cloud-test-grids

cloud-test-grids is a skill for Claude Code from aks-builds/quality-skills. It costs 136 tokens per session (2,438 once invoked), scanned A, original, MIT.

Guidance for testing websites across hosted browsers and mobile apps across hosted real devices or virtual devices. These services provide remote test environments such as BrowserStack, Sauce Labs, or Firebase Test Lab.

In plain words
What is it for?
Use it to choose and configure a cloud test provider, connect Selenium, Playwright, Cypress, Appium, or similar tools, and plan concurrent test runs.
Why use it?
It helps handle differences between browsers, devices, testing tools, pricing, and data-residency or compliance needs.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the quality-skills plugin — 57 skills shipped together

Good fit Use it to choose and configure a cloud test provider, connect Selenium, Playwright, Cypress, Appium, or similar tools, and plan concurrent test runs.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/aks-builds/quality-skills/cloud-test-grids
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.

Any agent
npx skills add aks-builds/quality-skills --skill cloud-test-grids
Clone the repo
git clone --depth 1 https://github.com/aks-builds/quality-skills

Made for: Claude Code.

Or install quality-skills, the plugin that ships this one along with the rest of its 57 skills.

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 cloud-test-grids

README.md
[![agentmods](https://agentmods.dev/badge/skills/aks-builds/quality-skills/cloud-test-grids/github.svg)](https://agentmods.dev/skills/aks-builds/quality-skills/cloud-test-grids)
Your own site
<a href="https://agentmods.dev/skills/aks-builds/quality-skills/cloud-test-grids"><img src="https://agentmods.dev/badge/skills/aks-builds/quality-skills/cloud-test-grids/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.

agentmods 80×15 button for cloud-test-grids

Your own site · 80×15
<a href="https://agentmods.dev/skills/aks-builds/quality-skills/cloud-test-grids"><img src="https://agentmods.dev/badge/skills/aks-builds/quality-skills/cloud-test-grids.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 136 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,438 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00136 $0.02438
Opus 5 $0.00068 $0.01219
Sonnet 5 $0.00027 $0.00488
Haiku 4.5 $0.00014 $0.00244

Measured 9d ago against content hash 2c607d551a90, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

cloud-test-grids 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 9d 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.

skills/cloud-test-grids/SKILL.md · 252 lines

How it starts

The opening of the file, as written. The whole thing — 252 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Cloud Test Grids

You are an expert in managed cloud-hosted browser and device test farms — BrowserStack, Sauce Labs, LambdaTest, AWS Device Farm, Firebase Test Lab, Perfecto, Kobiton, and friends. Your goal is to help engineers integrate against the right provider, configure capabilities correctly, manage cost, and avoid the common cross-provider pitfalls. Don't fabricate provider features, capability names, or pricing. When uncertain, point the reader to the provider's docs.

Initial Assessment

Check .agents/qa-context.md (fallback: .claude/qa-context.md) before answering. Pay attention to:

  • What are you testing? — Web (browsers), mobile (real or virtual), or both. Different providers excel at different things.
  • Real device vs emulator/simulator — affects cost dramatically.
  • Compliance — some providers offer FedRAMP / HIPAA / dedicated environments; data residency matters for some orgs.
  • Existing tool — Selenium / Playwright / Cypress / Appium / WebDriverIO. Some providers integrate more tightly with specific tools.
  • Scale — minutes per month, concurrent sessions.

If the file does not exist, ask: web / mobile / both, real / virtual devices, compliance scope, primary test tool, scale.


When cloud grids are worth it

  • You need 50+ browser × OS combinations. Self-host is operationally impractical.
  • You need real mobile devices — iOS especially. AWS Device Farm, Firebase Test Lab, BrowserStack, Sauce all offer real device pools.
  • You don't want to operate browser/device infrastructure. Opex on Grid + iOS Mac builders is significant.
  • You need geographic distribution — some providers offer test locations in EU / APAC / etc.
  • Low-to-medium volume — usually cheaper net-of-opex than self-host.

When self-host wins: see selenium-grid for the inverse case.


Major providers

Provider Strengths Notes
BrowserStack Broad browser + device coverage, mature, App Live (manual), Automate (programmatic) Industry default; expensive at scale
Sauce Labs Mature, strong CI integrations, Sauce Connect tunneling Long-running player; mature analytics
LambdaTest Wider catalog, often more affordable, AI-test features Newer entrant; aggressive expansion
AWS Device Farm Real-device cloud, native AWS integration, IAM-driven Mobile-focused; less ergonomic for web
Firebase Test Lab Real Android devices + iOS via integration, Google's runtime Android-strong; iOS coverage smaller
Perfecto Enterprise mobile, regulated industries Heavyweight
Kobiton Real-device mobile, manual + automation
Headspin Real-device + perf instrumentation Specialized for perf testing on mobile
TestGrid Open-source-style cloud option Emerging

Read the full file on GitHub · 252 lines

Files

What ships with it

1 file 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.

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. 9d ago First seen · 252 lines · 136 tokens per session scan A 2c607d551a90

Subscribe to this mod's changes

cloud-test-grids is a skill published in the GitHub repository aks-builds/quality-skills (2 stars, last pushed 6d ago), licensed MIT. It adds 136 tokens to every session and 2,438 once invoked, about $0.0007 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 2026-08-31.