Skip to main content
Claiming work is complete without verification is dishonesty, not efficiency. This skill enforces the iron law: no completion claims without fresh verification evidence.

​
Core Principle

Evidence before claims, always. If you haven’t run the verification command in this message, you cannot claim it passes.
Violating the letter of this rule is violating the spirit of this rule.

​
The Iron Law

NO COMPLETION CLAIMS WITHOUT FRESH VERIFICATION EVIDENCE
This is non-negotiable. No exceptions. Ever.

​
The Gate Function

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

​
Common Failures

ClaimRequiresNot Sufficient
Tests passTest command output: 0 failuresPrevious run, “should pass”
Linter cleanLinter output: 0 errorsPartial check, extrapolation
Build succeedsBuild command: exit 0Linter passing, logs look good
Bug fixedTest original symptom: passesCode changed, assumed fixed
Regression test worksRed-green cycle verifiedTest passes once
Agent completedVCS diff shows changesAgent reports “success”
Requirements metLine-by-line checklistTests passing

​
Red Flags - STOP

Stop immediately if you’re:
  • 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 having run verification

​
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)
For regression tests, you must verify the test fails without the fix and passes with it. A test that never fails proves nothing.

​
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

​
Real-World Examples

Wrong:
I've fixed the bug. The tests should pass now.
Right:
npm test

✓ 47 tests passing
0 failures

All tests pass. Bug is fixed.
Wrong:
The linter passed, so the build should be fine.
Right:
npm run build

Build completed successfully (exit 0)
Output: dist/bundle.js (245KB)

Build passes.
Wrong:
All tests pass, so we've met the requirements.
Right:
Re-reading plan from docs/plans/auth-feature.md:

✓ 1. User login via OAuth - Implemented in auth.ts:15-42
✓ 2. Session management - Implemented in session.ts:8-31
✓ 3. Token refresh - Implemented in refresh.ts:12-28
✗ 4. Logout endpoint - NOT FOUND

Requirements NOT met. Missing logout endpoint (requirement 4).
Wrong:
Agent reported success. Task complete.
Right:
git diff HEAD~1

Agent changed:
- src/parser.ts: Added parseJSON function
- tests/parser.test.ts: Added 3 test cases

Running tests:
✓ 3/3 new tests pass
✓ 47/47 total tests pass

Agent task verified complete.

​
Correct Phrasing

With Evidence

  • “All tests pass” (after showing test output)
  • “Build succeeds” (after showing build output)
  • “Fixed” (after showing test passing)
  • “Complete” (after showing checklist)

Without Evidence

  • “Should work”
  • “Looks good”
  • “Probably fixed”
  • “Seems correct”
  • “Done!” (without verification)

​
The Bottom Line

No shortcuts for verification. Run the command. Read the output. THEN claim the result. This is non-negotiable.

Build docs developers (and LLMs) love

Get started for freeTalk to us