# Run and track PageSpeed tests with NanoClaw

> Tracking PageSpeed scores with NanoClaw means asking your self-hosted agent from a chat app for your sites' stored PageSpeed history through xSpeed Hub, or letting an ncl scheduled task post a weekly history report to a chat.

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

NanoClaw puts the question in the chat app you already have open. Message the agent with its trigger word, @Andy by default, and ask how a site scores. The agent group you added xSpeed Hub to calls get_score_history and replies in the thread with the stored runs: score, LCP, FCP, CLS, TBT, Speed Index and TTFB for mobile and desktop. Ask for two or three lines, because a chat bubble is a poor place for a table.

For a regular report, create a scheduled task with ncl tasks create and a cron recurrence. A scheduled task has no chat attached, so the prompt has to say where to post, such as a Telegram chat. Word it as history only: read get_score_history for each site and list any drop with the run dates. The Hub has no scheduler for agent prompts and does not run tests on a timer, so the task reports what the plugin stored, and a site with no new run repeats its old numbers. You can pause, resume, cancel or run the task by hand with ncl tasks.

A fresh test is run_speed_test, a PageSpeed Insights run from the Hub, mobile or desktop, which takes up to about two minutes and spends a shared allowance. The agent replies in the thread once it has the result. The run is saved in the Hub's own report history on the Reports tab, which get_score_history may not include. run_benchmark gives a quick cached against uncached timing with no Lighthouse score.

## Set up NanoClaw 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 to your agent group

Copy the connection token from Connect AI in the Hub (only the workspace owner sees it). Then run this on the machine that hosts NanoClaw, with your agent group's ID from ncl groups list. The header goes in as a JSON object, because NanoClaw refuses credentials inside the URL. NanoClaw may ask an admin to approve the change.

```bash
ncl groups config add-mcp-server --id <group-id> --name xspeedhub \
  --url https://app.xspeedcache.com/xspeed/mcp \
  --headers '{"Authorization":"Bearer <your connection token>"}'
```

### 3. Restart the group and ask

The new server takes effect after a restart. Then message your agent with its trigger word, @Andy by default, and ask something that names xSpeed Hub.

```bash
ncl groups restart --id <group-id>
```

Full setup: https://xspeedcache.com/agent/nanoclaw/

### 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. Whether NanoClaw asks you before an MCP tool runs depends on how your fork and its admins are set up; its documentation gates adding a server behind approval but describes no per-tool prompt for calls. xSpeed Hub has no confirmation step of its own, so a write runs as soon as the agent calls it and your connection allows writes. The Hub tells the agent to confirm the target site and to ask once before a write that touches every site, which in NanoClaw shows up as a question in the chat. The firm stop is the token: with Read-only everywhere on, the Hub refuses every write tool. Keep it on for scheduled tasks.

## Prompts

- @Andy use xSpeed Hub to give me the latest mobile and desktop PageSpeed scores for shop, with the run dates.
- @Andy with xSpeed Hub, tell me which of my sites dropped on mobile since its previous stored run.
- @Andy using xSpeed Hub, time every site cached and uncached and name the slowest cached one.

## Example session

```
You: @Andy use xSpeed Hub to tell me how shop scores on mobile now.
  → get_score_history(site: shop) [read-only]: latest mobile 55 (12 days ago), previous 59; LCP 4.2 s
Agent: shop is 55 on mobile, from a run 12 days ago, down four from the run before. LCP is 4.2 s. A fresh test takes up to two minutes and spends shared allowance. Want one?
You: Yes, one mobile test.
  → run_speed_test(site: shop, strategy: mobile) [uses quota]: mobile score 57, LCP 4.0 s, TBT 290 ms, saved to the Hub report history
Agent: Fresh run: 57 on mobile, LCP 4.0 s. Still below the run before last, so the dip looks real but small.
```

## 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 NanoClaw

NanoClaw gates adding a server behind approval but describes no per-tool prompt for calls, so whether the agent stops before run_speed_test depends on your fork. The Hub has no confirmation step of its own. It tells the agent to confirm before a write across every site, which shows up as a question in the chat, but a single-site test needs no such question to run. For the scheduled task, send a connection token with Read-only everywhere on, so the Hub refuses run_speed_test whatever the prompt drifts into. The scheduled task and your chat messages go through the same agent group and token, so turning the switch off to allow tests from chat also allows purges and settings changes on every message, scheduled or not. The token sits in the group's container configuration on your host, so keep that machine and its backups private.

## 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

### Can NanoClaw send me a weekly PageSpeed report?

Yes. ncl tasks create runs a prompt on a cron schedule. Name the chat to post to in the prompt, because a scheduled task has no conversation attached, and keep it to get_score_history so it reads stored runs without spending the speed-test allowance.

### Will NanoClaw ask before it starts a speed test?

That depends on your fork, because NanoClaw describes no per-tool prompt for calls. The Hub has no confirmation step of its own, so with a write-enabled token a test runs once the agent calls it. Turn on Read-only everywhere on the token if the agent should only read.

### 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/) · [Grok Bot](https://xspeedcache.com/agent/grok-bot/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/)

## More with NanoClaw

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