How Gemini CLI handles this
In Gemini CLI you type the goal the way you would say it to a colleague: the docs site is slow on mobile, preview what xSpeed would change. Gemini calls list_sites to resolve the name and then optimize_site with dry_run on, and the CLI asks you to confirm the tool call before it runs. You get a plan, in order, with the level it picked and nothing changed on the site.
Tell it to apply the plan when you are ready. The pass runs each setting one at a time, checks the page after each change, and undoes anything that breaks it, for up to two minutes per site. If you want a number, name it and Gemini can send target_score and up to three rounds. That requires the Pro plugin on the site, and each round is a real measurement, so decide whether the number is worth the wait. xSpeed stops early on its own when rounds stop helping and reports why. Diminishing returns usually means what is left is outside what caching can reach.
Gemini then reports applied, undone and unfixable. If it says everything is already on, believe it and look at the unfixable list instead of rerunning. The Hub also gives Gemini a list of verify_urls and tells it to look at the pages before saying the pass went well. The plugin cannot run JavaScript, so a page that passes its HTML checks may still log an error in the browser. Open the listed pages yourself with the console open, then tell Gemini what you saw.
Set up Gemini CLI once
Already connected? Skip to the prompts. Alternatives and troubleshooting are on the Gemini CLI 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 Gemini CLI
Run this once. --scope user writes the server to ~/.gemini/settings.json so it works in every project; without it Gemini CLI saves to the project's .gemini/settings.json, which is the default.
gemini mcp add --scope user --transport http xspeedhub https://app.xspeedcache.com/xspeed/mcp
3Authenticate with /mcp auth
Start gemini and run /mcp auth xspeedhub. A browser page opens where you sign in to xSpeed Hub and approve access, and Gemini CLI receives the redirect on a local port. There is no token to paste, and the client keeps the credentials it receives. Run /mcp afterwards to check that xspeedhub shows as connected and lists its tools.
/mcp auth xspeedhub
Full Gemini CLI 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. Gemini CLI shows a confirmation for an MCP tool call unless the server entry sets trust to true or you start Gemini CLI with --approval-mode=yolo (or --yolo), which approves every tool call. You can proceed once, always allow that tool, always allow the whole xspeedhub server, or cancel; the last two choices stop later prompts for those tools. Policy rules in ~/.gemini/policies can allow, deny or ask for a named tool by server and tool name. The Hub has no confirmation step of its own, so a trusted server, YOLO mode or an allow rule lets a write run as soon as your connection allows writes.
What do I ask?
Three prompts written for Gemini CLI. More for this job are below.
Use xSpeed Hub to preview an optimization for docs at the standard level and wait for my confirmation.
Apply it through xSpeed Hub with a target score of 90 and at most two rounds, and tell me why it stopped when it finishes.
List the verify URLs from the last xSpeed Hub run so I can open them.
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 Gemini CLI
Gemini CLI asks before a tool call unless you have marked the server as trusted or started it with --approval-mode=yolo (or --yolo), which approves every tool call. A trust setting on the xSpeed Hub entry applies to every tool from that server, so optimize_site, generate_critical_css and purge_cache would all run without a prompt, and the Hub itself runs a write as soon as your connection allows it. Choosing always allow for optimize_site, or for the whole xspeedhub server, in a confirmation does the same for later calls, because the dry run and the real pass are the same tool. Choose proceed once while you tune a live site, so each call gets its own confirmation.
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 Gemini CLI
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
- Gemini CLI + xSpeed
- Every AI agent that works with xSpeed
From the blog