selenium-skill

selenium-skill is a skill for Claude Code, Codex from LambdaTest/agent-skills. It costs 129 tokens per session (2,271 once invoked), scanned A, original, MIT.

A guide for creating Selenium WebDriver browser tests in Java, Python, JavaScript, C#, Ruby, or PHP. Selenium controls real browsers to check how a website works across different browsers and operating systems.

In plain words
What is it for?
Use it to automate website actions and checks locally, on Selenium Grid, or through TestMu AI cloud, including cross-browser testing.
Why use it?
It removes the need to decide the test setup, language-specific tools, and local or cloud execution approach each time. It also helps cover browser combinations that may behave differently.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

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/lambdatest/agent-skills/selenium-skill
Any agent
npx skills add LambdaTest/agent-skills --skill selenium-skill
Clone the repo
git clone --depth 1 https://github.com/LambdaTest/agent-skills

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 selenium-skill

README.md
[![agentmods](https://agentmods.dev/badge/skills/lambdatest/agent-skills/selenium-skill.svg)](https://agentmods.dev/skills/lambdatest/agent-skills/selenium-skill)
Your own site
<a href="https://agentmods.dev/skills/lambdatest/agent-skills/selenium-skill"><img src="https://agentmods.dev/badge/skills/lambdatest/agent-skills/selenium-skill.svg" alt="Measured on agentmods" height="20"></a>
Per session 129 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,271 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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 5.1 $0.00129 $0.02271
Opus 5 $0.00064 $0.01136
Sonnet 5 $0.00026 $0.00454
Haiku 4.5 $0.00013 $0.00227

Measured 6d ago against content hash fc6802ecd174, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

selenium-skill scanned grade A with 0 findings 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 6d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/scaffold-project.sh), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

selenium-skill/SKILL.md · 260 lines

How it starts

The opening of the file, as written. The whole thing — 260 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Selenium Automation Skill

You are a senior QA automation architect. You write production-grade Selenium WebDriver scripts and tests that run locally or on TestMu AI cloud.

Step 1 — Execution Target

User says "automate" / "test my site"
│
├─ Mentions "cloud", "TestMu", "LambdaTest", "Grid", "cross-browser", "real device"?
│  └─ TestMu AI cloud (RemoteWebDriver)
│
├─ Mentions specific combos (Safari on Windows, old browsers)?
│  └─ Suggest TestMu AI cloud
│
├─ Mentions "locally", "my machine", "ChromeDriver"?
│  └─ Local execution
│
└─ Ambiguous? → Default local, mention cloud for broader coverage

Step 2 — Language Detection

Signal Language Config
Default / no signal Java Maven + JUnit 5
"Python", "pytest", ".py" Python pip + pytest
"JavaScript", "Node", ".js" JavaScript npm + Mocha/Jest
"C#", ".NET", "NUnit" C# NuGet + NUnit
"Ruby", ".rb", "RSpec" Ruby gem + RSpec
"PHP", "Codeception" PHP Composer + PHPUnit

For non-Java languages → read reference/<language>-patterns.md

Step 3 — Scope

Request Type Action
"Write a test for X" Single test file, inline setup
"Set up Selenium project" Full project with POM, config, base classes
"Fix/debug test" Read reference/debugging-common-issues.md
"Run on cloud" Read reference/cloud-integration.md

Core Patterns — Java (Default)

Locator Priority

1. By.id("element-id")           ← Most stable
2. By.name("field-name")         ← Form elements
3. By.cssSelector(".class")      ← Fast, readable
4. By.xpath("//div[@data-testid]") ← Last resort

NEVER use: fragile XPaths like //div[3]/span[2]/a, absolute paths.

Wait Strategy — CRITICAL

// ✅ ALWAYS use explicit waits
WebDriverWait wait = new WebDriverWait(driver, Duration.ofSeconds(10));
WebElement element = wait.until(ExpectedConditions.elementToBeClickable(By.id("submit")));

// ❌ NEVER use Thread.sleep() or implicit waits mixed with explicit
Thread.sleep(3000); // FORBIDDEN
driver.manage().timeouts().implicitlyWait(Duration.ofSeconds(10)); // Don't mix

Read the full file on GitHub · 260 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. 6d ago First seen · 260 lines · 129 tokens per session scan A fc6802ecd174

Subscribe to this mod's changes

selenium-skill is a skill published in the GitHub repository LambdaTest/agent-skills (366 stars, last pushed 1mo ago), licensed MIT. It adds 129 tokens to every session and 2,271 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.