agent safety skill risk: low
Verification Before Completion Enforcer
Instructs the model to identify the relevant verification command, execute it fully, read the output and exit code, and confirm results before making any claims of work being compl…
SKILL 1 file
SKILL.md
---
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.
## 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.
REQUIRED CONTEXT
- claim about to be made
- verification command to run
ROLES & RULES
- IDENTIFY what command proves this claim
- RUN the FULL command fresh and complete
- READ full output, check exit code, count failures
- VERIFY does output confirm the claim
- State actual status with evidence if NO
- State claim WITH evidence if YES
- ONLY THEN make the claim
- Skip any step = lying, not verifying
EXPECTED OUTPUT
- Format
- plain_text
- Constraints
- always run verification command first
- report evidence before any success claim
- never skip steps
SUCCESS CRITERIA
- Run verification commands before claiming completion
- Provide fresh command output as evidence
- Follow the full gate function before any success claim
FAILURE MODES
- Using should, probably, or seems to
- Expressing satisfaction before verification
- Committing or creating PR without verification
- Trusting agent success reports
- Relying on partial verification
- Thinking just this once
EXAMPLES
Includes tables of common failures with required verification vs insufficient evidence, red flags, rationalization excuses vs reality, and key patterns with good/bad examples for tests, regression, builds, requirements, and agent delegation.
QUALITY
- OVERALL
- 0.88
- CLARITY
- 0.92
- SPECIFICITY
- 0.95
- REUSABILITY
- 0.82
- COMPLETENESS
- 0.90
USAGE
Copy the prompt above and paste it into your AI of choice — Claude, ChatGPT, Gemini, or anywhere else you're working. Replace any placeholder sections with your own context, then ask for the output.
MORE FOR AGENT
- Full Output Enforcement Enforceragentsafety
- Full Output Completeness Enforceragentsafety
- FDA FSMA Food Safety Auditoragentsafety
- Claude Code Git Guardrails Setupagentsafety
- Comprehensive Codebase Bug Analysis and Fixeragentanalysis
- Xcode MCP Usage Guidelines for Agentsagenttool_use
- Xcode MCP Usage Guidelinesagenttool_use
- Rapid App MVP Prototyperagentcoding
- Local Documentation Online Sync Automatoragentoperations
- HashiCorp Packer Golden Image Expertagentoperations
- Xquik X/Twitter API Integration Skillagenttool_use
- MoltPass Client for AI Agent Identitiesagentsecurity
- AI-First Design Handoff Specs Generatoragentcoding
- Consciousness Council Multi-Perspective Deliberationagentplanning
- Creative Thinking Frameworks for CS Researchagentresearch
- Filesystem Agent Context Engineeringagenttool_use
- Academic Paper Figure Generatoragentresearch
- Multi-Agent Architecture Patterns Guideagentplanning
- Existing Web Design Premium Upgraderagentcreative
- Product Marketing Context Document Creatoragentmarketing
- Test-Driven Development Workflow Rulesagentcoding
- Agent Tool Design Principlesagenttool_use
- TDD Implementation Plan Writeragentplanning
- Conventional Git Commit Creatoragenttool_use
- GitHub Trending Dashboard Generatoragenttool_use