verification-before-completion

name	verification-before-completion
description	Use before declaring any work complete — run verification commands and confirm output before making any success claims

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"
Deploy succeeded	Pod status Running + health check 200	kubectl apply exit 0
Infra applied correctly	terraform show matches intent	terraform apply exit 0
Bug fixed	Original symptom tested: passes	Code changed, assumed fixed
Pipeline fixed	Green checkmark in CI	Config change committed
Agent completed	VCS diff shows changes	Agent reports "success"
Requirements met	Line-by-line checklist	Tests passing

Verification by Task Type

Infrastructure apply:

terraform show          # confirm state matches intent
# test the actual resource in cloud console/CLI

Container deploy:

kubectl get pods        # all pods Running, not CrashLoopBackOff
kubectl logs <pod>      # no errors
curl /health            # health check passes

CI/CD change:

• Trigger the pipeline and watch it pass
• Don't claim "fixed" until the green checkmark exists

DNS change:

dig @8.8.8.8 example.com    # resolves to expected IP
curl https://example.com     # site loads correctly

Proxy/network change:

curl -v https://example.com
tail -n 50 /var/log/nginx/error.log  # no new errors

Red Flags — STOP

• Using "should", "probably", "seems to"
• Expressing satisfaction before verification ("Done!", "Fixed!", "Deployed!", etc.)
• About to commit/push/PR without verification
• Trusting agent success reports
• Relying on partial verification
• Thinking "just this once"
• 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
"The command exited 0"	Exit code ≠ correct behavior
"Agent said success"	Verify independently
"The change was small"	Small changes break things too
"Partial check is enough"	Partial proves nothing
"Different words so rule doesn't apply"	Spirit over letter

Key Patterns

Infra:

✅ [Run terraform show] [Confirm resource matches intent] "Infrastructure applied correctly"
❌ "Apply exited 0, should be good"

Deploy:

✅ [kubectl get pods: all Running] [curl /health: 200] "Deploy successful"
❌ "Kubectl apply succeeded"

Requirements:

✅ Re-read plan → Create checklist → Verify each → Report gaps or completion
❌ "Tests pass, done"

Agent delegation:

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

The Bottom Line

No shortcuts for verification.

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

This is non-negotiable.