Requires running verification commands and reading their actual output before any claim that work is complete, fixed, or passing. Use when about to say done, tests pass, or bug fixed; before committing, a PR, or trusting a subagent's report; or when asked to run the full quality gate (build, types, lint, tests, secrets, diff).
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.**
**Announce at start:** "Using opm:verification-before-completion before claiming this is done."
## The Iron Law
```
NO COMPLETION CLAIMS WITHOUT FRESH VERIFICATION EVIDENCE
```
If you have not 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
```
## Quick Gate or Full Gate
- **Quick gate:** the Gate Function above, for any done claim.
- **Full gate:** before a PR, a release, or a phase close (or when asked for the full verification loop), read `references/full-loop.md` and run all six gates: build, types, lint, tests, secrets, diff review.
…
The line at the top of this page pins the label git:20261005.02a76f6, 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.
A 17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
pass: Frontmatter block present
pass: Frontmatter declares a name
pass: Frontmatter declares a description
pass: Size between 200 bytes and 200 KB (5484 bytes)
pass: No zero-width or bidi control characters
pass: No instruction hidden inside an HTML comment
pass: No link to an exfiltration or paste host
pass: No credential-shaped string
pass: No instruction to send local credentials anywhere
pass: No text hidden with inline styles
pass: No prompt-injection phrasing
pass: No curl or wget piped into a shell
pass: No recursive delete of root, home or parent
pass: No instruction to read or print local credentials
pass: No base64 blob over 200 characters
pass: No link to a raw IP address
pass: No script tag
Source
GitHub
harshadmadaye/opm · 5 stars · license MIT · pushed 2026-10-05 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_ikfo2a5h4r54chzr
GET https://markdownregistry.com/api/v1/resolve?ref=harshadmadaye/opm/verification-before-completion
GET https://markdownregistry.com/api/v1/blob/e78c66003ca3327592ab8a6ae30b38fb213c92646314522f21f8cd025e97dc7e
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.
harshadmadaye/opm · plugins/opm-video/skills/explainer-video/SKILL.md · Turns a spec or document into a narrated explainer video. Produces a 1920x1080 MP4 of illustrated still slides with a…
harshadmadaye/opm · skills/brainstorming/SKILL.md · Turns a rough idea into an approved design or written spec through one-question-at-a-time dialogue, scaled to spike…
harshadmadaye/opm · skills/brew-idea/SKILL.md · Runs a multi-agent debate over a project idea. Four angle agents (product, engineering, skeptic, market research)…
harshadmadaye/opm · skills/compound-learnings/SKILL.md · Captures a solved, non-obvious problem as a durable learning doc under docs/solutions/ with validated frontmatter, and…
harshadmadaye/opm · skills/executing-plans/SKILL.md · Executes a written implementation plan task-by-task by dispatching a fresh implementer subagent per task, a reviewer…
harshadmadaye/opm · skills/jump-start/SKILL.md · Creates an entire new project from one prompt. Takes a project name plus a brief, clarifies only what would change the…
harshadmadaye/opm · skills/milestone-planning/SKILL.md · Structures multi-week work as a milestone with a roadmap, a short always-read STATE digest, phased executable PLAN…
harshadmadaye/opm · skills/python-patterns/SKILL.md · Provides idiomatic modern Python (3.11+) patterns covering type hints, dataclasses and pydantic at boundaries, pathlib…
harshadmadaye/opm · skills/tdd-workflow/SKILL.md · Drives test-driven development through a strict RED-GREEN-REFACTOR cycle with test-runner detection, a "fails for the…
harshadmadaye/opm · skills/using-opm/SKILL.md · Establishes how to find and invoke OPM skills before taking any other action, including clarifying questions. Use when…
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, before committing or creating PRs - requires running…
mvschwarz/openrig · skills/_canonical/process/verification-before-completion/SKILL.md · Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running…
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…
