WebForAgents
HomeAll sitesOpen a fast laneBlog
English▾
WebForAgents
WebForAgents
WebForAgents

Open an AI agent fast lane on your website and stay a step ahead of your competitors in the age of agents.

Product

Free scanOpen a fast laneAll sites

Resources

BlogLive test reportOur scanner

Legal

Terms of ServicePrivacy PolicyLegalContactCookie settings
© 2026 Funovate Technology LLC. All rights reserved.
WebForAgents

Open an AI agent fast lane on your website and stay a step ahead of your competitors in the age of agents.

Product
Free scanOpen a fast laneAll sites
Resources
BlogLive test reportOur scanner
Legal
TermsPrivacyLegalContactCookie settings
© 2026 Funovate Technology LLC. All rights reserved.
WebForAgents
Notifications
No notifications yet
Home›vue.lab.webforagents.dev — Agent Readiness Report
Home›vue.lab.webforagents.dev — Agent Readiness Report

vue.lab.webforagents.dev

Visit vue.lab.webforagents.dev↗Claimed by the site owner

  • SaaS
  • Pricing plans
  • Docs
  • llms.txt
C72 / 100
Agent Readiness Score
  • Browser path· 70% of the score78 C
  • Fetch path· 30% of the score60 D
Scan screenshot

homepagevue.lab.webforagents.dev/

1 / 8
Report contents
    Technical standards

    Checking page code against public standards: can agents recognise and read it?

    Browser agents100

    We check the code of the task pages against public standards (WCAG, axe, Lighthouse): do controls have names, do forms have labels, is anything in the way. We only open and read pages; we never click or type.

    • B1Reachable in a browserNot scoredPass

      What we found

      • The pages load in a browser.

      Why it matters

      Browser agents have to load the page before they can do anything with it.

      Check it yourself

      Open https://vue.lab.webforagents.dev/ in a private browser window.
    • B2Interactive elements identifiableCaps the scoreWeight 15Pass

      BlocksAccessibility-tree agentsDOM agents

      What we found

      • 100% of 97 interactive elements can be identified by an agent.

      Why it matters

      Browser agents build their picture of a page from the accessibility tree. A control without a name, or a clickable element that is not a control, is invisible or ambiguous to them.

      If this check fails, this part of the score can be at most 69 (grade D).

      Check it yourself

      npx @axe-core/cli https://vue.lab.webforagents.dev/ --rules button-name,link-name,label
    • B4Key facts after renderingWeight 12Pass

      BlocksAccessibility-tree agentsDOM agents

      What we found

      • "Understand what the site does": the information is visible on https://vue.lab.webforagents.dev/.

      Why it matters

      Once an agent reaches a task's page, the information it came for (a price, the main text, contact details, what the site does) has to be visible text on the page. If it sits only in collapsed content, hidden data or an image, the agent cannot read it or needs extra steps.

      Check it yourself

      Open the task's page (for example the product or contact page of https://vue.lab.webforagents.dev/) in a browser without expanding anything, and check that the information is shown on the page.
    • B10Real linksWeight 10Pass

      BlocksDOM agentsAccessibility-tree agents

      What we found

      • Every link on the pages has a real address.

      Why it matters

      Agents that read the DOM follow a link by its address. A div or span that navigates with a script has no address, so they have to click it, and some tools that read the accessibility tree do not list it at all. In our runs this cost one to five extra steps.

      Check it yourself

      curl -s https://vue.lab.webforagents.dev/ | grep -Eo '<a[^>]*href="(#|javascript:)[^"]*"|onclick="[^"]*location[^"]*"' | head
    • B6Forms recognisableWeight 10Pass

      BlocksAccessibility-tree agentsScreenshot agents

      What we found

      • Forms on 8 pages can be recognised.

      Why it matters

      To sign up, get in touch or book, an agent first has to recognise what each field is and where the submit button is. We never fill or submit forms; we only check whether they can be recognised.

      Check it yourself

      Open an action task's entry page (sign-up, for example) and check in the browser's accessibility panel that every input has a name.
    • B3Not obstructedWeight 8Pass

      BlocksScreenshot agentsAccessibility-tree agents

      What we found

      • No page is covered by an overlay after loading.

      Why it matters

      Screenshot agents cannot see what an overlay covers, and agents that read the accessibility tree find the elements behind it but cannot click them. Gemini's and Microsoft's documentation both name unexpected pop-ups as a cause of errors.

      Check it yourself

      npx lighthouse https://vue.lab.webforagents.dev/ --only-audits=cumulative-layout-shift
    • B11Content in the page's own interfaceCaps the scoreWeight 6Pass

      BlocksAccessibility-tree agentsDOM agents

      What we found

      • Content and controls are in the pages' own HTML.

      Why it matters

      Text and controls drawn on a canvas, or a form inside a page embedded from another site, do not appear in the page's accessibility tree. Claude's browser tool documentation names both as cases where it gets no elements and falls back to screenshots; an agent that reads only the tree gets nothing.

      If this check fails, this part of the score can be at most 69 (grade D).

      Check it yourself

      Open https://vue.lab.webforagents.dev/ with the browser's accessibility panel and check that the content appears in the tree.
    • B12States statedWeight 5Pass

      BlocksAccessibility-tree agents

      What we found

      • Menus and controls state whether they are open, selected or checked.

      Why it matters

      Agents that read the accessibility tree tell whether a menu is open, a tab selected or a box checked from its state. Without it they click again or click the wrong thing.

      Check it yourself

      npx @axe-core/cli https://vue.lab.webforagents.dev/ --rules aria-required-attr
    • B13No native dialogsWeight 4Pass

      BlocksAccessibility-tree agentsScreenshot agents

      What we found

      • No page opens a native dialog while loading.

      Why it matters

      alert, confirm and prompt dialogs stop the page until someone answers. Claude in Chrome's documentation says they block it until a person closes them, and Amazon's Nova Act cannot handle them either.

      Check it yourself

      Open https://vue.lab.webforagents.dev/ with the console open and watch for dialogs while it loads.
    • B14Layout stableWeight 5Pass

      BlocksScreenshot agentsAccessibility-tree agents

      What we found

      • Layouts stay stable (largest layout shift 0).

      Why it matters

      Screenshot agents click by position, so a shift moves the target away from the click; agents that read the accessibility tree find their element references go stale. Chrome's Lighthouse lists layout stability among its agentic browsing checks.

      Check it yourself

      npx lighthouse https://vue.lab.webforagents.dev/ --only-audits=cumulative-layout-shift
    • B15No new tabsWeight 4Pass

      BlocksScreenshot agentsAccessibility-tree agentsDOM agents

      What we found

      • Links within the site open in the same tab.

      Why it matters

      A link that opens a new tab makes every kind of agent find and switch to that tab. In our runs Codex took one more step each time.

      Check it yourself

      curl -s https://vue.lab.webforagents.dev/ | grep -o 'target="_blank"' | wc -l
    • B16Pages readable in one goWeight 4Pass

      BlocksAccessibility-tree agents

      What we found

      • Every page can be read in one go (largest snapshot 2,234 tokens).

      Why it matters

      Agents read a page's snapshot as one tool result, and some cut it off: Codex at 10,000 tokens, Claude Code at 25,000 (about 21,000 in our count). Claude in Chrome reads 50,000 characters by default but can ask for more, so it is not counted.

      Check it yourself

      Open https://vue.lab.webforagents.dev/ and see how long its accessibility snapshot is.
    • B17No hover-only contentWeight 3Not applicable

      BlocksScreenshot agentsAccessibility-tree agents

      What we found

      • No hidden navigation menus.

      Why it matters

      Screenshot agents only see a menu after hovering over it, and a menu hidden with CSS is not in the accessibility tree. A menu that opens with a button can be found and opened by every kind of agent.

      How to fix

      Open menus with a <button aria-expanded> that also works on click, and keep important links visible.

      Check it yourself

      Check whether the navigation menus on https://vue.lab.webforagents.dev/ open with a click or the keyboard.
    • B7Targets easy to hitWeight 3Pass

      BlocksScreenshot agents

      What we found

      • Text contrast (shown, not scored): 100% of 191 text elements pass.

      Why it matters

      Screenshot agents click by position, so small or crowded targets get missed; Claude's computer use documentation notes that small text and icons need zooming in. Text contrast is shown but not scored.

      Check it yourself

      Run Lighthouse's accessibility check in Chrome DevTools and look at target size and contrast.
    • B18Direct addressesWeight 4Not applicable

      BlocksDOM agentsScreenshot agentsAccessibility-tree agents

      What we found

      • No "load more" buttons.

      Why it matters

      Agents move between pages by address, and Gemini's and OpenAI's agents can type an address directly. Items loaded only by a "load more" button have no address to come back to.

      How to fix

      Add page links (or rel="next") alongside "load more" and infinite scroll, and give tabs and filters their own URLs.

      Check it yourself

      Check whether later items on https://vue.lab.webforagents.dev/ can be reached through a page link.
    • B19Same name, same placeWeight 3Pass

      BlocksAccessibility-tree agents

      What we found

      • Link names are distinct: each name goes to one place.

      Why it matters

      An agent reading the accessibility tree sees a list of link names. When several "Learn more" links go to different places, it cannot tell which one to follow and may pick the wrong one.

      Check it yourself

      Look for links on https://vue.lab.webforagents.dev/ with the same name that point to different addresses.
    • B20Visible text matches the nameWeight 2Pass

      BlocksScreenshot agentsAccessibility-tree agents

      What we found

      • Every control's visible text is part of its name.

      Why it matters

      Many agents find a button on a screenshot and then look it up by name in the accessibility tree. If the button says "Buy now" but its name is something else, the two do not match.

      Check it yourself

      Check the buttons and links with aria-label on https://vue.lab.webforagents.dev/: does the name contain the text they show?
    • B5Page structureWeight 2Pass

      BlocksAccessibility-tree agents

      Why it matters

      Agents that read the accessibility tree find the main content through landmarks and headings, and read tables through their headers.

      Check it yourself

      npx @axe-core/cli https://vue.lab.webforagents.dev/ --rules bypass,landmark-one-main,page-has-heading-one,document-title,heading-order,th-has-data-cells
    • B8CAPTCHANot scoredNot applicable

      What we found

      • No action-task entry page was rendered.

      Why it matters

      Browser agents usually stop or hand control back to the user at a CAPTCHA. A CAPTCHA is a site's normal protection, so this is shown and never penalised.

      How to fix

      Nothing to fix. If you want agents to get through, consider showing the CAPTCHA only for suspicious traffic.

      Check it yourself

      Open an action task's entry page and look for a reCAPTCHA, hCaptcha or Turnstile widget.
    • B9Load speedNot scoredMeasured

      What we found

      • These are load times we measured on our own server. Images, media and fonts are not loaded and our network location differs from a real agent's, so the numbers are for reference only and not scored.
      • home (https://vue.lab.webforagents.dev/): DOMContentLoaded 980 ms, load event 995 ms, network quiet 1,164 ms.
      • page declared by the site (https://vue.lab.webforagents.dev/tools/resize?img=img&width=1280&format=webp): DOMContentLoaded 1,021 ms, load event 1,026 ms, network quiet 1,185 ms.
      • page declared by the site (https://vue.lab.webforagents.dev/tools/compress?img=img&kb=500): DOMContentLoaded 967 ms, load event 980 ms, network quiet 1,145 ms.
      • page declared by the site (https://vue.lab.webforagents.dev/pricing): DOMContentLoaded 983 ms, load event 992 ms, network quiet 1,155 ms.
      • page declared by the site (https://vue.lab.webforagents.dev/docs/getting-started): DOMContentLoaded 996 ms, load event 998 ms, network quiet 1,164 ms.
      • page declared by the site (https://vue.lab.webforagents.dev/docs/formats): DOMContentLoaded 967 ms, load event 969 ms, network quiet 1,136 ms.
      • page declared by the site (https://vue.lab.webforagents.dev/docs/api): DOMContentLoaded 979 ms, load event 986 ms, network quiet 1,148 ms.
      • page on the way (https://webforagents.org/site/vue.lab.webforagents.dev/agent-fast-lane): DOMContentLoaded 271 ms, load event 320 ms, network quiet 510 ms.

      Why it matters

      A browser agent waits for each page to load before it can read or click. The slower the page, the more time the agent spends, and past the tool's wait limit the step simply fails. This item is shown, not scored, for now.

      How to fix

      Cut the scripts and requests the first view waits for: defer non-essential third-party scripts, compress and cache static files, and let the main content render first.

      Check it yourself

      Open https://vue.lab.webforagents.dev/ in the Performance panel of Chrome DevTools, or run Lighthouse, and see how long the page takes to load.

    Fetch agents56

    Checks of the raw HTML against fetch agents' documentation, code and measured behaviour: content without JavaScript, search crawlers allowed, key facts in the visible text, pages not too large. We only read; we run no scripts.

    • F1ReachableNot scoredPass

      What we found

      • The homepage and the key pages we fetched returned 200 with HTML.

      Why it matters

      A blocked or challenged response leaves a fetch agent with nothing. This has the strongest measured effect on agent success.

      Check it yourself

      curl -sI -A 'Claude-User' https://vue.lab.webforagents.dev/

      Evidence

      • 200https://vue.lab.webforagents.dev/homepage HTML
    • F2Content without JavaScriptCaps the scoreWeight 30Partial

      BlocksWhole-page fetchersWindow readers

      What we found

      • Only 69% of the text shown in a browser is in the raw HTML; the rest needs JavaScript.

      Why it matters

      The fetch tools of Claude Code, Codex and Gemini CLI, and the major assistants' fetchers, do not run JavaScript.

      If this check fails, this part of the score can be at most 69 (grade D).

      How to fix

      Server-render or pre-render your public pages so the HTML response already contains the text.

      Check it yourself

      curl -s https://vue.lab.webforagents.dev/ | sed -e 's/<[^>]*>//g' | wc -w

      Evidence

      • 200https://vue.lab.webforagents.dev/homepage HTML
    • F4Reading cost for fetch agentsWeight 10Pass

      BlocksWhole-page fetchersWindow readersIndex readers

      What we found

      • {url}: within every truncation limit (about {tokens} tokens, shown only).

      Why it matters

      Every token an agent reads costs its user money and time. Fetch agents convert your HTML to markdown and read all of it; tools also cut pages longer than 1 MiB of HTML or 100,000 characters.

      Check it yourself

      curl -s https://vue.lab.webforagents.dev/ | wc -c

      Evidence

      • 200https://vue.lab.webforagents.dev/homepage HTML
    • F5Markdown availableNot scoredFail

      What we found

      • https://vue.lab.webforagents.dev/ has no markdown version: a request for text/markdown returned HTML and no alternate is advertised.

      Why it matters

      Markdown cuts the tokens an agent spends on a page. Claude Code, Cursor and OpenCode ask for it.

      How to fix

      Return text/markdown when the request's Accept header prefers it, and send Vary: Accept. Or advertise a .md version with <link rel="alternate" type="text/markdown">.

      Check it yourself

      curl -sI -H 'Accept: text/markdown, text/html, */*' https://vue.lab.webforagents.dev/

      Evidence

      • 200https://vue.lab.webforagents.dev/homepage as markdown
    • F7HTTP semanticsWeight 10Partial

      BlocksWhole-page fetchers

      What we found

      • A missing page (https://vue.lab.webforagents.dev/wfa-probe-j0k9fjts8d6d4oqa) returned HTTP 200 instead of 404, so agents may treat error pages as content.

      Why it matters

      Agents rely on status codes and redirects. A missing page that answers 200 looks like content.

      How to fix

      Return 404 for missing pages, keep redirects short and on your own domain, and declare charset in Content-Type.

      Check it yourself

      curl -sI https://vue.lab.webforagents.dev/does-not-exist

      Evidence

      • 200https://vue.lab.webforagents.dev/wfa-probe-j0k9fjts8d6d4oqarandom missing page
      • 200https://vue.lab.webforagents.dev/homepage HTML
    • F8robots.txt and user-triggered agentsWeight 15Pass

      BlocksClaude appsDuckDuckGo

      What we found

      • No robots.txt: all agents are allowed.
      • robots.txt allows the user-triggered agents that honour it.

      Why it matters

      robots.txt is the one access standard every major crawler honours; Claude-User honours it even for fetches a user asks for.

      Check it yourself

      curl -s https://vue.lab.webforagents.dev/robots.txt

      Evidence

      • 200https://vue.lab.webforagents.dev/robots.txtrobots.txt
    • F10Allowed into search indexesWeight 15Fail

      BlocksIndex readers

      What we found

      • https://vue.lab.webforagents.dev/: search crawlers disallowed in robots.txt: ; robots directives on the page: noindex,nofollow,noarchive.

      Why it matters

      ChatGPT, Perplexity, Copilot and Google's AI Overviews answer most questions from their own index instead of fetching the page. If robots.txt keeps their search crawlers out, or the page says noindex or noarchive, these agents cannot read the site. Keeping them out is your choice; the consequence is that they cannot read you.

      How to fix

      Allow OAI-SearchBot, PerplexityBot, Bingbot, Googlebot and Claude-SearchBot in robots.txt, and remove noindex, noarchive, nosnippet and nocache from key pages.

      Check it yourself

      curl -s https://vue.lab.webforagents.dev/robots.txt; curl -sI https://vue.lab.webforagents.dev/ | grep -i x-robots-tag; curl -s https://vue.lab.webforagents.dev/ | grep -io '<meta[^>]*name="\(robots\|googlebot\|bingbot\)"[^>]*>'
    • F11Key facts not only in the head or structured dataWeight 10Not applicable

      BlocksWhole-page fetchersWindow readers

      What we found

      • No page has JSON-LD structured data, so this check does not apply.

      Why it matters

      When fetch agents convert a page to text they drop the head and every script, JSON-LD included. A price, phone number or address written only in structured data never reaches them.

      How to fix

      Keep the structured data, and also write prices, phone numbers, addresses and product names in the visible text.

      Check it yourself

      curl -s https://vue.lab.webforagents.dev/ | grep -o '<script type="application/ld+json">[^<]*' | head
    • F12Not too many links before the main contentWeight 10Not applicable

      BlocksWindow readers

      What we found

      • No page has an H1 or main element, so this check does not apply.

      Why it matters

      Agents that read a page in windows, such as ChatGPT, see a few thousand characters at a time, navigation first. With fewer than 20 links the content fills about 78% of a window; with 60 or more, about a third. The bands come from a third-party measurement and are to be retested.

      How to fix

      Move a large menu's links to an "all pages" page, or put the main content before the navigation in the HTML; keep only the most used entries in the header.

      Check it yourself

      curl -s https://vue.lab.webforagents.dev/ | sed -n '1,/<h1\|<main/p' | grep -o '<a [^>]*href=' | wc -l

    robots.txt and AI agents

    Whether each agent is allowed to fetch your homepage and pricing page. Only user-triggered agents that honour robots.txt are scored.

    • F8robots.txt and user-triggered agentsWeight 15Pass

      BlocksClaude appsDuckDuckGo

      What we found

      • No robots.txt: all agents are allowed.
      • robots.txt allows the user-triggered agents that honour it.

      Why it matters

      robots.txt is the one access standard every major crawler honours; Claude-User honours it even for fetches a user asks for.

      Check it yourself

      curl -s https://vue.lab.webforagents.dev/robots.txt

      Evidence

      • 200https://vue.lab.webforagents.dev/robots.txtrobots.txt
    AgentVendorHomepagePricing page
    User-triggered agents
    Claude-UserScoredAnthropicAllowed—
    ChatGPT-UserOpenAIAllowed—
    Perplexity-UserPerplexityAllowed—
    Google-AgentGoogleAllowed—
    Meta-ExternalFetcherMetaAllowed—
    Amzn-UserAmazonAllowed—
    MistralAI-UserMistralAllowed—
    DuckAssistBotScoredDuckDuckGoAllowed—
    Search crawlers
    Claude-SearchBotAnthropicAllowed—
    OAI-SearchBotOpenAIAllowed—
    PerplexityBotPerplexityAllowed—
    GooglebotGoogleAllowed—
    BingbotMicrosoftAllowed—
    ApplebotAppleAllowed—
    Amzn-SearchBotAmazonAllowed—
    Meta-WebIndexerMetaAllowed—
    MistralAI-IndexMistralAllowed—
    Training crawlers
    ClaudeBotAnthropicAllowed—
    GPTBotOpenAIAllowed—
    Google-ExtendedGoogleAllowed—
    Applebot-ExtendedAppleAllowed—
    Meta-ExternalAgentMetaAllowed—
    AmazonbotAmazonAllowed—
    CCBotCommon CrawlAllowed—
    BytespiderByteDanceAllowed—

    Declared

    Files and metadata a site can publish for agents. Shown for reference; they don't affect the score.

    • A2A agent cardAbsentNo A2A agent card.
    • Agent Skills indexAbsentNo Agent Skills index.
    • agents.jsonAbsentNo /.well-known/agents.json.
    • AI catalogAbsentNo AI catalog.
    • API catalog (RFC 9727)AbsentNo API catalog (RFC 9727).
    • Agent Resource DiscoveryAbsentNo Agent Resource Discovery file.
    • Content usage preferencesAbsentNo Content Signals or AIPREF usage preferences.
    • JSON-LD structured dataAbsentNo JSON-LD structured data.
    • llms.txtAbsentNo llms.txt.
    • MCP server cardAbsentNo MCP server card at a well-known path (current discovery goes through the AI catalog).
    • NLWebAbsentNo NLWeb endpoint found. NLWeb has no discovery file, so it is found only when the site links to it.
    • OAuth / OpenID metadataAbsentNo OAuth or OpenID authorization server metadata.
    • OAuth protected resource metadata (RFC 9728)AbsentNo OAuth protected resource metadata (RFC 9728).
    • SitemapAbsentNo sitemap.xml.
    • WebMCPAbsentNo WebMCP tools.
    Readiness rules R5.1.0
    Scanned Nov 21, 2026, 2:33 PM
    Start address
    https://vue.lab.webforagents.dev/ · 18 requests to the site
    About this scan
    Engine 9ea438697c132fd8d724a45a9ed43110781cefd0 · Converter html-to-markdown v2.5.2 · Tokenizer o200k_base · Prices P2026-11-01
    About this scan
    Browser 153.0.8010.52 · axe-core 4.14.0

    Simulated tasks

    A simulated agent starts on the homepage and does common tasks: how many steps, how many tokens it spends

    Browser 63 pts(Steps 50 · Tokens 100) | Fetch 63 pts(Steps 50 · Tokens 100)

    How it’s scored
    BrowserFetch
    StepsClicks + actions + extra steps for the worst-placed kind of agent (closing a pop-up, opening a menu, scrolling, switching to a new tab…)Clicks + extra steps for the worst-placed agent (reading on, refetching after a cross-host redirect). Raw HTML links only
    Step scoreFirst, the fewest steps the task needs: 1 click to the target page plus 1 action per parameter to fill in (a read-only task 1, a search 2, a booking 3). As many steps as the minimum scores 100; each extra step takes off 25; 4 or more extra steps score 0.
    Token scoreThe heaviest page on the route, and whether the agents listed below can read it in one go: all 100, half 50, none 0
    How much each agent reads at onceCodex CLI: at most 10,000 tokens at onceClaude Code: at most 21,000 tokens at onceReads the page's accessibility snapshot; past the limit it can't get everything at once and has to read in parts or look another way, costing extra steps and tokensClaude Code: at most 100,000 characters at onceCodex CLI: at most 10,000 tokens at onceReads the page converted to text; past the limit it can't get everything at once and has to read on, costing extra steps and tokens
    WeightSteps 75% + tokens 25%, together 60% of the browser scoreSteps 75% + tokens 25%, together 60% of the fetch score

    Both scores are the average over the tasks.

    BrowserFetch
    TaskStepsTokensStepsTokens
    Task 1Prepare image resizeDeclared by the site · not scoredTarget page/tools/resize?img=img&width=1280&format=webp1 step1 click(s) · Not scored—Not reachedNo link in the raw HTML leads here; it appears only after scripts run · Not scored—
    See how
    Browser
    1. 1Home /1,039 tokens
    2. 2/tools/resize902 tokens
    Fetch

    —

    Task 2Prepare image compressionDeclared by the site · not scoredTarget page/tools/compress?img=img&kb=5001 step1 click(s) · Not scored—Not reachedNo link in the raw HTML leads here; it appears only after scripts run · Not scored—
    See how
    Browser
    1. 1Home /1,039 tokens
    2. 2/tools/compress835 tokens
    Fetch

    —

    Task 3View pricingDeclared by the site · not scoredTarget page/pricing1 step1 click(s) · Not scored—Not reachedNo link in the raw HTML leads here; it appears only after scripts run · Not scored—
    See how
    Browser
    1. 1Home /1,039 tokens
    2. 2/pricing829 tokens
    Fetch

    —

    Task 4Read getting startedDeclared by the site · not scoredTarget page/docs/getting-started1 step1 click(s) · Not scored—Not reachedNo link in the raw HTML leads here; it appears only after scripts run · Not scored—
    See how
    Browser
    1. 1Home /1,039 tokens
    2. 2/docs/getting-started961 tokens
    Fetch

    —

    Task 5Read image format documentationDeclared by the site · not scoredTarget page/docs/formats3 steps2 click(s) · new tab 1 · Not scored—Not reachedNo link in the raw HTML leads here; it appears only after scripts run · Not scored—
    See how
    Browser
    1. 1Home /1,039 tokens
    2. 2webforagents.org/site/vue.lab.webforagents.dev/agent-fast-lane2,234 tokens
    3. 3/docs/formats840 tokens
    4. +Switch to the new tab: +1Screenshot agentsAccessibility-tree agentsDOM agents
    Fetch

    —

    Task 6Read URL parameter documentationDeclared by the site · not scoredTarget page/docs/api3 steps2 click(s) · new tab 1 · Not scored—Not reachedNo link in the raw HTML leads here; it appears only after scripts run · Not scored—
    See how
    Browser
    1. 1Home /1,039 tokens
    2. 2webforagents.org/site/vue.lab.webforagents.dev/agent-fast-lane2,234 tokens
    3. 3/docs/api915 tokens
    4. +Switch to the new tab: +1Screenshot agentsAccessibility-tree agentsDOM agents
    Fetch

    —

    Task 7Check pricing plansNot detected this scan · not scoredentry not foundNot detected this scanNot scored—Not detected this scanNot reachable by following links in the raw HTML · Not scored—
    See how

    Chosen because: Pricing plans, SaaS

    Task 8Look something up in docsNot detected this scan · not scoredentry not foundNot detected this scanNot scored—Not detected this scanNot reachable by following links in the raw HTML · Not scored—
    See how

    Chosen because: Docs

    Task 9Find contact detailsentry not foundNot reached0 pts—Not reachedNot reachable by following links in the raw HTML · 0 pts—
    Task 10Understand what the site doesTarget page/0 steps100 pts1,039 tokens100 pts0 steps100 pts300 tokens100 pts
    See how
    Browser
    1. 1Home /1,039 tokens
    2. Heaviest page 1,039 tokens
    Fetch
    1. worst page 300 tokens

    Costs are estimates: tokens are counted with the o200k tokenizer and priced at Claude Opus 5.5's input rate.

    Tokens on each page
    1. Homepagevue.lab.webforagents.dev/
      Browser agent1,040 tokens 1.2× baseline (876) · $0.0042 per read
      • Header 17%
      • Main content 27%
      • Sidebar 47%
      • Footer 9%
      Heaviest blocks
      1. List (in “Agent Fast Lane”)165 tokens

    Agent Fast Lane

    Open. WebForAgents checks the notes on the live site every week. Last checked: Nov 21, 2026, 2:38 PM.

    Full guide for agents · 6 shortcuts→

    For AI agents

    Tessel provides product image resize and compression forms. A browser is required; there is no public API. Processing currently shows a sign-in prompt.

    • /tools/resize?img={img}&width={width}&format={format} pre-fills resize; width is 640, 1280, or 1920 and format is jpg, webp, or png.

    • /tools/compress?img={img}&kb={kb} pre-fills compression; kb is 50–5000.

    • On either tool, #status[data-state=ready] indicates a filled form; submitting shows a sign-in prompt. Hand sign-in back to the user.

    Fast Lane notes by the Tessel team. WebForAgents checks the links and page elements, not how the product works.