Verification Before Completion

SkillDev tools

Verification before completion is a skill that stops an AI agent from claiming work is done without proof. Before any statement that something is complete, fixed, or passing, the agent must identify the command that proves the claim, run it fresh, read the full output, and report success only with evidence. It applies before commits, pushes, and pull requests.

Available today. Use it from your connected AI after setup.

Have an AI agent setup that can load agent skills.

Then ask your AI: use the Verification Before Completion skill

What your AI can do with it

  • Runs a gate: identify the proving command, run it fresh, read full output, then claim
  • Requires test command output showing 0 failures before claiming tests pass
  • Requires build exit code 0 before claiming a build succeeds
  • Enforces red-green verification for regression tests (pass, revert, must fail, restore)
  • Verifies sub-agent work via the VCS diff instead of trusting success reports
  • Bans hedged wording like "should", "probably", or "seems to" in status claims

Getting started

  1. Have an AI agent setup that can load agent skills.
  2. Add the verification-before-completion skill to the agent's available skills.
  3. The skill triggers automatically when the agent is about to claim work is complete, fixed, or passing, or before committing or creating PRs.
  4. Optionally review the skill's gate function and red flags with the agent so it applies the rules consistently.

What this skill tells your AI

The instructions your AI receives, as published by obra/superpowers in skills/verification-before-completion/SKILL.md and read by ahel’s review.

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

Signals

GitHub stars
290k
Forks
26k
Last commit
Sep 2026
Installs
220k installs

Questions

What skills are needed for document verification?
This item covers verification of code work, not documents. For its scope, the needed skill is verification-before-completion: run the command that proves the claim and confirm its output before asserting success.
What does "skill validation" mean?
Here it means validating a claim with fresh evidence: identify the command that proves it, run it completely, read the full output and exit code, and only then make the claim.
Advanced
Catalog kind
skill
Key
verification-before-completion-obra
Source
github.com/obra/superpowers