Verification Before Completion

From the author

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

— the description by Jesse Vincent

AutoGineer summary

Written by AutoGineer from the skill’s own files, not by the author

This skill establishes a strict operational protocol for AI agents to ensure that no claims of success, completion, or correctness are made without first executing and reviewing fresh verification evidence. It mandates a gate function that requires agents to identify, run, read, and verify the output of specific commands before reporting any status. The framework is designed to prevent rationalization, assumptions, and reliance on partial checks or previous results, enforcing the principle that evidence must always precede assertions.

What it does

Enforces a mandatory verification gate before any claim of task completion.
Requires execution of fresh, full verification commands for every status report.
Provides a structured checklist for validating builds, tests, and requirements.
Identifies common rationalization patterns that lead to unverified success claims.
Mandates independent verification of agent-delegated tasks.
Establishes a strict evidence-first communication standard.

When to use it

Before claiming that code is fixed, passing, or complete.
Before committing changes or creating pull requests.
Before moving to a subsequent task in a workflow.
When delegating work to other agents to ensure their success reports are accurate.
Whenever an agent is tempted to use phrases like 'should work' or 'looks correct'.

Advantages

Eliminates assumptions and reliance on outdated or partial test results.
Reduces the risk of reporting false positives or incomplete work.
Ensures that all claims are backed by concrete, reproducible evidence.
Standardizes the definition of 'done' across different development tasks.
Prevents common cognitive biases and rationalizations during the development process.

Usage examples

“I have finished the bug fix, can I submit the PR?”: The agent will first run the specific test case that failed, confirm it now passes with 0 failures, and only then report that the fix is verified and ready for PR.
“Is the build ready for deployment?”: The agent will execute the build command, verify the exit code is 0, and confirm the build output is clean before stating that the build is ready.

Install

Download the skill as a ZIP:
https://autogineer.com/agent-skills/openai/verification-before-completion/download

Unzip it into the cross-client skills folder of your project:

mkdir -p .agents/skills && unzip verification-before-completion.zip -d .agents/skills

Documentation by Jesse Vincent

Overview

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

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

Files

ATTRIBUTION.mdAdded by AutoGineer944 B
LICENSELicence file added by AutoGineer1.0 KiB
SKILL.md3.6 KiB
agents/openai.yaml147 B

Requirements and compatibility

Written for: OpenAI Codex

Works with: Claude Code, Claude apps, OpenAI Codex, GitHub Copilot, Cursor, Gemini CLI, Kiro, OpenCode, Goose, Amp, Roo Code, JetBrains Junie, Factory Droid, Devin (ex-Windsurf), Mistral Vibe, OpenHands, Letta

“Works with” means the tool reads the open Agent Skills format; a skill written for one tool may use features others lack.

Security

No issues found by our static scan· No issues found

A static scan is not a guarantee. Skills are third-party content: review a skill before you let an agent use it.

Migrate To Shoehorn
Matt Pocock· Community
Automate the migration of TypeScript test assertions from unsafe as-casting to the type-safe shoehorn library.
Software developmentClaude CodeClaude appsOpenAI Codex+14 more
MITGitHub stars of the source repository317.5k
Tdd
Matt Pocock· Community
A reference guide for implementing the red-green-refactor loop in test-driven development.
Software developmentClaude CodeClaude appsOpenAI Codex+14 more
MITGitHub stars of the source repository317.5k
Test Driven Development
Jesse Vincent (obra)· Community
A rigorous framework for Test-Driven Development, mandating that failing tests precede all production code.
Software developmentClaude CodeClaude appsOpenAI Codex+14 more
MITGitHub stars of the source repository314k
Webapp Testing
AnthropicOfficial
A toolkit for automating local web application testing using Playwright and server management helpers.
Software developmentClaude CodeClaude appsOpenAI Codex+14 more
Apache-2.0Low riskHas scriptsGitHub stars of the source repository188.6k
Test Driven Development
Addy Osmani· Community
A systematic approach to software development using the red-green-refactor cycle to ensure code reliability and maintainability.
Software developmentClaude CodeClaude appsOpenAI Codex+14 more
MITGitHub stars of the source repository113.9k
Browser Testing With Devtools
Addy Osmani· Community
Integrate Chrome DevTools to enable live browser inspection, debugging, and automated UI verification for your AI agent.
Software developmentClaude CodeClaude appsOpenAI Codex+14 more
MITGitHub stars of the source repository113.9k

Download ZIP

The ZIP holds the skill’s files, its licence files and an ATTRIBUTION.md. Download verification-before-completion.zip