agentleFS
christopherarterchristopherarter/superpowers-reasonix/skills/superpowers-verification-before-completion/SKILL.md

superpowers-verification-before-completion

Skill101 starsChanged 30 days agoMITView on GitHub

About to say done, fixed, or passing? STOP. Load first, show real evidence.

3 other projects use a version of this, 2 of them edited.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 2 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Commit, PR, task completion

    line 114
  2. Distinctive:

    Run the command. Read the output.

    line 124

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Verification Before Completion

Overview

Claiming work complete without verification = dishonesty, not efficiency.

Core principle: Evidence before claims, always.

Break the letter = break the spirit.

The Iron Law

NO COMPLETION CLAIMS WITHOUT FRESH VERIFICATION EVIDENCE

Haven't run the verification command in this message? 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) via bash
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
Subagent completedVCS diff shows changesSubagent reports "success"
Requirements metLine-by-line checklistTests passing

Red Flags - STOP

  • "should", "probably", "seems to"
  • Satisfaction before verification ("Great!", "Perfect!", "Done!", etc.)
  • About to commit/push/PR unverified
  • Trusting subagent success reports
  • Relying on partial verification
  • "just this once"
  • Tired, want 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
"Subagent said success"Verify independently
"I'm tired"Exhaustion ≠ excuse
"Partial check is enough"Partial proves nothing
"Different words, 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"

Subagent delegation:

✅ Subagent reports success → Check VCS diff → Verify changes → Report actual state
❌ Trust subagent report

When To Apply

ALWAYS before:

  • ANY success/completion claim
  • ANY expression of satisfaction
  • ANY positive statement about work state
  • Commit, PR, task completion
  • Next task
  • Delegating to subagents

Applies to: exact phrases, paraphrases, 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.

Non-negotiable.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.