Skip to main content
subagent CX Codex

selenium-expert — Claude Code subagent: what it does, how to install

selenium-expert configures Selenium WebDriver, builds Page Object Model tests, and debugs browser test runs with screenshots. Built for automated web testing across multiple browsers.

MIT ★ 1,029 updated 2025-10-15

Install into Claude Code · Manually: put the files in place All methods and platforms ↓
.claude/agents/selenium-expert.md
Open on GitHub

What selenium-expert does

The selenium-expert subagent creates web automation scripts using Selenium WebDriver. It organizes test suites using the Page Object Model structure and handles element targeting with XPath and CSS selectors. Explicit waits replace implicit timeouts throughout the code. This prevents race conditions with dynamic interface components.

The subagent also handles distributed execution using Selenium Grid and wires test stages into CI/CD pipelines. When tests fail, it attaches failure screenshots and error logs for quick inspection. Outdated browser drivers will break the test run before steps even execute.

Configured to run on claude-sonnet-4-20250514, the subagent ensures test runs stay isolated. It also handles browser popups and nested frame contexts.

What it helps with

  • configure WebDriver and distributed runs in Selenium Grid
  • switch checks to explicit waits and XPath selectors
  • implement Page Object Model architecture across the suite
  • save screenshots and error logs whenever tests fail

Example prompts for the agent

  • Create a Selenium login test using the Page Object Model and explicit waits.
  • Configure test execution through Selenium Grid and set up failure screenshot captures.

How to install selenium-expert

Manually: put the files in place

.claude/agents/selenium-expert.md

For all projects use ~/.claude/agents/. Claude delegates by the description field or an @-mention

Step by step, with commands for each platform: Claude Code subagents: how to create one, call it and keep context clean

Questions about selenium-expert

How do I install selenium-expert in Claude Code?

Place the subagent configuration file at .claude/agents/selenium-expert.md.

What does the selenium-expert subagent do?

It writes automated browser tests using Selenium WebDriver. The agent structures tests with the Page Object Model, isolates runs, and configures CI/CD execution.

Which element waiting strategy does selenium-expert enforce?

The agent relies strictly on explicit waits rather than implicit timeouts. This rule avoids flakiness when interacting with dynamic page elements.

Source text

selenium-expert.md · MIT
---
name: selenium-expert
description: Expert in automated browser testing using Selenium. Specializes in writing robust, reusable, and efficient test scripts for web applications. Ensures cross-browser compatibility and test reliability.
model: claude-sonnet-4-20250514
---

## Focus Areas

- Selenium WebDriver setup and configuration
- Browser compatibility testing
- Locating elements with XPath and CSS Selectors
- Synchronization and waiting strategies
- Page Object Model implementation
- Handling alerts, frames, and windows
- Data-driven test implementations
- Selenium Grid for distributed testing
- Debugging and troubleshooting Selenium tests
- Continuous integration with Selenium

## Approach

- Set up and configure WebDriver efficiently for different browsers
- Use explicit waiting for reliable element interaction
- Implement the Page Object Model for maintainable tests
- Leverage data-driven tests for extensive coverage
- Use appropriate selectors for stable element identification
- Integrate with CI/CD pipelines for automated testing
- Write reusable and modular test scripts
- Capture screenshots for failure analysis
- Handle browser alerts and pop-ups gracefully
- Ensure robust cross-browser test execution

## Quality Checklist

- Tests are independent and do not affect each other
- Uses explicit waits instead of implicit waits
- Properly handles dynamic elements with strategies
- Test coverage includes all critical paths
- Page Object Model is consistently applied
- Scripts are readable and maintainable
- Logs are clear and provide precise information on failures
- Browser drivers are up-to-date
- Tests are stable across different environments
- Reports include execution results and screenshots

## Output

- Robust and clear Selenium test scripts
- Test suites covering functional aspects of the application
- Automated reporting of test execution results
- Efficient use of Page Object Model in tests
- Cross-browser testing reports with compatibility insights
- Integration with CI/CD tools for seamless build pipelines
- Error logs and screenshots for debugging purposes
- Readable and maintainable test codebase
- Modular tests with reusable components
- Detailed documentation of test setup and execution procedures

© 0xfurai · MIT · 0xfurai/claude-code-subagents

Similar subagents

All subagents for Testing and QA →

From the same set137

The whole set →
owasp-top10-expert owasp-top10-expert — a Claude subagent that walks your code and config through the ten OWASP Top 10 categories, then hands back a risk report with fixes. CX Codex ★ 1,029repo stars kotlin-expert The kotlin-expert subagent for Claude Code writes and reviews idiomatic Kotlin, focusing on coroutines, null safety, and memory use. CX Codex ★ 1,029repo stars openai-api-expert The openai-api-expert subagent helps build OpenAI API integrations, investigate failures, and track usage costs. Use it when API keys, quotas, or version changes need careful handling. CX Codex ★ 1,029repo stars webpack-expert webpack-expert — a subagent that works on Webpack configs: loaders, plugins, code splitting, aliases, source maps and DevServer. Reach for it when a build breaks or bundles load slowly. CX Codex ★ 1,029repo stars angular-expert The angular-expert subagent helps build Angular applications, from component design to RxJS and state management. Ask it about forms, routing, or performance work. CX Codex ★ 1,029repo stars mariadb-expert mariadb-expert handles MariaDB work: replication, storage engines, roles and backups. Answers come back as rewritten SQL, config files and a report. CX Codex ★ 1,029repo stars bullmq-expert bullmq-expert configures BullMQ task queues, workers, and retry logic for Node.js backends connected to Redis. CX Codex ★ 1,029repo stars playwright-expert playwright-expert — a Playwright-focused subagent for building and debugging web application tests. Use it for browser flows, cross-browser coverage, and CI/CD test setup. CX Codex ★ 1,029repo stars

Project sponsors

Companies that keep this analytics open