Verification before completion
Stops the agent from saying "done" or "tests pass" until it has rerun the check and read the whole output. Use whenever the agent reports success, commits or opens a pull request.
verification-before-completion- Author
- Jesse Vincent
- Source
- obra/superpowers/skills/verification-before-completion @ 22f0b46
- License
- MIT · Copyright (c) 2025 Jesse Vincent
About this skill
What it does
The skill stops the agent from saying "done", "fixed" or "tests pass" without proof. Before any such claim, a commit, a PR or the next task, it has to name the command that proves the claim, run it in full right now, read the whole output with the exit code, and only then report — with the evidence. An earlier run, "should pass" or a subagent's word does not count.
The skill is a single SKILL.md, mostly tables. One matches each claim to its evidence: a build needs exit 0, not a clean linter; a fixed bug needs the original symptom retested; a regression test needs a red-green check (revert the fix, watch the test fail); a delegated task needs the VCS diff. The others list the excuses agents use and the words that give an unchecked claim away — "should", "probably", or a "Great" before anything ran. A claim in other words is still a claim.
When to use it, and when not
Use it wherever the agent reports its own results: fixes, test runs, builds, delegated work, plans where each "done" opens the next step — above all once you have caught it claiming success it never checked.
It adds nothing when the agent claims nothing about the work: answering a question or explaining code. In a project with no tests and no build it cannot invent evidence; it only makes the agent say what it could not check.
How to run it
The install command below puts SKILL.md and the licence in place. The agent picks the skill up by its description before it reports success or commits; to call it yourself:
- Claude Code:
/verification-before-completion, or ask for the skill by name. - Codex:
$verification-before-completion. - Cursor: type
/in the Agent chat and pickverification-before-completion.
Example: /verification-before-completion Before you push, prove the migration fix works: run the tests and the build and show me the output.
It calls no other skills; executing-plans uses it to accept each task and systematic-debugging before reporting a fix.
How it differs from similar skills
Self-review before PR from our catalog is a checklist over the diff — debug leftovers, secrets, scope, tests, migrations — where "do not claim tests pass unless you ran them in this session" is one line among many. Verification before completion turns that line into a rule for every status message, not only the one before a PR. Release checklist decides whether a release is safe to ship and checks production after the deploy; it does not police what the agent claims along the way. Define a measurable goal settles before the work starts what evidence will prove it done; this skill demands that evidence, freshly run, before every claim. Doubt-driven development takes claims a test run cannot settle, such as "this is safe" or "this scales", and gives them to a fresh-context subagent told to find what is wrong.
Install
Run one command — it saves SKILL.md and the files it uses into your agent's skills folder. Claude Code and Codex pick up a new skill without a restart; if it does not show up, restart the agent.
curl -fsSL --create-dirs -o ~/.claude/skills/verification-before-completion/SKILL.md https://anymodel.org/en/skills/superpowers/verification-before-completion/SKILL.md -o ~/.claude/skills/verification-before-completion/LICENSE https://anymodel.org/en/skills/superpowers/verification-before-completion/LICENSE
curl -fsSL --create-dirs -o ~/.agents/skills/verification-before-completion/SKILL.md https://anymodel.org/en/skills/superpowers/verification-before-completion/SKILL.md -o ~/.agents/skills/verification-before-completion/LICENSE https://anymodel.org/en/skills/superpowers/verification-before-completion/LICENSE
foreach ($f in 'SKILL.md','LICENSE') { $p = Join-Path "$HOME\.claude\skills\verification-before-completion" $f; New-Item -ItemType Directory -Force (Split-Path $p) | Out-Null; Invoke-WebRequest "https://anymodel.org/en/skills/superpowers/verification-before-completion/$f" -UseBasicParsing -OutFile $p }foreach ($f in 'SKILL.md','LICENSE') { $p = Join-Path "$HOME\.agents\skills\verification-before-completion" $f; New-Item -ItemType Directory -Force (Split-Path $p) | Out-Null; Invoke-WebRequest "https://anymodel.org/en/skills/superpowers/verification-before-completion/$f" -UseBasicParsing -OutFile $p }Any other agent: save the file into its skills folder, or give it the link to the file: https://anymodel.org/en/skills/superpowers/verification-before-completion/SKILL.md
SKILL.md
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
Connect through AnyModel API
This skill runs on whatever model your agent uses. Point Claude Code, Codex or Cursor at AnyModel to run it on Claude, GPT, Gemini and more with one key — pay per token, no subscription.
AnyModel