How Claude Cowork handles this
Cowork suits the review you would rather not sit through. You have several sites and a client wants a speed summary by the end of the day. You describe the job once: read the stored PageSpeed history for each site, flag any whose mobile score fell since the last run, and retest only those. Cowork works through list_sites and get_score_history on its own, then reports back, which is quicker than asking the same question twelve times in a chat.
The part to watch is the retest. run_speed_test is a PageSpeed Insights run from the Hub, mobile or desktop, one site at a time, and each one can take up to about two minutes. It also spends a speed-test allowance that is shared, so a long task can use more of it than you meant. Put a limit in the brief: retest at most three sites, mobile only, and stop there. run_benchmark can time every site cached and uncached in one call, but it returns response times and no Lighthouse score.
Cowork uses the connectors already on your Claude account, so xSpeed Hub has to be added in Claude first. Cowork loads connectors when a session starts, so open a new session after you add it. Ask for the result as a short summary per site, with the score, the metric that moved and the date of the run it came from.
Set up Claude Cowork once
Already connected? Skip to the prompts. Alternatives and troubleshooting are on the Claude Cowork 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 your Claude account
Cowork does not keep its own connector list. In Claude, go to Customize > Connectors, click Add custom connector, name it xspeedhub, paste the URL, choose Sign in now and, if asked, Register automatically. The full steps, including the Team and Enterprise route, are on the Claude page: /agent/claude/.
https://app.xspeedcache.com/xspeed/mcp
3Connect, then start a new Cowork session
Click Connect on the connector and approve access on the xSpeed Hub page. Cowork loads the connectors enabled for your account when a session starts, so open a new Cowork session after you connect. You can also switch the connector on from the + menu in the chat box.
Customize > Connectors > xspeedhub > Connect
4Set tool permissions before the first task
Open the connector under Customize > Connectors and set each tool to Always allow, Needs approval or Blocked. A sensible start is Always allow for the read tools and Needs approval for purge_cache, toggle_cache, update_settings and the other writes. Then pick a Cowork mode; Manual is the one that shows you each request.
Tool permissions: get_cache_status = Always allow Tool permissions: purge_cache = Needs approval
Full Claude Cowork 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. Cowork has three modes. Manually approve (Manual) pauses and asks you to Allow or Deny each action. Automatically approve (Auto) keeps working and blocks what Claude judges to be unsafe. Skip all approvals (Skip) asks nothing and checks nothing. Each connector tool also has a permission, set under Customize > Connectors. In Manual mode, Always allow runs, Needs approval asks and Blocked is denied; in Skip mode only Blocked stops a call. xSpeed Hub has no confirmation step of its own, so under Skip, or for any tool set to Always allow, a write runs as soon as your connection allows writes. Auto relies on Claude's own judgement, which is not a lock.
What do I ask?
Three prompts written for Claude Cowork. More for this job are below.
Use xSpeed Hub to read the stored PageSpeed history for every site, list the ones whose mobile score dropped, and retest at most three of them on mobile.
With xSpeed Hub, build a one-line-per-site summary of the latest desktop and mobile scores, with the date of each run.
Ask xSpeed Hub for the benchmark history on shop and tell me whether response time improved after the settings change I made on Monday.
What happens, step by step
PageSpeed Insights is Google's Lighthouse audit, and its score and Core Web Vitals are the numbers most people mean by "my speed". Through xSpeed Hub an agent can read the scores a site has already stored, run a new PageSpeed test on mobile or desktop, and read or run a separate benchmark of cached against uncached response time. The three answer different questions, and the Hub tells the agent which to use for each.
01
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.
02
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.
03
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.
04
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.
05
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 worth keeping
- 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 Claude Cowork
Cowork has three modes: Manual asks you to Allow or Deny each action, Auto keeps working and blocks what Claude judges unsafe, and Skip asks nothing and checks nothing. Each connector tool also has its own setting under Customize > Connectors: Always allow, Needs approval or Blocked. Set get_score_history to Always allow and run_speed_test to Needs approval, and stay in Manual for a review you want to watch. Auto is a model judging its own agent, so it is not a lock, and Skip lets every test run. The Hub adds no confirmation of its own, and each test spends shared allowance. If you walk away from a broad review, state a hard cap on tests in the prompt and set run_speed_test to Blocked. Read-only access for Cowork means signing in as a Viewer member of the workspace, or sending the connection token with Read-only everywhere on through Claude's Request headers beta, because that switch covers only the connection token.
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
Keep going
Track PageSpeed scores with other agents
More with Claude Cowork
Documentation
- How to run a speed test
- PageSpeed Insights integration
- Running speed tests in xSpeed Hub
- How to run a PageSpeed audit
- How to write prompts for xSpeed Hub
- Claude Cowork + xSpeed
- Every AI agent that works with xSpeed
From the blog
- Reading a PageSpeed Report in 2026: 30% of the Score Is a Metric Google Does Not Rank You On
- 45% of the WordPress Sites Our Scan Calls Clean Are Failing Google in 2026: Lab Scores Against Field Data
- The Same Page Scored 61 and 73 Twelve Minutes Apart: How to Benchmark WordPress Caching Plugins in 2026