verification-before-completion

Use it when: the agent is about to say work is done, fixed or passing, or to commit, open a PR or move on
It does: makes it run the command that proves the claim, read the full output, and only then report what it shows
Forbids: "should work now", "looks correct" and an early "Done!" or "Perfect!" without fresh evidence
Also covers: subagents: when one reports success, the agent checks the actual diff before believing it

Skill 12 of 14 in the Superpowers bundle · Before it: systematic-debugging · After it: dispatching-parallel-agents

TLDR

Its rule is "no completion claims without fresh verification evidence". Before any claim of success, or even a pleased "Great!", the agent names the command that would prove it, runs it in full, reads the output and exit code, and then states the result with the evidence, or the real status if it falls short. A run from earlier in the session doesn't count. It spells out what each claim needs: zero failures in the test output for "tests pass", a build that exits cleanly for "build succeeds" (a passing linter isn't enough), the original symptom retested for "bug fixed", and a line-by-line check against the plan for "requirements met". A new regression test only counts once it's been seen to fail with the fix undone. It lists the usual excuses (I'm confident, just this once, I'm tired), and tells the agent to treat words like "should" and "probably" as a sign to stop and run the check.

Summarizes the skill at bb92a77.

npx skills add https://github.com/obra/superpowers --skill verification-before-completion

skills.sh page · Source on GitHub · All skills from obra/superpowers

Installs: 216,670 on skills.sh, Sep 21, 2026
Repo stars: 289,267 obra/superpowers
First seen: Jan 19, 2026 on skills.sh

Weekly installs

7.1K

-4% over 8 weeks · week to Sep 21

Weekly values

Week to	Installs
Aug 3	7,401
Aug 10	7,587
Aug 17	7,030
Aug 24	8,295
Aug 31	7,178
Sep 7	7,254
Sep 14	7,274
Sep 21	7,096

Category	category:engineering category:software-engineering Test-first work, implementation from specs, git hygiene and scope control. Everything for building software: planning, coding, debugging, design, frameworks, cloud, agents and skills.
Type	type:workflow A multi-step process the agent follows: interview, debug, run a TDD loop, review.
Effect	effect:none Adds no side effects of its own. It shapes how the agent thinks, writes or reviews. Guidelines and routers are always effect:none, even when the task they support edits code.
Needs	needs:none Instructions only. Works in any agent that supports skills.
Publisher	by:community Everyone else. Unverified vendor claims default to community.
Topics	verification testing agent-workflows

SKILL.md

From obra/superpowers at bb92a77. Checked daily, last changed Oct 20, 2026.

Frontmatter

name: verification-before-completion
description: 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

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