How NanoClaw handles this
A scheduled task posts the stored PageSpeed history to Slack every Monday, read through get_score_history, which starts nothing. This week shop is down seven points on mobile. Before you reply to the agent, you open the Connect AI page and switch Read-only everywhere off. The token in the agent group's header is the same one the Monday report uses, and the Hub counts optimize_site as a write even in a dry run, so with the switch on it refuses the preview as well as the pass.
Then you message the agent with its trigger word and ask it to use xSpeed Hub to preview a pass on shop. It calls optimize_site with dry_run on and posts the plan in the chat: the settings xSpeed would turn on at the standard level, with nothing changed. You answer yes, and the real pass measures the site, applies each setting one at a time, checks the page after each, and undoes anything that breaks it, for up to about two minutes. The reply lists applied, undone and unfixable, plus the verify URLs the Hub hands back. The Hub tells the agent to have those pages checked, and from a chat app that means you open them on a computer with the browser console visible, because xSpeed checks HTML and cannot run JavaScript.
Then switch Read-only everywhere back on. The switch belongs to the token, and the token is what every agent group and every other client that sends it uses, so leaving it off turns the Monday report into a task that could write. If you want a pass on every site, optimize_site accepts them all in one call, but the Hub's confirm-once instruction for writes across every site does not name optimize_site, so ask the agent to list the sites and wait for your yes.
Set up NanoClaw once
Already connected? Skip to the prompts. Alternatives and troubleshooting are on the NanoClaw 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 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.
ncl groups config add-mcp-server --id <group-id> --name xspeedhub \
--url https://app.xspeedcache.com/xspeed/mcp \
--headers '{"Authorization":"Bearer <your connection token>"}' 3Restart 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.
ncl groups restart --id <group-id>
Full NanoClaw 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. 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.
What do I ask?
Three prompts written for NanoClaw. More for this job are below.
@Andy use xSpeed Hub to read the stored PageSpeed history for every site and post any mobile drop. Read only.
@Andy with xSpeed Hub, preview an optimization for shop at the standard level and wait for my yes.
@Andy using xSpeed Hub, list the verify URLs and the unfixable list from the last run on shop.
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 NanoClaw
NanoClaw's documentation gates adding a server behind approval but describes no per-tool prompt for tool calls, so whether the agent stops before the real pass depends on your fork and on the model following the Hub's instructions. xSpeed Hub has no confirmation step of its own, and the dry run and the real pass are the same tool, so a model that skips the preview applies the pass straight away once writes are allowed. Say plainly in your message that it must show the plan and wait, and keep the window with writes allowed short. Do not put optimize_site in a scheduled task: ncl tasks create runs a prompt with no chat attached and nobody to read the plan or open the pages. The token sits in the agent group's container configuration on your host, so keep that machine private.
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 NanoClaw
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
- NanoClaw + xSpeed
- Every AI agent that works with xSpeed
From the blog