Geb Testing

Geb Testing is a skill for Claude Code, Codex from PramodDutta/qaskills. It costs 34 tokens per session (4,209 once invoked), scanned A, original, MIT.

A skill for Geb, a Groovy-based framework that automates browsers through WebDriver. It organizes pages and reusable interface parts so tests can interact with web applications consistently.

In plain words
What is it for?
Use it to create, review, debug, and structure browser tests with page objects, reusable modules, and WebDriver.
Why use it?
It helps reduce brittle browser tests by centralizing page structure and handling dynamic content waits. It also connects browser tests with Spock, a testing framework for the JVM.

Skill for Claude CodeCodex

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/pramoddutta/qaskills/geb-testing
Any agent
npx skills add PramodDutta/qaskills --skill geb-testing
Clone the repo
git clone --depth 1 https://github.com/PramodDutta/qaskills

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for Geb Testing

README.md
[![agentmods](https://agentmods.dev/badge/skills/pramoddutta/qaskills/geb-testing.svg)](https://agentmods.dev/skills/pramoddutta/qaskills/geb-testing)
Your own site
<a href="https://agentmods.dev/skills/pramoddutta/qaskills/geb-testing"><img src="https://agentmods.dev/badge/skills/pramoddutta/qaskills/geb-testing.svg" alt="Measured on agentmods" height="20"></a>
Per session 34 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,209 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00034 $0.04209
Opus 5 $0.00017 $0.02105
Sonnet 5 $0.00007 $0.00842
Haiku 4.5 $0.00003 $0.00421

Measured yesterday against content hash b198af8d8522, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

Geb Testing scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -s http://localhost:3000/health && break
seed-skills/geb-testing/SKILL.md · 544 lines

How it starts

The opening of the file, as written. The whole thing — 544 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Geb Testing

You are an expert QA engineer specializing in Geb, the Groovy-based browser automation framework built on top of WebDriver. When the user asks you to write, review, debug, or set up Geb tests, follow these detailed instructions. You understand the Geb ecosystem deeply including the jQuery-like content DSL, Page Object pattern with content blocks, module composition, Spock integration, waiting/polling, and configuration management.

Core Principles

  1. Content DSL — Use Geb's declarative content blocks in Page Objects to define element references. The jQuery-like $() navigator provides powerful element selection.
  2. Page Object Pattern — Every page interaction goes through a Page class with static content definitions. Pages define their url, at checker, and navigable content.
  3. Module Composition — Extract reusable UI components (headers, footers, modals, tables) into Module classes that can be embedded in multiple pages.
  4. Implicit Assertions — Geb automatically waits for at checkers to pass during page transitions. Use waitFor {} for dynamic content.
  5. Spock Integration — Use GebSpec or GebReportingSpec as the base class for tests. Spock's BDD-style given/when/then blocks pair naturally with Geb.
  6. Configuration Over Code — Use GebConfig.groovy for browser selection, base URL, waiting strategies, and reporting. Keep tests focused on behavior.
  7. Navigator API — Master the $() navigator for element selection. Chain methods like .text(), .value(), .click(), .attr() for fluent interactions.

Project Structure

project-root/
├── build.gradle                      # Gradle build with Geb dependencies
├── src/
│   └── test/
│       ├── groovy/
│       │   ├── pages/
│       │   │   ├── BasePage.groovy
│       │   │   ├── LoginPage.groovy
│       │   │   ├── DashboardPage.groovy
│       │   │   └── CartPage.groovy
│       │   ├── modules/
│       │   │   ├── NavBarModule.groovy
│       │   │   ├── ModalModule.groovy
│       │   │   └── TableModule.groovy
│       │   ├── specs/
│       │   │   ├── auth/
│       │   │   │   ├── LoginSpec.groovy
│       │   │   │   └── RegistrationSpec.groovy
│       │   │   ├── shopping/
│       │   │   │   └── CartSpec.groovy
│       │   │   └── smoke/
│       │   │       └── SmokeSpec.groovy
│       │   └── helpers/
│       │       ├── TestDataHelper.groovy
│       │       └── ApiHelper.groovy
│       └── resources/
│           └── GebConfig.groovy      # Geb configuration
├── reports/
│   └── geb/
└── gradle/
    └── wrapper/

Read the full file on GitHub · 544 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. yesterday First seen · 544 lines · 34 tokens per session scan A b198af8d8522

Subscribe to this mod's changes

Geb Testing is a skill published in the GitHub repository PramodDutta/qaskills (217 stars, last pushed 5d ago), licensed MIT. It adds 34 tokens to every session and 4,209 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.

Related

Other skills, from other repositories

ui-automation

WHartTest UI 自动化管理工具。用于创建、编辑、删除 UI 测试模块、页面、元素、页面步骤和测试用例。支持执行记录查询和错误分析。当需要将浏览器技能获取到的页面元素保存到平台、创建 UI 自动化用例、执行测试或分析执行结果时使用。元素采集默认优先 browser-use,无法覆盖时再用 playwright-skill 兜底。.

MGdaasLab/WHartTest · 96 tokens

playwright-skill

浏览器自动化执行工具。用于执行 Web 页面测试、表单填写、登录验证、截图等浏览器操作。.

MGdaasLab/WHartTest · 31 tokens

muggle-test

Change-driven E2E acceptance testing: detects the user's recent changes (local diff or PR), maps them to affected user flows, and runs real-browser tests on localhost or a preview/staging URL. Invoke it before inspecting anything — what changed and what it affects is its own first step; reading the diff by hand…

multiplex-ai/muggle-ai-works · 226 tokens

muggle-test-feature-local

Run a real-browser end-to-end (E2E) acceptance test against localhost to verify a feature works correctly — signup flows, checkout, form validation, UI interactions, or any user-facing behavior. Launches a browser that executes test steps and captures screenshots. The browser runs under a real identity: each managed…

multiplex-ai/muggle-ai-works · 0 tokens

browser-automation

Enterprise-grade browser automation using WebDriver protocol. Use when the user needs to automate web browsers, perform web scraping, test web applications, fill forms, take screenshots, monitor performance, or execute multi-step browser workflows. Supports Chrome, Firefox, and Edge with connection pooling and health…

EmilLindfors/rust-browser-mcp · 61 tokens

actionbook-web-test

Run browser-based web tests against websites using Actionbook CLI. Activate when the user wants to test a website workflow, run smoke tests, verify a user flow, check if a web application works, run regression tests, or validate browser-based interactions. Supports test definition, execution, assertion, reporting, and…

actionbook/actionbook · 71 tokens