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

global
0installs0uses~1.0k
v1.0Saved May 2, 2026

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.

Files1
1 files · 1.0 KB

Select a file to preview

Overall Score

89/100

Grade

A

Excellent

Safety

95

Quality

88

Clarity

92

Completeness

82

Summary

This skill enforces a verification-before-completion discipline that requires agents to run fresh verification commands and confirm output before making any success claims. It establishes a "gate function" workflow: identify the verification command, execute it fully, read the complete output, confirm the claim matches evidence, then state the result with proof. The skill treats unverified claims as dishonesty and documents common failure patterns, red flags, and rationalizations to prevent.

Detected Capabilities

Workflow enforcement for verification-before-claimsStructured gate function methodologyCommon failure pattern detectionRationalization prevention and red flag identificationEvidence-based completion validationRequirements checklist verification

Trigger Keywords

Phrases that MCP clients use to match this skill to user intent.

verify before committest passing confirmationevidence-based completionverification gateregression test validationbuild success checkprevent false claims

Use Cases

  • Verify test suites pass before claiming work complete
  • Confirm linter checks pass before code review or commit
  • Validate build succeeds with exit code 0 before deployment
  • Verify bug fixes by reproducing original symptom
  • Red-green test cycle verification for regression tests
  • Check VCS diffs when delegating tasks to agents
  • Prevent false completion claims before PR creation

Quality Notes

  • POSITIVE: Exceptionally clear and well-structured discipline. Uses tables, examples, and red flag patterns to make the rule concrete and actionable.
  • POSITIVE: Directly addresses psychological barriers (tiredness, overconfidence, partial shortcuts) with explicit rationalization prevention patterns.
  • POSITIVE: Grounded in real failure memories (24 documented cases) — makes the cost of non-compliance tangible rather than abstract.
  • POSITIVE: Clear gate function workflow (5 steps) gives an agent unambiguous mechanical process to follow.
  • POSITIVE: Distinguishes between spirit and letter of the rule — prevents clever workarounds while keeping intent clear.
  • POSITIVE: Comprehensive comparison tables (tests vs linters, agent reports vs independent verification) make distinctions concrete.
  • POSITIVE: The skill is self-contained and requires no external files or context — pure discipline and methodology.
  • MINOR: No explicit scope boundaries stated — the skill applies to 'any work', which is intentional breadth but could benefit from a brief 'when NOT to apply' section if any exist.
  • MINOR: No error handling guidance for when verification fails — the skill assumes failure leads to correct status reporting, but could benefit from guidance on diagnosing why verification failed.
Model: claude-haiku-4-5-20251001Analyzed: May 2, 2026

Reviews

Add this skill to your library to leave a review.

No reviews yet

Be the first to share your experience.

Add obra/verification-before-completion to your library

Command Palette

Search for a command to run...