Skip to content
Back to skills

Reproduce Before Report

ASecurity

Verify M2 reproduce-before-report phase 2a for Agent Looper dogfood.

  • 3 stars
  • 0 votes
  • 0 copies
  • 0 views
  • Added October 20, 2026
ai-agentsbash

Works with

  • cursor

Security analysis

A100/100

Pro scans all 5 files and shows the line behind each finding

Scanned October 20, 2026

npx -y skills add dancingteeth/agent-looper --skill reproduce-before-report --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Reproduce Before Report?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for Reproduce Before Report
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/dancingteeth-reproduce-before-report/badge)](https://www.skillsdirectory.com/skills/dancingteeth-reproduce-before-report)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
SKILL.md
---
name: loop-verify-reproduce-before-report
description: Verify M2 reproduce-before-report phase 2a for Agent Looper dogfood.
---

# Verify — reproduce-before-report

## Rules

1. Verifier wins — exit `0` from `verify.sh` only.
2. Fail → fix → rerun from step 1.
3. No partial handoff.
4. Scope: `src/review/`, `src/loop/loopConfig*`, related tests/docs only.

## Checklist

### Step 1 — Typecheck

```bash
pnpm exec tsc --noEmit
```

### Step 2 — Focused tests

```bash
pnpm exec vitest run \
  src/review/reviewVerdict.test.ts \
  src/review/reviewReproduce.test.ts \
  src/review/loopPostReview.test.ts \
  src/loop/loopConfig.test.ts \
  src/loop/agentLoop.test.ts
```

### Step 3 — Full suite

```bash
pnpm exec vitest run
```

### Step 4 — Loop verifier

```bash
bash .cursor/loops/reproduce-before-report/verify.sh
```

Files in this skill

  • GOAL.md1.7 KB
  • VERIFY.skill.md844 B
  • loop.json544 B
  • verify.sh627 B

Attribution

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments

Loading comments…

Newsletter

Get the weekly list of safe new skills, and the ones we pulled.