ReddRadar
Agent skill
verification-before-completion
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
Install this agent skill to your Project
npx add-skill https://github.com/autohandai/community-skills/tree/main/verification-before-completion
SKILL.md
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.
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
autohandai/community-skills
mapping-mitre-attack-techniques
Maps observed adversary behaviors, security alerts, and detection rules to MITRE ATT&CK techniques and sub-techniques to quantify detection coverage and guide control prioritization. Use when building an ATT&CK-based coverage heatmap, tagging SIEM alerts with technique IDs, aligning security controls to adversary playbooks, or reporting threat exposure to executives. Activates for requests involving ATT&CK Navigator, Sigma rules, MITRE D3FEND, or coverage gap analysis.
autohandai/community-skills
hunting-for-spearphishing-indicators
Hunt for spearphishing campaign indicators across email logs, endpoint telemetry, and network data to detect targeted email attacks.
autohandai/community-skills
analyzing-malicious-url-with-urlscan
URLScan.io is a free service for scanning and analyzing suspicious URLs. It captures screenshots, DOM content, HTTP transactions, JavaScript behavior, and network connections of web pages in an isolat
autohandai/community-skills
implementing-zero-standing-privilege-with-cyberark
Deploy CyberArk Secure Cloud Access to eliminate standing privileges in hybrid and multi-cloud environments using just-in-time access with time, entitlement, and approval controls.
autohandai/community-skills
implementing-pam-for-database-access
Deploy privileged access management for database systems including Oracle, SQL Server, PostgreSQL, and MySQL. Covers session proxy configuration, credential vaulting, query auditing, dynamic credentia
autohandai/community-skills
detecting-t1003-credential-dumping-with-edr
Detect OS credential dumping techniques targeting LSASS memory, SAM database, NTDS.dit, and cached credentials using EDR telemetry, Sysmon process access monitoring, and Windows security event correlation.
Didn't find tool you were looking for?