# Raise a WordPress site's PageSpeed score with Grok Build

> Raising a WordPress PageSpeed score with Grok Build means asking it in your terminal to preview and then apply an xSpeed optimization pass through xSpeed Hub, and to check the pages it lists.

Page: https://xspeedcache.com/agent/grok-build/optimize-site/
Last updated: October 2026

You are in a terminal with Grok Build, and the site you care about has a slow score. You name the site and the goal, and Grok calls list_sites to resolve the handle, then optimize_site with dry_run on. That first call returns the plan, which settings xSpeed would turn on and at which level, and it changes nothing on the site. Start at standard. The safe level keeps to removals and server-side settings, and aggressive includes settings known to break some themes, so move up only on purpose.

When you tell Grok to apply it, the real pass runs. xSpeed measures the site, applies each setting one at a time, checks that the page still renders after each change, and undoes anything that breaks it. Give it up to two minutes per site. The reply lists applied, undone with the reason, and unfixable. If the unfixable list is long, the site has weight caching cannot remove, and the right move is to fix those items rather than run the pass again. A site that is already tuned answers that everything is already on.

The Hub then gives Grok a list of verify_urls and tells it to look at the pages before saying the pass worked. The plugin checks HTML in PHP and cannot run your scripts, so open those pages in a browser with the console visible and tell Grok what you see. If the site has the Pro Critical CSS module, Grok can also generate critical CSS and purge afterwards, each as its own approved step.

## Set up Grok Build once

### 1. Put 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.

### 2. Add xSpeed Hub with grok mcp add

Run this once. Add --scope project to write the server to .grok/config.toml in the current directory instead of your user config, which is only sensible if the repo never holds a token. Grok Build handles the OAuth flow for a remote server on its own.

```bash
grok mcp add --transport http xspeedhub https://app.xspeedcache.com/xspeed/mcp
```

### 3. Sign in from the TUI

Start grok and open /mcps. Select xspeedhub and press i to authenticate, or just use a Hub tool and let the browser flow start on first use. Sign in to xSpeed Hub and approve access. There is no token to paste; Grok Build stores the credentials it receives in ~/.grok/mcp_credentials.json. If the connection fails, run grok mcp doctor xspeedhub.

```
/mcps
```

Full setup: https://xspeedcache.com/agent/grok-build/

### 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. Grok Build starts in Ask mode, which prompts for anything a rule has not already allowed, so a Hub write tool prompts until you say otherwise. You can allow the reads with a rule such as MCPTool(xspeedhub__get_*) in the permission section of your config, and leave the writes unmatched. Evaluation runs deny, then ask, then allow. Two other modes remove the prompt: Always-approve, from /always-approve, Ctrl+O or --always-approve, approves tool calls unless a deny rule or a hook stops them, and Auto lets a classifier approve tools it judges safe. If a Hub write must never run unprompted, add a deny rule. The Hub itself has no confirmation step.

## Prompts

- Using xSpeed Hub, preview an optimization for the forum site at the standard level, and stop after the plan.
- Apply it to forum with xSpeed Hub, and if anything is undone, explain what broke before suggesting more changes.
- Do not try aggressive. Ask xSpeed Hub what is left on the unfixable list and tell me what I would fix by hand.

## Example session

```
You: The forum site scores low on mobile. Preview an optimization with xSpeed Hub, standard level.
  → list_sites [read-only]: 4 sites; forum is forum.example.com
  → optimize_site(site: forum, aggressiveness: standard, dry_run: true) [dry run]: plan: 4 settings to apply (CSS minify, defer JS, lazy-load images, compression), nothing changed
Agent: The plan is CSS minify, script deferral, lazy-loading and compression. Nothing has changed. Apply it to forum?
You: Yes, apply it.
  → optimize_site(site: forum, aggressiveness: standard) [changes site]: applied 3, undone 1 (broke the reply editor), unfixable: large DOM on thread pages
Agent: Three settings are on and one was undone because it broke the reply editor. Large thread pages are the main item left. Open a thread and try the reply box in a browser, with the console visible, and tell me if anything errors.
```

## How it works

1. **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.
2. **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.
3. **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.
4. **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.
5. **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.
6. **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

- 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 Build

Grok Build starts in Ask mode, which prompts for any tool call a rule has not allowed, the dry run included. An MCPTool allow rule for xspeedhub__optimize_site would cover the preview and the real pass alike, so allow only the reads, such as MCPTool(xspeedhub__get_*) and MCPTool(xspeedhub__list_*), and leave optimize_site unmatched. Auto mode lets a classifier approve what it judges safe, and Always-approve skips prompts, and in either one the Hub runs a write as soon as your connection allows writes. Add a deny rule for any tool that must never run unprompted, because deny rules still apply under Always-approve. A read-only connection (the connection token with Read-only everywhere on, or a Viewer sign-in) makes the Hub refuse the preview too, since it counts as a write call.

## 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

### Does Grok Build ask before it optimizes my site?

In its default Ask mode it prompts for any tool call that no rule has allowed, the dry run included. The preview and the real pass are the same tool, so an allow rule for optimize_site covers both. Auto mode and Always-approve remove the prompt, and the Hub has no confirmation step of its own, so add a deny rule for what must never run unprompted, or connect with a connection token that has Read-only everywhere on.

### What should I do when the xSpeed optimization leaves a long unfixable list?

Treat it as a to-do for the site, not a reason to retry. Caching cannot reduce page weight, hotlinked images or page structure, so fix those items in the theme or content, then run the pass again.

### What does optimize_site actually do?

It measures the site, applies the recommended xSpeed settings one at a time, checks that the page still renders after each change, and undoes any change that breaks it. It then reports what was applied, skipped and reverted, and what it could not fix. It reaches caching and asset delivery only.

### Should I run a dry run first?

Yes, especially on a site you have not optimized before. dry_run: true returns the plan, what would be skipped and what cannot be fixed, and changes nothing. The tool description tells the agent to prefer it, but nothing forces it, so say so in your prompt if you want a preview.

### Can I tell it to get my site to a score of 90?

Yes, with target_score, on a site that has xSpeed Pro. It repeats measure, apply and re-measure for up to 3 rounds per site and stops early when rounds stop helping, saying why. On a Free site the score target is ignored and you get a single pass with a note that no iterative tuner is installed.

### Why did it say everything is already on?

That is a real answer. The settings it can apply were already enabled, so there was nothing to change. The result also lists what it could not fix, such as page weight, images hosted on another domain or DOM size, and those need changes outside a caching plugin.

### Does the agent check that my pages still work?

The site checks its own HTML after each change and reverts anything that breaks it, but it cannot run JavaScript. After a run that changed something, the Hub tells the agent to open the returned verify_urls and check the page renders and the console is clean, or to give you the URLs to check yourself.

### Does generate_critical_css work on a Free site?

No. It needs the Pro Critical CSS module on that site, and without it the site answers with an unknown-tool error. On a Pro site, purge the cache afterwards, because pages already cached were built without the critical CSS.

## Raise the PageSpeed score with other agents

[Claude Code](https://xspeedcache.com/agent/claude-code/optimize-site/) · [Claude](https://xspeedcache.com/agent/claude/optimize-site/) · [Claude Cowork](https://xspeedcache.com/agent/claude-cowork/optimize-site/) · [ChatGPT](https://xspeedcache.com/agent/chatgpt/optimize-site/) · [Codex](https://xspeedcache.com/agent/codex/optimize-site/) · [Cursor](https://xspeedcache.com/agent/cursor/optimize-site/) · [GitHub Copilot in VS Code](https://xspeedcache.com/agent/github-copilot/optimize-site/) · [Windsurf](https://xspeedcache.com/agent/windsurf/optimize-site/) · [Gemini CLI](https://xspeedcache.com/agent/gemini-cli/optimize-site/) · [Antigravity](https://xspeedcache.com/agent/antigravity/optimize-site/) · [Zed](https://xspeedcache.com/agent/zed/optimize-site/) · [Kiro](https://xspeedcache.com/agent/kiro/optimize-site/) · [OpenCode](https://xspeedcache.com/agent/opencode/optimize-site/) · [OpenClaw](https://xspeedcache.com/agent/openclaw/optimize-site/) · [Hermes Agent](https://xspeedcache.com/agent/hermes-agent/optimize-site/) · [ChatGPT dots](https://xspeedcache.com/agent/chatgpt-dots/optimize-site/) · [Grok](https://xspeedcache.com/agent/grok/optimize-site/) · [Grok Bot](https://xspeedcache.com/agent/grok-bot/optimize-site/) · [Muse](https://xspeedcache.com/agent/muse/optimize-site/) · [Manus](https://xspeedcache.com/agent/manus/optimize-site/) · [Kimi Code](https://xspeedcache.com/agent/kimi/optimize-site/) · [Paperclip](https://xspeedcache.com/agent/paperclip/optimize-site/) · [NanoClaw](https://xspeedcache.com/agent/nanoclaw/optimize-site/)

## More with Grok Build

- [Purge the WordPress cache with Grok Build](https://xspeedcache.com/agent/grok-build/purge-cache/)
- [Find out why WordPress pages are not cached with Grok Build](https://xspeedcache.com/agent/grok-build/troubleshoot-cache/)
- [Scan a website for speed problems with Grok Build](https://xspeedcache.com/agent/grok-build/speed-scan/)
- [Run and track PageSpeed tests with Grok Build](https://xspeedcache.com/agent/grok-build/pagespeed-tests/)
- [Tune WordPress cache settings with Grok Build](https://xspeedcache.com/agent/grok-build/cache-settings/)
- [Warm the WordPress cache with Grok Build](https://xspeedcache.com/agent/grok-build/preload-cache/)
- [Set up the Redis object cache with Grok Build](https://xspeedcache.com/agent/grok-build/object-cache/)
- [Manage Cloudflare caching with Grok Build](https://xspeedcache.com/agent/grok-build/cloudflare/)
- [Manage every WordPress site at once with Grok Build](https://xspeedcache.com/agent/grok-build/fleet/)

## Documentation

- How to generate Critical CSS: https://xspeedcache.com/docs/critical-css/
- Performance recommendations: https://xspeedcache.com/docs/performance-recommendations/
- How to run a speed test: https://xspeedcache.com/docs/external-score/
- Free vs Pro: what is included: https://xspeedcache.com/docs/free-vs-pro/