Agent templatev1.1Updated 2026-11-03

Responsive Browser Lab

Check your website at phone, tablet and desktop sizes. Get a report of what broke, how to reproduce it and which checks actually ran.

  • Phone, tablet and desktop sizes in cloud Chromium
  • Evidence, reproduction steps and severity in one report
  • Prepaid browser access; no provider API key
Clone this project Use from Claude / Codex

By FlyMy.AI templates/website-qa-responsive v1.1

Responsive Browser Lab: Responsive Browser Lab with Browser Use
Responsive Browser Labgpt-6-luna
Browser Use

$ YOUR NEXT RUN

Claude CodeCodexCursorAny agent

Use Responsive Browser Lab in your assistant

Paste this prompt into Claude Code, Codex, Cursor or any agent. It reads the guide and helps you connect.

Read https://flymy.ai/templates/website-qa-responsive/template.txt and help me set up Responsive Browser Lab using my own connections. Ask for the missing inputs and budget before running it.
Open public projectDownload brief

Proof

  • Public projectCopy it to your account
  • Copy checkedSetup uses your own inputs and connections
  • Partial coverageWidths applied; viewport heights differed
1agentone QA agent
1toolspriced below
on demandrunsschedule after the first report
Usage-basedconfirm budget firstyour usage determines the cost

What it does

  • Cloud Chromium with a requested screen size for each profile. The report records the actual viewport, including any mismatch. This is screen-size simulation, not native Safari or physical-device testing.
  • Check text fit, horizontal overflow, missing images and sticky overlaps.
  • Open and close menus, then follow navigation within the selected routes.
  • Report evidence, reproduction steps and severity; list checks that could not run.

Ideal for Teams checking public websites before a release, with explicit coverage and reproducible findings.

Connects to

  • Browser UsePrepaid / usage-basedbuilt in

Project diagram

from the reference project
Project diagram of Responsive Browser LabINPUTS AND TIMERSLEADTOOLSOUTPUTSPublic website URLRoutes and QAfocusScreen profilesResponsive BrowserLabgpt-6-lunaBrowser UsePrepaid / usage-bas…Coverage reportReproduciblefindingsBUDGET RULE / Up to 4 profiles and 8 routes; $0.18 browser-task cap per profile, plus agent usage and applicable service or traffic charges.
  1. Inputs
    Public website URLRoutes and QA focusScreen profiles
  2. Lead agent
    Responsive Browser Labgpt-6-luna
  3. Tools
    Browser UseBrowser task budget up to $0.18 per profile; agent usage and applicable service or traffic charges are additional.
  4. Outputs
    Coverage reportReproducible findings
The diagram as text
  • Inputs: Public website URL, Routes and QA focus, Screen profiles
  • Lead: Responsive Browser Lab (gpt-6-luna) uses Browser Use
  • Tool: Browser Use - Browser task budget up to $0.18 per profile; agent usage and applicable service or traffic charges are additional. (built into FlyMy.AI)
  • Output: Coverage report (from Responsive Browser Lab)
  • Output: Reproducible findings (from Responsive Browser Lab)

Day one

from the reference project
  • 01Copy projectOpen the public project and copy it to your account.no template fee
  • 02Connect toolsBrowser Use is prepaid by FlyMy.AI. You do not need a Browser Use account. Calls use your FlyMy.AI balance.no provider key
  • 03Set the scopeChoose the public website, up to 8 routes, profiles or devices, QA focus and budget.before running
  • 04Review the reportReview completed checks, findings and any partial or unavailable coverage.usage-based

How it runs

templates/website-qa-responsive v1.1

Start after your inputs and budget are confirmed. Each profile gets a separate browser check. Actual viewport dimensions are included in the report.

The agent team

from the reference project

Responsive Browser LabQAlead

Check your website at phone, tablet and desktop sizes. Get a report of what broke, how to reproduce it and which checks actually ran.

Browser Use
Instruction excerpt

Cloud Chromium with a requested screen size for each profile. The report records the actual viewport, including any mismatch. This is screen-size simulation, not native Safari or physical-device testing. Stay within the selected routes and budget. Report only checks supported by returned evidence; mark incomplete coverage. Do not log in, submit forms, buy or send messages.

Budget: Up to 4 profiles and 8 routes; $0.18 browser-task cap per profile, plus agent usage and applicable service or traffic charges.

on demandgpt-6-luna

You will be asked

once, in one message
  • Which website?A public HTTPS website; pages behind login are outside the scope.https://example.com
  • Which routes?Choose up to 8 routes within the website./, /pricing, /contact
  • Which screen profiles?Up to 4 profiles; the report compares requested and observed dimensions.phone 390 x 844, tablet 768 x 1024
  • What should the report focus on?Choose the pages or interactions that matter for this check.menu, text fit, missing images
  • What budget should it use?Up to 4 profiles and 8 routes; $0.18 browser-task cap per profile, plus agent usage and applicable service or traffic charges.Confirm before the first run

Keys and passwords never go into the chat: you connect accounts on their own pages.

What it costs

Run limits checked on 2026-11-03

0%template markup or purchase feeUsage pricing →

Price of one run
ItemUnit pricePer runCost
Browser UseBrowser task cap: $0.18 / profileUp to 4 profilesBudget cap
FlyMy.AI agentModel usageActual work performedUsage-based
TemplateCopy the public projectOne copy$0
Final run costUsage-based

Up to 4 profiles and 8 routes. Browser task budget: $0.18 per profile, plus agent usage and any later provider traffic charge. Actual usage is reported; the budget is not a fixed price. No fixed-price result or device run is claimed.

What stays yours

the same for every template

Your connections stay yours

A copy never carries the author's keys or connections.

Nothing runs until you answer

Clone creates the agents and a setup chat; nothing bills before your reply.

A budget you set

Choose the budget before the first run. Review usage in your own project.

Versions

a copy keeps the version it was made from
  • v1.12026-11-03Public project with a checked copied-project run; reports requested and observed viewport dimensions and partial coverage.

Other ways to start

01 - Clone in FlyMy.AI

Open the reference project and press Clone; a setup chat asks once.

Clone this project
02 - Your Claude or Codex

Connect FlyMy.AI with skill.md and paste the request below.

03 - API and SDK

Agents MCP projects_copy with fleet:4ff45f01-a128-4bd5-9b0a-692faf5f4f20, or client.projects.copy.

FAQ

Is this ready to run?

Live browser runs and a copied-project run checked on November 3, 2026. The browser provider applied the requested widths but returned different viewport heights; the report marks this coverage as partial.

Does this test physical devices or Safari?

No. It runs cloud Chromium at requested screen sizes. The report records actual viewport dimensions and marks a mismatch as partial coverage. Use BrowserStack Device Lab for physical-device testing.

Do I need a Browser Use API key?

Browser Use is prepaid by FlyMy.AI. You do not need a Browser Use account. Calls use your FlyMy.AI balance.

Does it submit forms or make purchases?

No. It checks public pages and navigation within your chosen routes. Forms, logins, messages and purchases are outside its scope.

What does it cost?

Up to 4 profiles and 8 routes. Browser task budget: $0.18 per profile, plus agent usage and any later provider traffic charge. Actual usage is reported; the budget is not a fixed price.

Does copying enable a schedule?

No. Copying starts with your own inputs and accounts. No schedule is enabled by default.

Illustrative example, not a live result
Illustrative report structure
website: https://example.com
coverage: complete, partial or connection required
profile: requested and observed dimensions, or device / OS / browser
finding: page, severity, reproduction, expected and observed result
evidence: service-returned details
unverified: checks that did not run

Sources

Public reference project →Usage pricing →MCP connections →Browser Use in FlyMy.AI →

Content and connection guidance checked 2026-11-03. See linked documentation for current availability and prices.