---

name: verification-before-completion description: Use when about to claim work is complete, fixed, or passing - requires running verification commands and confirming output before making any success claims

Verification Before Completion

Overview

Core principle: Evidence before claims, always.

Violating the letter of this rule is violating the spirit of this rule.

The Iron Law

CopyNO 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:

1. IDENTIFY: What command proves this claim?
2. RUN: Execute the command (fresh, complete)
3. READ: Full output, check exit code
4. VERIFY: Does output confirm the claim?
5. ONLY THEN: Make the claim

Skip any step = lying, not verifying.

What Counts as Evidence

Red Flags

Stop if you catch yourself:

• Using "should", "probably", "seems to"
• Expressing satisfaction before verification ("Great!", "Done!")
• Trusting agent success reports without checking
• Thinking "just this once"
• ANY wording implying success without running verification

Common rationalizations:

Correct Patterns

Copy✅ [Run test command] [See: 34/34 pass] "All tests pass"
❌ "Should pass now" / "Looks correct"

✅ [Run build] [See: exit 0] "Build passes"
❌ "Linter passed" (linter doesn't check compilation)

✅ Agent reports success → Check VCS diff → Verify changes
❌ Trust agent report

The Bottom Line

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

No shortcuts. Non-negotiable.