# Run and track PageSpeed tests with Grok Bot

> Tracking PageSpeed scores with Grok Bot means giving one of xAI's named Bots a routine that reads your sites' stored PageSpeed history through xSpeed Hub on its cloud computer, and keeping fresh tests behind an approval.

Page: https://xspeedcache.com/agent/grok-bot/pagespeed-tests/
Last updated: October 2026

A Bot keeps its context and works on a persistent cloud computer, so it suits the PageSpeed check you keep meaning to do every Monday. Attach the xspeedhub plugin with @ and ask the Bot to create a routine: read get_score_history for each site, compare the newest mobile and desktop runs with the previous ones, and post a short report of what dropped, with LCP and TBT beside each score. The Bot shows the next run when it saves the routine, and background routines keep running while your laptop is closed. The Hub has no scheduler for agent prompts, so the timer is the Bot's.

Two things about the data shape that report. get_score_history reads the PageSpeed Insights and GTmetrix runs the plugin stored and starts nothing, and the Hub does not run tests on a schedule, so a quiet week can repeat last week's numbers; have the Bot print the date of each site's newest run. When a drop needs confirming, run_speed_test gives a fresh PageSpeed Insights reading from the Hub, mobile or desktop, in up to about two minutes, and saves it to the Hub's own report history, which get_score_history may not show. run_benchmark times cached against uncached response and carries no Lighthouse score.

Because the Bot keeps context, it can set this week's numbers against the report it posted last week without you pasting them back in. On a Team Bot, only the owner can add the plugin from the Setup panel, and each teammate signs in to xSpeed Hub with their own account, so whether a teammate's request can start a test follows that person's workspace role.

## Set up Grok Bot 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. Ask 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.
```

### 3. Attach 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 setup: https://xspeedcache.com/agent/grok-bot/

### 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.

## Prompts

- Create a routine: every Monday at 8:00, use @xspeedhub (xSpeed Hub) to read the PageSpeed history for every site and post any drop. History only.
- Use @xspeedhub (xSpeed Hub) to tell me which site has the oldest stored PageSpeed run.
- With xSpeed Hub, run one desktop test on shop and compare it with the score you reported last week.

## Example session

```
You: Use @xspeedhub (xSpeed Hub) to compare this week's stored PageSpeed runs with last week's report.
  → list_sites [read-only]: 3 sites: shop, blog, docs
  → get_score_history(site: shop) [read-only]: latest mobile 62 (2 days ago), previous 57; desktop 84
  → get_score_history(site: blog) [read-only]: latest mobile 66 (9 days ago), same run as last week
  → get_score_history(site: docs) [read-only]: latest mobile 71 (3 days ago), previous 74; CLS 0.12 against 0.03
Agent: shop is up five on mobile since last week. blog has no new run, so its number is last week's. docs dropped three points and CLS jumped to 0.12, which usually means something shifts the layout. A fresh mobile test on docs would confirm it and spends shared allowance. Run it?
You: Allow once.
  → run_speed_test(site: docs, strategy: mobile) [uses quota]: mobile score 70, CLS 0.11, LCP 2.9 s, saved to the Hub report history
Agent: Confirmed: docs is at 70 with CLS still at 0.11. I will keep the layout shift in next week's report.
```

## How it works

1. **Read before you test**: get_score_history returns the stored PageSpeed Insights and GTmetrix runs for a site: the score per run, with LCP, FCP, CLS, TBT, Speed Index and TTFB, mobile and desktop. It starts nothing. The Hub tells the agent to use it whenever you ask what your score is, or whether it improved, because a new test spends a shared allowance.
2. **Run a new test when you need one**: run_speed_test runs a real PageSpeed Insights audit on the site from the Hub and returns the score, the Core Web Vitals and the top opportunities. strategy is mobile (the default) or desktop, and one call tests one of them. It can take up to about 2 minutes, so the agent should say it is running before it calls.
3. **Test the other device**: Mobile and desktop scores differ, often by a lot. For both, the agent makes two calls, one per strategy. A failure is reported with its reason: PageSpeed not configured, quota reached, a timeout, or a site the audit cannot reach.
4. **Measure the cache on its own**: run_benchmark times the home page with the cache bypassed and again served from cache, and returns the response times. It is a read tool, and it accepts site: "all" for every site. It does not return a Lighthouse score, so the agent must not use it to answer a PageSpeed question.
5. **Compare over time**: get_benchmark_history returns past benchmark runs, uncached against cached, together with the settings changes on the same timeline, which is how you answer "did that change help?". For PageSpeed scores over time, use get_score_history.

## Reference

| | |
| --- | --- |
| Read stored scores | get_score_history (read): PageSpeed Insights and GTmetrix runs, starts nothing |
| Metrics per run | Score, LCP, FCP, CLS, TBT, Speed Index, TTFB, for mobile and desktop |
| Run a new test | run_speed_test (write, uses the shared allowance): one PageSpeed Insights run per call |
| strategy | mobile (default) or desktop |
| Duration | Up to about 2 minutes per run |
| Why a test is a write | It spends a shared PageSpeed allowance and stores a report; it changes nothing on the site |
| Read-only access | A connection token with Read-only everywhere on, or a Viewer member's sign-in: run_speed_test is refused; get_score_history, run_benchmark and get_benchmark_history still work. An OAuth sign-in gets the scopes the client asks for |
| Benchmark | run_benchmark (read): cached against uncached response time for the home page, no Lighthouse score |
| Benchmark history | get_benchmark_history (read): past runs plus settings changes on the same timeline |
| Scheduling | The Hub does not schedule PageSpeed tests itself; its daily pass only reads reports the plugin already stored |
| Where a new test is stored | In the Hub's own report history, the one the Hub dashboard shows |

## Rules

- Check the history first. Ask for stored scores before starting a test, and run a new one only when you want a fresh measurement or something changed.
- Never answer a PageSpeed or Lighthouse question with run_benchmark. It times your own cache and carries no score.
- run_speed_test changes nothing on your site, but the Hub classes it a write because it spends a shared allowance. A connection token with Read-only everywhere on, or a Viewer sign-in, refuses it. An OAuth sign-in gets the scopes the client asks for, so there your client's approval prompt is the gate.
- Lab scores move a few points between runs of the same page. The agent should compare like with like, same site, same strategy, and not report one run's difference as a trend.
- A new test does not run on a timer. If you want a regular test, the agent has to be started by something else, such as a scheduled job in your client, and a scheduled run that spends the allowance should be one you are comfortable leaving unattended.

## Good to know with Grok Bot

xAI notes that a routine's Test run performs real work, including calls to connected tools, so test the routine with a history-only prompt or the test itself can start a speed test. When a call needs approval, Grok Bot offers Allow once, Always allow or Deny. Always allow on run_speed_test saves a rule, and from then on a routine can start tests with nobody there, each one spending the shared allowance, because the Hub has no confirmation step of its own. Add an Ask first rule for run_speed_test under Settings, General, Auto-review, since Ask first wins over an automatic allow, and keep routines to reads so they never need that answer. For a Bot that can only read, sign in as a Viewer member of the workspace: the Hub then refuses run_speed_test, and get_score_history and run_benchmark keep working.

## More prompts for this job

They work in any client connected to xSpeed Hub.

- Using xSpeed Hub, what is the mobile PageSpeed score for shop? Check the stored history before you run anything.
- Use xSpeed Hub to run a new mobile PageSpeed test on blog and tell me the score, LCP and the top opportunities.
- With xSpeed Hub, test shop on desktop and mobile and tell me which one is worse.
- Using xSpeed Hub, has the PageSpeed score on docs improved over the last few runs?
- Use xSpeed Hub to benchmark the cache on every site and tell me which one saves the least time.
- Did turning on minification on shop help? Use xSpeed Hub to compare the benchmark history around that change.
- My PageSpeed test failed on staging. Use xSpeed Hub to tell me why.

## Frequently asked questions

### Will a Grok Bot routine start PageSpeed tests while I am away?

Only if you let it. A routine can call any tool the plugin exposes, and an Always allow rule on run_speed_test removes the prompt. Keep an Ask first rule on it, write the routine as history only, or sign in as a Viewer member so the Hub refuses the test.

### Does the Bot remember last week's scores?

Bots keep context over time, so it can refer back to an earlier report. The numbers themselves come from get_score_history on each run, which is the plugin's stored history, so check the run dates it prints rather than trusting a remembered figure.

### What is the difference between run_speed_test and run_benchmark?

run_speed_test runs a real PageSpeed Insights audit and returns a Lighthouse score with Core Web Vitals. run_benchmark measures how fast your own cache answers compared with an uncached request for the home page, and returns no Lighthouse score. Use the first for "what is my PageSpeed score" and the second for "is my caching working".

### How long does a PageSpeed test take?

A single run can take up to about 2 minutes, so the agent should tell you it has started before it calls. One call tests one device, mobile or desktop, so checking both takes two calls.

### Can I ask for the last score without running a new test?

Yes. get_score_history reads the stored PageSpeed Insights and GTmetrix runs for the site and starts nothing. The Hub tells the agent to read it first whenever you ask what your score is, because a new test spends a shared allowance.

### Will the Hub run PageSpeed tests on a schedule?

No. The Hub does not schedule PageSpeed tests itself. Its daily pass re-verifies sites, snapshots cache status and pulls the PageSpeed and GTmetrix reports the plugin has already stored, and it can alert on a score regression. If you want regular new tests, they have to be started by a client that can run scheduled jobs.

### Why is a speed test treated as a write tool?

It does not change your site. The Hub classes run_speed_test as a write because it spends a shared PageSpeed allowance and stores a report, and a read-only connection (the connection token with Read-only everywhere on, or a Viewer sign-in) should not be able to cost the owner anything. Such a connection can still read stored scores with get_score_history.

## Track PageSpeed scores with other agents

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

## More with Grok Bot

- [Purge the WordPress cache with Grok Bot](https://xspeedcache.com/agent/grok-bot/purge-cache/)
- [Find out why WordPress pages are not cached with Grok Bot](https://xspeedcache.com/agent/grok-bot/troubleshoot-cache/)
- [Scan a website for speed problems with Grok Bot](https://xspeedcache.com/agent/grok-bot/speed-scan/)
- [Raise a WordPress site's PageSpeed score with Grok Bot](https://xspeedcache.com/agent/grok-bot/optimize-site/)
- [Tune WordPress cache settings with Grok Bot](https://xspeedcache.com/agent/grok-bot/cache-settings/)
- [Warm the WordPress cache with Grok Bot](https://xspeedcache.com/agent/grok-bot/preload-cache/)
- [Set up the Redis object cache with Grok Bot](https://xspeedcache.com/agent/grok-bot/object-cache/)
- [Manage Cloudflare caching with Grok Bot](https://xspeedcache.com/agent/grok-bot/cloudflare/)
- [Manage every WordPress site at once with Grok Bot](https://xspeedcache.com/agent/grok-bot/fleet/)

## Documentation

- How to run a speed test: https://xspeedcache.com/docs/external-score/
- PageSpeed Insights integration: https://xspeedcache.com/docs/pagespeed-insights-integration/
- Running speed tests in xSpeed Hub: https://xspeedcache.com/docs/hub-speed-tests-and-notifications/
- How to run a PageSpeed audit: https://xspeedcache.com/docs/pagespeed/