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

Gate type: verification (always autonomous — see soe:gate-classification).

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

Done-Means-Done Scan (run before claiming complete)

The tables above catch reasoning failures ("should work"). This scan catches artifact failures — placeholder/fake work masquerading as done. Run it on the changed production paths before any completion claim (a check you perform, not a new framework; the grep set is adapted from ruflo's production-validator, MIT):

# 1. No stubs / placeholders left in the diff's PRODUCTION code (tests/docs excluded)
git diff --name-only | grep -vE '(^|/)(test|tests|spec|__tests__)/|\.(md|test|spec)\.' | while read -r f; do
  [ -f "$f" ] && grep -nEi 'TODO|FIXME|XXX|\bstub\b|\bmock(ed)?\b|\bfake\b|not[ _-]?implemented|placeholder|throw new Error\(["'"'"']not impl' "$f"
done
# 2. The change is real — the diff must actually show it
git diff --stat

• ANY hit in step 1 on a production path → NOT complete. Finish it, or explicitly record it as a known gap in the completion report (never silently).
• Tests/docs may legitimately contain mock/stub — the scan is scoped to production paths on purpose.
• If the change touches a service/endpoint, also exercise its real health/contract check (project-specific) — not just that the file compiles.

This makes the skill's "verify by artifact, not report" principle executable, not just asserted.

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.