# Verification Before Completion

> Run the verification and read its output before claiming work is complete, fixed, or passing — evidence first, claim second. Use before any completion claim, commit, PR, or harvest.

- **Type:** Skill
- **Install:** `agentstack add skill-skywalkercyt-mp-implement-verification-before-completion`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [skywalkercyt](https://agentstack.voostack.com/s/skywalkercyt)
- **Installs:** 0
- **Category:** [Agent Skills](https://agentstack.voostack.com/c/agent-skills)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [skywalkercyt](https://github.com/skywalkercyt)
- **Source:** https://github.com/skywalkercyt/mp-implement/tree/main/skills/verification-before-completion

## Install

```sh
agentstack add skill-skywalkercyt-mp-implement-verification-before-completion
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## About

# Verification Before Completion

> **Adapted skill** — discipline originating in Superpowers v5.1.0 (MIT, Jesse Vincent), rewritten in mattpocock-skills style. The honesty gate in `/mp-implement-issue` step 7 and both pipelines' harvest — no slice counts as done until it passes.

**Iron law: no completion or success claim without fresh verification evidence produced in this step.** A claim made before its verification is a guess dressed as a fact.

## The gate

For each claim you are about to make:

1. Name the command that proves it.
2. Run that command in full — fresh, in this step.
3. Read the complete output and the exit code.
4. If the output confirms the claim, make the claim and quote the evidence ("34/34 pass", "exit 0"). If it contradicts the claim, state the actual status with the evidence instead.

Evidence means output from the run you just did. "Should pass", an earlier run, a partial check, a linter where tests are owed, or another agent's self-report are not evidence — a sub-agent's "success" is a lead to verify (check the diff), not a result.

## Regression tests

A regression test proves red-green: revert the fix and watch the test fail, restore the fix and watch it pass. A test that never failed proves nothing about the fix.

## Requirements

"Tests pass" is not "requirements met". Close out by re-reading the source checklist (issue, spec, plan) and verifying each requirement line by line; report any gap as its actual status.

## Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [skywalkercyt](https://github.com/skywalkercyt)
- **Source:** [skywalkercyt/mp-implement](https://github.com/skywalkercyt/mp-implement)
- **License:** MIT

Install and usage instructions live in the source repository linked above.

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** no
- **Filesystem access:** no
- **Shell / process execution:** no
- **Environment & secrets:** no
- **Dynamic code execution:** no

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: passed — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/skill-skywalkercyt-mp-implement-verification-before-completion
- Seller: https://agentstack.voostack.com/s/skywalkercyt
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.