably", "seems to"
- •Saying "Done!" before running tests
- •About to commit without verification
- •Relying on partial checks
- •Expressing satisfaction before evidence
All of these mean: STOP. Run verification. Then claim.
Correct Pattern
code
[Run: npm test] [Output: 34/34 passing] All tests pass.
Incorrect Pattern
code
I've fixed the bug. Tests should pass now.
No output = no evidence = not verified.
Integration with Status Updates
Before running /wb:update_status to mark phases complete:
- •Run all phase verification commands
- •Confirm all tasks actually done
- •Check automated criteria pass
- •Then update status with evidence