AutoGineer
Generated banner for Verification Before Completion
Generated logo for Verification Before Completion

Verification Before Completion

OpenAIOfficialCreated by Jesse VincentDistributed by OpenAI

  • Skill
  • Guidelines
  • Software development
  • MIT
  • No issues found
Download ZIP

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  • Eliminates assumptions and reliance on outdated or partial test results.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

  1. Download the skill as a ZIP:

    https://mp-staging.autogineer.com/agent-skills/openai/verification-before-completion/download

  2. 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

Verification Before Completion

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

ClaimRequiresNot Sufficient
Tests passTest command output: 0 failuresPrevious run, "should pass"
Linter cleanLinter output: 0 errorsPartial check, extrapolation
Build succeedsBuild command: exit 0Linter passing, logs look good
Bug fixedTest original symptom: passesCode changed, assumed fixed
Regression test worksRed-green cycle verifiedTest passes once
Agent completedVCS diff shows changesAgent reports "success"
Requirements metLine-by-line checklistTests 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

ExcuseReality
"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

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.

Attribution and licence

Created by
Jesse Vincent
Publisher
OpenAI (Official)
Distributed by
OpenAI
Source
openai/plugins · plugins/superpowers/skills/verification-before-completion · commit d420d13
Licence
MIT License (redistribution allowed)
  • LICENSE (added by AutoGineer from plugins/superpowers/LICENSE)
  • ATTRIBUTION.md (written by AutoGineer)
Synced
Also distributed in
obra/superpowers

AutoGineer is not affiliated with or endorsed by Jesse Vincent or OpenAI.

Download ZIP

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