Skillget

verify

skill
Guvenlik Denetimi
Gecti
Health Gecti
  • License — License: MIT
  • Description — Repository has a description
  • Active repo — Last push 0 days ago
  • Community trust — 100 GitHub stars
Code Gecti
  • Code scan — Scanned 12 files during light audit, no dangerous patterns found
Permissions Gecti
  • Permissions — No dangerous permissions requested
Purpose
This tool acts as a verification layer for Claude Code. It reads your specification documents, uses browser agents to test each acceptance criterion against your local development server, and generates a pass/fail report with visual evidence.

Security Assessment
The tool runs local browser agents via Playwright against your local dev server. While it runs locally and requires no dangerous system permissions, the automation inherently interacts with web applications, which could involve local credentials or sensitive session data. The codebase was scanned and contains no dangerous patterns, hardcoded secrets, or out-of-bounds network requests. Overall risk is rated as Low for local development use.

Quality Assessment
The project is actively maintained, with repository activity as recent as today. It is backed by a solid community trust indicator with 100 GitHub stars. It uses the permissive MIT license and provides a clear, well-documented setup and usage guide.

Verdict
Safe to use.
SUMMARY

Verification Layer for Claude Code

README.md

opslane-verify

A verification layer for Claude Code. Reads your spec doc, runs one browser agent per acceptance criterion against your local dev server, and returns pass/fail with screenshots and video — before you push. No CI. No infrastructure.

How it works

graph LR
    A[spec doc] --> B[spec interpreter]
    B --> C[planner]
    C --> D[agent: AC 1]
    C --> E[agent: AC 2]
    C --> F[agent: AC n]
    D --> G[judge]
    E --> G
    F --> G
    G --> H[report]
  1. Spec Interpreter — reviews each AC for testability gaps, asks clarifying questions
  2. Planner — extracts testable acceptance criteria from the annotated spec
  3. Agents — one Claude + Playwright agent per AC, runs against your dev server
  4. Judge — reviews screenshots and traces, returns pass/fail per AC
  5. Report — prints results; failures include screenshot links and session recordings

Verify Report

Installation

Prerequisites

  • Claude Code with OAuth login (claude login)
  • Playwright MCP

Install

/plugin marketplace add opslane/verify
/plugin install opslane-verify@opslane/verify

macOS only: brew install coreutils (for gtimeout)

Usage

# One-time auth setup (skip if your app has no login)
/verify-setup

# Run verification — will ask you for the spec
/verify

/verify always asks for your spec upfront, then walks you through any clarifying questions before running.

Debugging failures

# View Playwright trace for a failed AC
npx playwright show-report .verify/evidence/<ac_id>/trace

# Watch session recording
open .verify/evidence/<ac_id>/session.webm

Yorumlar (0)

Sonuc bulunamadi