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.
npx skills add LambdaTest/agent-skills --skill capybara-skillgit clone --depth 1 https://github.com/LambdaTest/agent-skillsWrote 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.
[](https://agentmods.dev/skills/lambdatest/agent-skills/capybara-skill)<a href="https://agentmods.dev/skills/lambdatest/agent-skills/capybara-skill"><img src="https://agentmods.dev/badge/skills/lambdatest/agent-skills/capybara-skill/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/lambdatest/agent-skills/capybara-skill"><img src="https://agentmods.dev/badge/skills/lambdatest/agent-skills/capybara-skill.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00081 | $0.00975 |
| Opus 5 | $0.00041 | $0.00487 |
| Sonnet 5 | $0.00016 | $0.00195 |
| Haiku 4.5 | $0.00008 | $0.00097 |
Grade A, and why
capybara-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 10d ago.
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.
How it starts
The opening of the file, as written. The whole thing — 138 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Capybara Automation Skill
Core Patterns
Basic Test (RSpec)
require 'capybara/rspec'
RSpec.describe 'Login', type: :feature do
it 'logs in with valid credentials' do
visit '/login'
fill_in 'Email', with: '[email protected]'
fill_in 'Password', with: 'password123'
click_button 'Login'
expect(page).to have_content('Dashboard')
expect(page).to have_current_path('/dashboard')
end
it 'shows error for invalid credentials' do
visit '/login'
fill_in 'Email', with: '[email protected]'
fill_in 'Password', with: 'wrong'
click_button 'Login'
expect(page).to have_content('Invalid credentials')
end
end
DSL
# Navigation
visit '/path'
go_back
go_forward
# Interacting
fill_in 'Label or Name', with: 'text'
choose 'Radio Label'
check 'Checkbox Label'
uncheck 'Checkbox Label'
select 'Option', from: 'Select Label'
attach_file 'Upload', '/path/to/file'
click_button 'Submit'
click_link 'More Info'
click_on 'Button or Link'
# Finding
find('#id')
find('.class')
find('[data-testid="x"]')
find(:xpath, '//div')
all('.items').count
# Matchers
expect(page).to have_content('text')
expect(page).to have_selector('#element')
expect(page).to have_css('.class')
expect(page).to have_button('Submit')
expect(page).to have_field('Email')
expect(page).to have_link('Click Here')
expect(page).to have_current_path('/expected')
expect(page).to have_no_content('error')
Within Scope
within('#login-form') do
fill_in 'Email', with: '[email protected]'
click_button 'Login'
end
within_table('users') do
expect(page).to have_content('Alice')
end
TestMu AI Cloud
Capybara.register_driver :lambdatest do |app|
caps = Selenium::WebDriver::Remote::Capabilities.new(
browserName: 'chrome',
'LT:Options' => {
user: ENV['LT_USERNAME'], accessKey: ENV['LT_ACCESS_KEY'],
build: 'Capybara Build', name: 'Login Test',
platform: 'Windows 11', video: true
}
)
Capybara::Selenium::Driver.new(app,
browser: :remote,
url: 'https://hub.lambdatest.com/wd/hub',
capabilities: caps)
end
Capybara.default_driver = :lambdatest
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 10d ago First seen · 138 lines · 81 tokens per session scan A 62cb951db6d9
capybara-skill is a skill published in the GitHub repository LambdaTest/agent-skills (366 stars, last pushed 1mo ago), licensed MIT. It adds 81 tokens to every session and 975 once invoked, about $0.0004 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.
Other skills, from other repositories
tui-test
Control, inspect, test, and record real terminal apps with the tui-test CLI or its Rust, Python, and JavaScript APIs. Use for shells, TUI apps, text and style locators, keyboard or mouse input, terminal state, clipboard waits, screenshots, recordings, snapshots, and live terminal sessions.
aspire-integration-testing
Write integration tests using .NET Aspire's testing facilities with xUnit. Covers test fixtures, distributed application setup, endpoint discovery, and patterns for testing ASP.NET Core apps with real dependencies.
Codeception Testing
Expert-level Codeception testing skill for PHP applications. Covers acceptance, functional, and unit testing with the Actor pattern, BDD-style syntax, Page Objects, API testing, and database helpers.
JMeter Load Testing
Load and performance testing skill using Apache JMeter, covering test plans, thread groups, assertions, listeners, timers, and distributed testing.
Laravel Dusk Testing
Expert-level Laravel Dusk browser testing skill for PHP/Laravel applications. Covers Chrome-based E2E testing, browser assertions, Page Objects, component testing, authentication helpers, and database integration.
133-java-testing-acceptance-tests
Use when you need to implement acceptance tests from maintainer-sanitized Gherkin scenario facts for framework-agnostic Java (no Spring Boot, Quarkus, Micronaut) — confirming @acceptance scenarios before coding, happy path with RestAssured, DB/Kafka test fixtures, WireMock for external REST only, and AT classes run by…