How Codex handles this
Codex is usually open on a repository when the cache goes cold. You merged a change, the release went out, and you ask it to warm the site that runs from that repository. It matches the name against list_sites, calls start_preloader on that handle, and the plugin begins crawling the sitemap in the background. You never leave the session to open wp-admin or run a crawl by hand.
To watch it, ask for progress. Codex calls get_preloader_status, a read that reports whether a run is active and how far through the URL list it has got. If the crawl overlaps with something heavy, tell Codex to stop it and it calls stop_preloader. Pages already warmed stay cached. For one site only, you can also let Codex use the preloader command of WP-CLI when it has a shell on that server, though the Hub route needs no server access at all.
Codex has a sandbox and an approval policy, and those govern shell commands. MCP tools have their own settings: each server takes default_tools_approval_mode (auto, prompt, writes or approve), and each tool can override it. By default Codex asks only about MCP calls that advertise side effects or a destructive annotation, and xSpeed Hub's tools declare neither, so that default does not cover start_preloader. Set the server to prompt, then give get_preloader_status an approve override so the read runs quietly. The Hub runs a start as soon as your connection allows writes, so approval_policy never, the yolo flag or an auto-approving reviewer leave nothing in front of the crawl.
Set up Codex once
Already connected? Skip to the prompts. Alternatives and troubleshooting are on the Codex 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 and sign in
Add the server with its URL, then log in. The login opens an xSpeed Hub page in your browser; approve access there. There is no token to paste, and Codex keeps the credentials it receives. Start Codex and type /mcp to see the server.
codex mcp add xspeedhub --url https://app.xspeedcache.com/xspeed/mcp codex mcp login xspeedhub
3Keep the Hub's tools on a prompt
Open ~/.codex/config.toml. Set the server to prompt for every tool, then let one read tool run without a question. The tool timeout defaults to 60 seconds, and a PageSpeed test can take up to about two minutes, so raise it.
[mcp_servers.xspeedhub] url = "https://app.xspeedcache.com/xspeed/mcp" default_tools_approval_mode = "prompt" tool_timeout_sec = 150 [mcp_servers.xspeedhub.tools.get_cache_status] approval_mode = "approve"
Full Codex 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. Codex has two layers for shell work: the sandbox mode limits what commands can touch, and the approval policy sets when Codex stops to ask. MCP tools have their own settings. Each server takes default_tools_approval_mode (auto, prompt, writes or approve) and each tool can override it with approval_mode. Codex also asks about MCP calls that advertise side effects or a destructive annotation, but xSpeed Hub's tool definitions do not declare either, so do not rely on that default for the Hub; set the server to prompt. approval_policy never, --yolo and an auto_review reviewer take the human out of the loop. xSpeed Hub has no confirmation step of its own, so an approved or auto-approved write runs as soon as your connection allows writes.
What do I ask?
Three prompts written for Codex. More for this job are below.
The release just shipped. Use xSpeed Hub to warm the shop site and show me the preloader progress once.
With xSpeed Hub, check get_preloader_status on blog and stop the preloader if it has been running for a while.
Use xSpeed Hub to warm only the two sites I changed today, shop and docs, and report each result.
What happens, step by step
The first visitor to an uncached page pays for building it. The preloader fixes that by visiting your pages first. Through xSpeed Hub an agent can start the crawl on one site or on every site in a workspace, watch how far it has got, and stop it. The crawl runs inside WordPress in the background; the agent only starts it, reads its progress and stops it.
01
Check the cache and the preloader
get_cache_status tells the agent whether page caching is on, because there is nothing to fill when it is off. get_preloader_status shows whether a crawl is already running, so the agent does not start a second one.
02
Make sure the preloader is switched on
The preloader module is off on a fresh install, and the site refuses start_preloader until it is on. The agent can read the module with get_settings and, if you agree, switch it on with update_settings on the preloader module. The Hub tells the agent to briefly confirm intent before an update_settings call, but that is guidance to the agent, not a lock.
03
Start the crawl
start_preloader makes the site read its sitemap, follow any nested sitemap indexes, drop URLs that your cache exclusion rules skip, and queue the rest. The call returns once the queue is built; the pages are then fetched in the background, a few per run. For every site at once the agent passes site: "all", and the Hub starts the sites one after another with a one-second pause.
04
Watch the progress
get_preloader_status reports whether a crawl is running, how many URLs it has processed out of the total, the last URL it visited and the most recent errors. It works on one site at a time, so for several sites the agent calls it once per site.
05
Read what failed
A page that answers 403 or 406 usually means a server firewall is blocking the warmer by its user-agent, not that the page is broken. The status message names the user-agent to allow. A crawl that queues no URLs is reported as an error with the reason, not as a success.
06
Stop it if the server struggles
stop_preloader ends a running crawl. It is safe mid-run: pages already warmed stay cached. The agent can stop one site or every site in the workspace.
Reference
| Start and stop | start_preloader and stop_preloader (write) |
|---|---|
| Progress | get_preloader_status (read): running or not, processed out of total, last URL, recent errors |
| What gets crawled | The sitemap (the WordPress one at /wp-sitemap.xml unless you set another), nested indexes followed, excluded URLs skipped |
| Needs | The preloader module switched on (it is off by default) and page caching on |
| Pages per run | 5 by default, 1 to 50, set in the preloader module |
| Schedule setting | manual, hourly, daily or weekly, set in the preloader module |
| Every site at once | start_preloader and stop_preloader accept site: "all"; get_preloader_status does not |
| Fan-out pacing | Sites start one after another with a 1 second pause, one result per site |
| Warmer user-agent | xSpeed-Warmer/1.0, the string a firewall rule would need to allow |
| Stopping | Safe mid-run; warmed pages stay cached |
| Read-only access | A Viewer member's sign-in, or the connection token with Read-only everywhere on: start_preloader and stop_preloader are refused; get_preloader_status works. An OAuth sign-in by anyone else gets the scopes the client asks for. |
| Confirmation | None on the Hub; your client's prompt is the gate |
Rules worth keeping
- Warm after a purge, not instead of one. The Hub tells the agent that starting the preloader after a purge saves the next visitor from paying for the rebuild.
- A crawl requests every page in the sitemap, so it adds load to the origin. Start with one site, and on a small host keep Pages per run low or stop the crawl if the site slows.
- start_preloader and stop_preloader are write tools. The Hub calls the preloader low-risk and only asks the agent to confirm when the target site is unclear or the call covers every site, so your client's approval prompt and read-only access (a Viewer sign-in, or the connection token with Read-only everywhere on) are the gates that matter.
- A fan-out only starts the crawls. Check each site with get_preloader_status afterwards, and treat some sites failing to start as a partial result, not a failure of the whole call.
Good to know with Codex
Codex's default does not put a prompt in front of the Hub's tools, because they declare no side-effect annotation. Set the server to prompt and Codex asks before every Hub call, start_preloader and stop_preloader included. A per-tool approve override on the start runs it without a question, on any site the agent names. approval_policy never and --yolo remove prompts for everything, MCP calls included, so for any run you start that way, and for codex exec in scripts or CI where nobody can answer a prompt, use the connection token with Read-only everywhere on (or a Viewer sign-in).
More prompts for this job
They work in any client connected to xSpeed Hub.
Use xSpeed Hub to start the preloader on shop and tell me how many URLs it queued.
Using xSpeed Hub, how far through its crawl is blog? Show processed against total and any errors.
With xSpeed Hub, purge the cache on docs, then warm it again.
Use xSpeed Hub to start the preloader on every site in my workspace and tell me which ones refused.
Use xSpeed Hub to stop the preloader on shop. It is slowing the server down.
The preloader on shop says it is disabled. Use xSpeed Hub to turn the module on, then start the crawl.
Using xSpeed Hub, which of my sites has no running crawl and a low hit ratio?
Frequently asked questions
Keep going
Warm the cache with other agents
More with Codex
Documentation
- How to warm your cache ahead of visitors
- How to crawl your sitemap
- How to enable Page Cache
- Managing your fleet with xSpeed Hub
- How to write prompts for xSpeed Hub
- Codex + xSpeed
- Every AI agent that works with xSpeed
From the blog