Verification Before Completion

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

# 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
```

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

**File edits:** Use Write/StrReplace for source and artifacts. Shell is for running commands only—not for writing text files (especially on Windows).

## TDD Compliance Gate (MANDATORY)

**When production code was written**, you MUST prove TDD compliance **before** claiming done:

1. **IDENTIFY** files with production code changes
2. **CHECK** git history for test-first pattern:
   - Test commit hash: `[hash]`
   - Code commit hash: `[hash]`
   - Test commit is **before** code commit: YES/NO
3. **VERIFY** test quality (read test files, not assumptions):
   - Happy path covered: YES/NO
   - Edge cases (null/empty/boundary): YES/NO
   - Error cases: YES/NO
4. **RUN** full test suite; confirm 0 failures

**If ANY check fails:**
- State `TDD compliance FAILED` with evidence
- **DO NOT** claim completion
- Fix (delete code and restart with TDD, or add missing tests with red-green proof)

**Evidence format (include in completion message):**

```text
TDD Compliance:
- Test commit: abc1234
- Code commit: def5678
- Test-first: YES
- Happy path: YES | Edge cases: YES | Error cases: YES
- All tests pass: YES (42/42)
```

**Docs-only / chore-only changes:** State `TDD gate: N/A (no production code)`.

## 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
```

## Common Failures

| Claim | Requires | Not Sufficient |
|-------|----------|----------------|
| Tests pass | Test command output: 0 failures | Previous run, "should pass" |
| 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 |
| TDD compliance | Git log shows test commit before code commit; quality checklist | Code commit without prior test commit; tests added after implementation |

## 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 having run verification**
- Git log shows code before tests (TDD violation)

## 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 |
| "Tests after achieve same goals" | Git log must prove test-first. Tests-after = implementation bias. |
| "Already spent X hours, deleting is wasteful" | Sunk cost. Unverified code is technical debt. |

## 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
```

**TDD compliance:**
```
✅ git log --oneline shows: test commit → code commit → verify
❌ git log shows: code commit → test commit (tests after)
```

## 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. Read the output. THEN claim the result.

This is non-negotiable.