How Grok Bot handles this
The verify step is where a Bot earns its place in this job. You attach the xspeedhub plugin with @ and ask the Bot to raise the score on the portfolio site, preview first. It calls optimize_site with dry_run on and posts the plan in the chat: the settings xSpeed would turn on at the standard level, with nothing changed. Grok Bot offers Allow once, Always allow or Deny when an action needs approval, so the preview is also the first approval card you see.
You approve the real pass. It measures the site, applies each setting one at a time, checks the page after each, and undoes anything that breaks it, for up to about two minutes. The result names the verify_urls, and the Hub tells the agent to open them and check that each page renders and the console is clean. Grok Bot's cloud computer has a browser, so the Bot can load those pages itself and tell you what it saw: which pages render cleanly, and which one logs an error after script deferral. That turns a list of URLs into a first-pass check you can act on.
Treat the Bot's look as a first pass, not the last word. Its browser is one machine in a cloud, not your visitors' phones, so open one or two of the pages yourself before you call the run done. If the site has the Pro Critical CSS module, the Bot can generate critical CSS next and purge the cache so pages rebuild with it, each as its own approved step.
Set up Grok Bot once
Already connected? Skip to the prompts. Alternatives and troubleshooting are on the Grok Bot guide.
1Put your sites in xSpeed Hub
Sign in at app.xspeedcache.com with Google or email; the Hub is free and has no site cap. Then connect each WordPress site from its own dashboard: click Connect Hub in the xSpeed Cache top bar, then Connect via xSpeed Hub. Each site needs the free xSpeed Cache plugin.
2Ask your Bot to add xSpeed Hub
In a chat with your Bot, ask it to add a custom remote HTTPS MCP server with this URL. xAI says a plugin you add from your own chat is personal and account-wide, so every Bot on your account can use it. When the browser opens, approve access on the xSpeed Hub page.
Add a custom remote HTTPS MCP server called xspeedhub with the URL https://app.xspeedcache.com/xspeed/mcp and sign me in.
3Attach it and ask a first question
Type @ in a chat to attach the xspeedhub plugin to the task, then ask something that names xSpeed Hub. A list of your sites means the connection works.
Use @xspeedhub (xSpeed Hub) to list my sites and tell me which ones have page caching turned off.
Full Grok Bot setup, sign-in options and FAQ
Before you send a prompt that changes something
Reads change nothing on your sites, though contact_support emails xSpeed support. Writes run once your connection allows them, so your client's approval prompt and a read-only connection (the token's Read-only everywhere switch, or a Viewer sign-in) are the gates that matter. When an action needs approval, Grok Bot offers Allow once, Always allow or Deny. Always allow saves a rule, so the same kind of call no longer stops for you. Auto-review rules under Settings, General, Auto-review can force Ask first or allow matching actions automatically, and Ask first wins when both match. xSpeed Hub has no confirmation step of its own, so a Hub write tool you always allow runs as soon as your connection allows writes. Add Ask first rules for purge_cache, update_settings, toggle_cache, optimize_site and the other write tools. For read-only access, sign in as a Viewer member of the workspace.
What do I ask?
Three prompts written for Grok Bot. More for this job are below.
Use @xspeedhub (xSpeed Hub) to preview an optimization for portfolio at the standard level. Stop after the plan.
With xSpeed Hub, apply the plan to portfolio, then open each verify URL in your browser and tell me what the console shows.
Every Friday, use xSpeed Hub to read the stored PageSpeed history for each site and report any drop. Report only.
What happens, step by step
optimize_site is the Hub tool for "make my site faster". It measures the site, applies the recommended xSpeed settings one at a time, checks the page still renders after each change, undoes anything that breaks it, and reports what it applied, what it undid and what it could not fix. It reaches caching and asset delivery only. Page weight, images hosted on another domain and heavy video are outside it, and the report says so instead of claiming a win.
01
See where the site stands
The agent reads get_score_history for the last stored scores and list_modules for which modules exist on that site and what state they are in. Neither changes anything.
02
Preview with dry_run
optimize_site with dry_run: true returns the plan: each change and its tier, what would be skipped (already on, or needing a higher aggressiveness) and what it cannot fix. Nothing is applied. The tool description tells the agent to prefer this before the first real run on a site you have not optimized before.
03
Apply it
optimize_site without dry_run applies the plan. aggressiveness is safe (removals and server-side changes only), standard (the default) or aggressive, which includes settings known to break some themes and should be opted into deliberately. A run can take up to about 2 minutes per site.
04
Look at the site afterwards
When changes were applied, the result carries verify_urls and a note. The site checks its own HTML and reverts anything that breaks it, but it cannot run JavaScript, so verified: true does not prove the page works in a browser. The Hub tells the agent to open those URLs and check the page renders and the console is clean, or to tell you which URLs to check.
05
Reach for a number only if you named one
target_score (1 to 100, Pro sites only) turns one pass into repeated rounds toward that score, up to max_rounds, with 3 as the most per site. Each round is a real PageSpeed measurement and up to about 2 minutes. The result says why it stopped, and diminishing returns means what is left is outside what caching can reach.
06
Critical CSS on Pro sites
generate_critical_css generates above-the-fold CSS so the first screen can paint without waiting for the full stylesheets. It needs the Pro Critical CSS module on that site, and the site answers with an unknown-tool error without it. Pages are rebuilt with it on their next build, so the agent purges the cache afterwards.
Reference
| Main tool | optimize_site (write): measure, apply one setting at a time, verify, undo what breaks, re-measure |
|---|---|
| Preview | dry_run: true returns the plan and changes nothing |
| aggressiveness | safe, standard (default) or aggressive |
| Every site at once | site: "all" or a list of handles, one result per site, sites run one after another; the Hub's confirm-once instruction does not name optimize_site, so your client's prompt is the gate |
| Time | Up to about 2 minutes per site |
| target_score | 1 to 100; needs Pro on the site; without it the site runs one pass and says so |
| max_rounds | Up to 3 per site; only sent along with target_score; 12 rounds in total per call |
| Wide fan-out with a target | Each site gets fewer rounds, and the result carries a note saying so |
| Result fields | applied, skipped, reverted, unfixable, score, verified, rounds; verify_urls after a run that changed something |
| Already tuned site | Returns "everything is already on" plus what it cannot fix; that is an answer, not a failure |
| Critical CSS | generate_critical_css (write), Pro Critical CSS module required; purge_cache afterwards |
| Read-only connection | optimize_site and generate_critical_css are refused; dry_run is still a write call, so it is refused too. Applies to the connection token with Read-only everywhere on and to a Viewer sign-in, not to other OAuth sign-ins |
Rules worth keeping
- Run dry_run first. optimize_site changes live site settings as soon as your connection allows writes. The tool description tells the agent to preview first on a site that has not been optimized, but that is guidance, so your client's approval prompt and a read-only connection (the connection token with Read-only everywhere on, or a Viewer sign-in) are the real gates.
- Keep aggressive for a deliberate choice. It includes settings known to break some themes, and the agent should say so before using it.
- After a run that changed something, open the pages in verify_urls. The HTML checks cannot run JavaScript, so a page can pass them and still be broken in a browser. Do not call a run safe because verified is true.
- Relay the unfixable list. When a site is already tuned, the honest answer is that caching is done and the rest is page weight, hotlinked images or DOM size. The agent should not retry the tool or claim a gain it did not make.
- Only ask for target_score when you want the site driven to a number. Each round costs a real PageSpeed measurement, and a plain "make it faster" is one pass.
Good to know with Grok Bot
Choose Allow once on optimize_site, not Always allow. The dry run and the real pass are the same tool, so an Always allow saved while you approve the preview lets the real pass through with no card, and xSpeed Hub has no confirmation step of its own to catch it. Add an Ask first rule under Settings, General, Auto-review for optimize_site, generate_critical_css and purge_cache; Ask first wins when an automatic allow also matches. Keep routines to reads: a routine can watch get_score_history and report a drop, but a scheduled optimize_site runs with nobody to read the plan, and a routine's Test run does real work, calling connected tools for real. A Viewer sign-in refuses optimize_site entirely, dry run included.
More prompts for this job
They work in any client connected to xSpeed Hub.
Ask xSpeed Hub to preview what optimize_site would change on shop with a safe pass. Do not apply anything.
Use xSpeed Hub to optimize the blog site with the standard pass, then give me the pages to check by hand.
With xSpeed Hub, get docs to a mobile PageSpeed score of 90 if you can, and tell me why it stopped if it does not get there.
Use xSpeed Hub to show me what optimize_site would do on every site, as a dry run, and list which sites have the most left to change.
Use xSpeed Hub to generate critical CSS for shop, then purge the cache so the pages are rebuilt with it.
With xSpeed Hub, optimize shop, then compare the new PageSpeed score with the last stored one.
Using xSpeed Hub, what could optimize_site not fix on the shop site?
Frequently asked questions
Keep going
Raise the PageSpeed score with other agents
More with Grok Bot
Documentation
- How to generate Critical CSS
- Performance recommendations
- How to run a speed test
- Free vs Pro: what is included
- How to write prompts for xSpeed Hub
- Grok Bot + xSpeed
- Every AI agent that works with xSpeed
From the blog