Use when about to claim work is complete, fixed, or passing. Run verification and paste output before any success claim.
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# 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.
Use `verify-loop` to define that command before writing code. Run the wrappers in `verify-loop/scripts/` (`verify.py`, `verify.sh`, or `check-snapshot-console.cjs`). Paste the runner's `VERIFY_PASS` or `VERIFY_FAIL` line. Do not copy errors between tools by hand.
## 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 |
|-------|----------|----------------|
…
The line at the top of this page pins the label git:20261006.876cce4, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
GET https://markdownregistry.com/api/v1/artifacts/art_n5xy4nhovpiqxnmr
GET https://markdownregistry.com/api/v1/resolve?ref=kunanonj/ai-skills-hub/verification-before-completion
GET https://markdownregistry.com/api/v1/blob/f981ddcf0c8e43b8bf8c1dd47113604f1ce7cab602db11d8d7dfe37dc75aa8bd
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
kunanonj/ai-skills-hub · plugins/superstacks/skills/code-review/SKILL.md · Use when reviewing a branch, PR, or WIP since a commit, tag, or merge-base. Two-axis Standards and Spec review via…
kunanonj/ai-skills-hub · plugins/superstacks/skills/diagnosing-bugs/SKILL.md · Use when the user says diagnose or debug this, or reports something broken, throwing, failing, or slow.
kunanonj/ai-skills-hub · plugins/superstacks/skills/domain-modeling/SKILL.md · Use when discussing codebase terminology, writing or editing a GLOSSARY.md, or recording or editing an ADR.
kunanonj/ai-skills-hub · plugins/superstacks/skills/gardening/SKILL.md · Use when finding small maintenance work. One concern per PR, each with a verify command and a small diff budget.
kunanonj/ai-skills-hub · plugins/superstacks/skills/grill-with-docs/SKILL.md · Use when grilling a plan or design that should also produce ADRs and a glossary as you go.
kunanonj/ai-skills-hub · plugins/superstacks/skills/grilling/SKILL.md · Use when the user wants to stress-test a plan, decision, or idea, or uses any grill trigger phrases.
kunanonj/ai-skills-hub · plugins/superstacks/skills/how/SKILL.md · Use for how-does-X-work walkthroughs, placement, ownership, and layering questions before changing code.
kunanonj/ai-skills-hub · plugins/superstacks/skills/intake-triage/SKILL.md · Use when a coordinator has a batch of bug reports, feedback, or alerts. Deduplicate, group, score two-way vs one-way…
kunanonj/ai-skills-hub · plugins/superstacks/skills/interrogate/SKILL.md · Use for interrogate, adversarial review, multi-model review, challenge this, stress test this code, or find blind spots.
kunanonj/ai-skills-hub · plugins/superstacks/skills/mistake-to-constraint/SKILL.md · Use when a mistake repeats. Encode it as the strongest guard — type or runtime, lint, test, directory convention, then…
obra/superpowers · skills/verification-before-completion/SKILL.md · Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running…
mvschwarz/openrig · packages/daemon/specs/agents/shared/skills/process/verification-before-completion/SKILL.md · Use when about to claim work is complete, fixed, or passing, or before committing or creating PRs
mvschwarz/openrig · skills/_canonical/process/verification-before-completion/SKILL.md · Use when about to claim work is complete, fixed, or passing, or before committing or creating PRs
a5c-ai/babysitter · library/methodologies/superpowers/skills/verification-before-completion/SKILL.md · Use when about to claim work is complete, fixed, or passing, before committing or creating PRs. Evidence before…
a5c-ai/babysitter · library/methodologies/cc10x/skills/verification-before-completion/SKILL.md · Evidence requirement enforcement ensuring all claims are backed by logs, test results, or exit codes. Zero = success…
ganyuanran/aegis · skills/verification-before-completion/SKILL.md · Use when about to claim work is complete, fixed, passing, verified, release-ready, or ready to commit, merge, publish…
coco-research/coco · skills/verification-before-completion/SKILL.md · Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running…