Open Cranes

Codex

Add Cranes to Codex with the Cranes plugin, which brings in your thinking when you type @cranes and keeps your skills in each session, or with one command.

What you get

There are two ways to add Cranes to Codex:

With the plugin Connection only
Your thinking when you type @cranes Brought in before Codex starts on the message Codex calls Cranes when you ask
Your Cranes skills Copied into Codex at the start of each session Come in with your thinking when they fit
Reading and changing your thinking from a session Yes Yes
Saving When you ask, or say yes to an offer When you ask, or say yes to an offer

Set up

With the plugin. It comes from Cranes’s public plugin repository, cranesintelligence/plugins.

  1. In a terminal, run:

    codex plugin marketplace add cranesintelligence/plugins

  2. Run codex, open /plugins, and install Cranes.

  3. Open /hooks, review Cranes’s hooks, and trust them. Codex doesn’t run a plugin’s hooks until you do.

Connection only.

  1. In Cranes, choose Use in other AIs in the sidebar. The Codex card under Add an AI has this command with a copy button.

  2. In a terminal, run:

    codex mcp add cranes --url https://usecranes.com/connect/mcp

Sign in

Each sign-in opens Cranes in your browser. Check what it may use, choose whether to Keep my own ideas, and choose Allow.

With the plugin, there are two sign-ins:

  1. Start a session. The plugin’s first message gives the sign-in command for where Codex installed it; run it in a terminal. This one is for @cranes and your skills. It’s shared on your computer with the plugins for Claude Code and Cursor, and shows under Use in other AIs as Cranes for coding agents.
  2. Start a new session. The first time Codex uses Cranes for anything else, it asks you to sign in.

Connection only: Codex usually sends you to sign in on its own. If it doesn’t, run codex mcp login cranes.

What’s automatic, and when you ask

With the plugin:

  • Your thinking when you type @cranes. Before Codex works on the message, the plugin asks Cranes what your thinking guides for it, and Codex shows what Cranes guided and where each part came from. @cranes on its own checks the work in front of Codex. When nothing applies, Codex says so in a line. Messages without @cranes never reach Cranes.
  • What it sends. Only for a message with @cranes: the message, plus a short description of the work (the repository and branch, how far along it is, and up to five of your earlier messages that corrected Codex). Never your code.
  • Your skills. At the start of each session, your Cranes skills are copied into ~/.agents/skills as cranes- plus the skill’s name. A copy you edit is never overwritten; Codex offers to save your edit back to Cranes. If a skill doesn’t appear, restart Codex.

Connection only: Codex calls Cranes when you ask: type @cranes, or ask what your thinking says.

Either way, saving waits for your yes. To skip typing @cranes in a repository, add the line under Have your AI use Cranes on its own on Use in other AIs to its AGENTS.md. See When Cranes comes in.

Codex Ask us