Catalog
obra/verification-before-completion

obra

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

NewUpdated Sep 9, 2026

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

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
Files1
1 files · 1.0 KB

Select a file to preview

Overall Score

82/100

Grade

B

Good

Grades are signals, not a certification. Always review a skill yourself before use.

Safety

92

Quality

76

Clarity

88

Completeness

72

Summary

This skill enforces a disciplined verification gate: before claiming work is complete, passing, or fixed, an agent must identify the verification command, execute it fresh, read the full output, and confirm it matches the claim. It is a behavioral guideline designed to prevent false success claims and ensure evidence precedes assertions.

Detected Capabilities

code verificationtest command executionbuild command validationprocess output analysisbehavioral enforcement

Trigger Keywords

Phrases that agents use to match this skill to user intent.

verify before claimingtest verification gateevidence over assertionsprevent false claimscompletion checkpointfresh verification

Use Cases

  • Preventing premature test pass claims without fresh execution
  • Enforcing verification before commit or PR creation
  • Blocking unverified build success claims
  • Ensuring regression test red-green cycles are validated
  • Guarding against agent false-positive success reports
  • Preventing completion claims based on partial checks or assumptions

Quality Notes

  • Clear, structured presentation with examples and anti-patterns clearly contrasted
  • Effective use of tables to show failure modes and rationalization excuses
  • Iron Law and Gate Function provide memorable, actionable mental models
  • Red Flags section explicitly calls out danger signals to pause on
  • Comprehensive coverage of common claim types (tests, build, linter, regression, requirements, delegation)
  • Missing: explicit guidance on what constitutes 'full output' (e.g., tail counts, log file size limits)
  • Missing: examples of actual command outputs and how to interpret ambiguous exit codes
  • Missing: handling of flaky tests or intermittent failures — should verification be repeated?
  • Missing: scope clarity on what counts as a 'claim' (e.g., does progress reporting count?)
Model: claude-haiku-4-5-20251001Analyzed: Sep 9, 2026

Reviews

Add this skill to your library to leave a review.

No reviews yet

Be the first to share your experience.

Version History

  1. v1.1

    Content updated

    ✦ AIRemoves normative language on dishonesty, trust failure, and verification as non-negotiable requirement.

    2026-09-09

    LATEST
  2. v1.0

    2026-05-02

    View This VersionInitial version

Use obra/verification-before-completion in your dev environment

Command Palette

Search for a command to run...