# Verification Before Completion

> Use when about to claim work is complete, fixed, or passing—requires running verification commands and confirming output before making any success claims.

- Skill: `karim-bhalwani/verification-before-completion` (Agent Skill, multi-file: 3 files)
- Install (CLI): `npx skillmds@latest add karim-bhalwani/verification-before-completion`
- Raw SKILL.md: https://api.skillmd.com/api/skills/karim-bhalwani/verification-before-completion/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: Coding & Dev Tools
- Author: karim-bhalwani (https://skillmd.com/u/karim-bhalwani)
- Updated: 2026-09-17
- Page: https://skillmd.com/skills/karim-bhalwani/verification-before-completion

---


# 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.

## 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 |

## 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**

## 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)
```

**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

## The Bottom Line

**No shortcuts for verification.**

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

This is non-negotiable.

## Outputs & Deliverables

- **Primary Output**: Verification evidence (command outputs, test logs, CI run links)
- **Secondary Output**: Checklist of verification commands and required acceptance criteria
- **Success Criteria**: Evidence confirms the claimed status (exit codes, zero failures)
- **Quality Gate**: Attach verification artifacts to PRs or closure reports when claiming completion

## Common Pitfalls

- **Premature Satisfaction**: Saying "done" before running verification. Always execute the full verification command.
- **Partial Evidence**: "Most tests pass" is not passing. 100% success rate or state the actual failure count.
- **Ignoring Exit Codes**: Assuming "looks good" means success. Check exit codes; `0` = success, non-zero = failure.
- **Stale Verification**: Running verification once per project is not enough. Re-verify when claiming completion each time.
- **Mixing Concerns**: Testing one thing but claiming another passes. Verify exactly what you're claiming.
- **Trusting Reports**: Agent says "success" but you didn't verify. Always run the check yourself independently.

## Integration Points

| Phase | Input From | Output To | Context |
|-------|-----------|-----------|---------|
| Completion Claim | Any agent finishing work | Verification gate | Require fresh evidence before accepting completion |
| Testing | Implementation complete | Evidence collection | Run full test suite, capture output, check exit codes |
| PR/Merge | Code ready for review | Artifact attachment | Include verification evidence in PR comments or closure |
| Requirements Check | Feature specification | Line-by-line validation | Verify each requirement is met with evidence |

## Constraints

- **Technical Constraints:** Verification requires running the canonical commands in the project environment; do not rely on stale outputs
- **Governance Constraints:** Claims without attached verification are invalid for closure