
Verification Before Completion
- 159k installs
- 262k repo stars
- Updated July 24, 2026
- obra/superpowers
Verification-before-completion is a workflow skill that gates completion claims on fresh verification evidence
About
Enforces evidence-based completion claims before commits or PRs. Requires running verification commands and confirming output before making any success assertions. Eliminates unverified status claims by gating completion on fresh evidence.
- Evidence before assertions: run verification commands fresh before claiming completion
- Gate function: identify proof command, execute full output, verify result claims
- Prevents shipping unverified work: tests pass, linter clean, build succeeds all need proof
Verification Before Completion by the numbers
- 158,622 all-time installs (skills.sh)
- +8,845 installs in the week ending Jul 28, 2026 (Skillselion tracking)
- Ranked #8 of 1,382 Code Review & Quality skills by installs in the Skillselion catalog
- Security screen: LOW risk (skills.sh audit)
- Data as of Jul 28, 2026 (Skillselion catalog sync)
verification-before-completion capabilities & compatibility
- Capabilities
- test verification · linter checking · build validation · bug confirmation
- Use cases
- testing · code review
What verification-before-completion says it does
Claiming work is complete without verification is dishonesty, not efficiency.
npx skills add https://github.com/obra/superpowers --skill verification-before-completionAdd your badge
Show developers this skill is listed on Skillselion. Paste this into your README.
| Installs | 159k |
|---|---|
| repo stars | ★ 262k |
| Security audit | 3 / 3 scanners passed |
| Last updated | July 24, 2026 |
| Repository | obra/superpowers ↗ |
How do agents prove work is done before committing?
Verify completion with fresh evidence before committing or creating pull requests
Who is it for?
Any project where false positives matter: production deploys, merged PRs, shipped features
Skip if: Early exploration before any completion claim is imminent, or tasks where the user explicitly wants a hypothesis without verification.
When should I use this skill?
The agent is about to claim work is complete, fixed, or passing, or to commit, push, or open a PR.
What you get
Fresh command output with exit codes, failure counts, and evidence-backed completion claims attached to commits or PRs.
- Verification command output
- Evidence-backed status claims
By the numbers
- 5-step verification gate function before any completion claim
- Common-failures table documents 7 claim types and insufficient shortcuts
- References 24 recorded failure memories from unverified claims
Files
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 EVIDENCEIf 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 verifyingCommon 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 reportWhy 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.
Related skills
Forks & variants (16)
Verification Before Completion has 16 known copies in the catalog totaling 563 installs. They canonicalize to this original listing.
- pedronauck - 201 installs
- guanyang - 117 installs
- eyadsibai - 53 installs
- jamditis - 49 installs
- jackiexiao - 39 installs
How it compares
Pick verification-before-completion as a universal pre-claim gate; pair with test-driven-development when defining what tests must exist before verification runs.
FAQ
What is the verification-before-completion iron law?
verification-before-completion states NO COMPLETION CLAIMS WITHOUT FRESH VERIFICATION EVIDENCE. If the agent has not run the proving command in the same message, it cannot claim tests pass, builds succeed, or work is complete.
Does a previous test run count as verification?
verification-before-completion explicitly rejects previous runs, partial checks, linter-only success for build claims, and trusting subagent success reports. The full verification command must execute fresh with output read in the current message.
When must verification-before-completion apply?
verification-before-completion applies before any success or completion claim, expressions of satisfaction, commits, PR creation, task completion, moving to the next task, or delegating work—covering exact phrases, paraphrases, and implications of correctness.
Is Verification Before Completion safe to install?
skills.sh reports 3 of 3 security scanners passed. Review the Security Audits panel on this page before installing in production.