How Claude Code handles this
You usually get here right after a build, when the site feels heavy or a PageSpeed report has just landed. You are already in the terminal, so you name the site and the goal. Claude Code matches the name with list_sites and calls optimize_site with dry_run on. That first call changes nothing. It returns the plan: which settings xSpeed would turn on and in what order, at the standard level unless you ask for safe or aggressive.
Read the plan, then tell Claude Code to apply it. The real pass measures the site, applies each setting one at a time, checks that the page still renders after every change, and undoes anything that breaks it. It can take up to two minutes per site. What comes back is three lists: what was applied, what was undone and why, and an unfixable list for problems caching cannot reach, such as page weight or images hotlinked from another domain. A site that is already tuned answers that everything is already on. That is a real answer, so do not ask for a retry.
The Hub then gives Claude Code a list of verify_urls and tells it to look at the site before it says the pass went well. The plugin checks the HTML in PHP and cannot run your JavaScript, so a page can arrive intact and still throw an error in the browser. In practice you ask Claude Code to report on those URLs, then open them yourself with the console visible. If the site has the Pro Critical CSS module, Claude Code can also call generate_critical_css afterwards and purge the cache so pages rebuild with it.
Set up Claude Code once
Already connected? Skip to the prompts. Alternatives and troubleshooting are on the Claude Code 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.
2Add xSpeed Hub to Claude Code
Run this once. --scope user makes the server available in every project; leave it off and it applies to the current project only, which is Claude Code's default.
claude mcp add --transport http --scope user xspeedhub https://app.xspeedcache.com/xspeed/mcp
3Sign in with /mcp
Start Claude Code, run /mcp, pick xspeedhub and finish the sign-in in your browser. You approve access on an xSpeed Hub page; there is no token to paste, and Claude Code keeps the credentials it receives and refreshes them.
/mcp
Full Claude Code 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. Claude Code asks before it runs an MCP tool unless a permission rule already allows it, or you work in auto mode, where a classifier reviews actions instead of you, or in bypassPermissions mode, which skips prompts. A rule such as mcp__xspeedhub__get_cache_status allows one tool, and mcp__xspeedhub__get_* allows every read whose name starts with get_. Keep purge_cache, update_settings, toggle_cache and the other write tools on the prompt, because the Hub itself runs a write as soon as your connection allows it.
What do I ask?
Three prompts written for Claude Code. More for this job are below.
Shop feels slow after the build. Use xSpeed Hub to preview what xSpeed would change, standard level, and wait for my go-ahead.
With xSpeed Hub, apply the plan you just showed me to shop, then list the verify URLs and what a broken page would look like.
Read back the unfixable list from that xSpeed Hub run and tell me which items I can fix in the theme code in this repo.
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 Claude Code
Claude Code permission rules work per tool, and the dry run and the real pass are the same tool. If you add a permission rule that allows mcp__xspeedhub__optimize_site so the preview stops prompting, the real pass stops prompting too. A rule such as mcp__xspeedhub__get_* trusts the reads that start with get_, such as get_score_history, and leaves optimize_site on the prompt. Keep that tool on the prompt and read the plan before you answer it. Auto mode, where a classifier reviews actions instead of you, and bypassPermissions mode, which asks nothing, skip the prompt for every tool. Run the preview with the default standard level first, and ask for aggressive only when you have a staging copy to try it on.
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 Claude Code
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
- Claude Code + xSpeed
- Every AI agent that works with xSpeed
From the blog