Verification Before Completion

The Iron Law

NO COMPLETION CLAIMS WITHOUT FRESH VERIFICATION EVIDENCE

If you haven't run the verification command in this message, you cannot claim it passes.

The Gate Function

BEFORE claiming any status or expressing satisfaction:

1. IDENTIFY: What 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?
   - 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

What Each Claim Requires

E2E Gate (when invoked from /start)

If this verification was triggered by the /start pipeline, you MUST verify that Playwright E2E tests exist and pass:

npx playwright test

If this command fails because Playwright is not installed or no E2E tests exist, verification FAILS. Go back to Step 5 of /start and do the work. Do not rationalize skipping E2E.

Test Proportionality Check

Before claiming completion, assess whether tests are proportional to the code you shipped.

For each piece of production code, identify its test:

Proportionality failures (verification MUST fail if any apply):

• 200+ lines of UI code shipped with 0 component/E2E tests covering interactions
• API routes shipped with only input-validation helper tests (route handler itself untested)
• Bug fix shipped without a regression test reproducing the original symptom
• Navigation added/changed without an E2E test clicking the nav and verifying the destination
• "All N tests pass" where N hasn't increased despite new production code

The check: Look at git diff --stat for the work being verified. For every production file changed, point to the test that covers it. If you can't → verification FAILS.

When proportionality fails, route back explicitly:

After ANY loop-back: Re-run the FULL gate function (identify → run → read → verify). Do not skip re-verification. Do not assume the new test fixed everything — run ALL tests and re-check ALL proportionality. Partial re-checks prove nothing.

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"

Red Flags — STOP

• Using "should", "probably", "seems to"
• Expressing satisfaction before verification ("Great!", "Perfect!", "Done!")
• About to commit/push/PR without verification
• Trusting agent success reports without independent verification
• ANY wording implying success without having run verification

Rationalization Prevention

The Bottom Line

Run the command. Read the output. THEN claim the result.

This is non-negotiable.