Connect Codex to your editor
You just shipped a fix from a bare terminal, and a reasonable worry is forming: am I supposed to abandon my editor for this? No. The whole pitch of this last lesson is that Codex is happiest sitting next to the editor you already use, and that it does a different job than the AI completion you already have in there. Get this placement right and the agent stops being a detour you context-switch into and becomes part of how you already work.
Put it next to your code
Section titled “Put it next to your code”Remember from the install lesson that Codex is one agent with several front doors — and the IDE is one of them. There are two ways to stand it next to budgetcli:
The lowest-friction option needs nothing new: open your editor’s integrated terminal and run codex in it, from the repo root, exactly as you did this whole chapter. Now the agent is one pane of the same window as your files — you review its proposed edits in the same place you’d review a teammate’s, without leaving the editor.
The fuller option is the official IDE integration for VS Code or a JetBrains IDE, which wires the two together more tightly — the editor’s open files and selection become context the agent can use, and the diffs it proposes render natively in the editor rather than as text in the terminal. The exact integration surface — which editors are supported and what each adds — moves quickly, so the official docs are the page to trust for specifics. (One nice consequence for this audience: because Cursor is a VS Code fork, the VS Code extension installs there too.)
The durable point underneath the specifics: you do not run Codex in a window far from your code. You run it where your code already is — and because it’s the same agent you configured at the CLI, your sign-in and every habit from this chapter carry straight across.
It complements your completion — it doesn’t compete with it
Section titled “It complements your completion — it doesn’t compete with it”This is the reframe that matters most for anyone arriving from inline AI completion. That tool is autocomplete — it finishes the line you’re typing, in the flow of your keystrokes, and it’s excellent at it. Codex is an agent — you hand it a whole task and it reads across files, makes a set of coordinated edits, and runs your tests. Those are different jobs, and they don’t cancel out:
- Keep your inline completion for the moment-to-moment typing — the function body you’re halfway through, the obvious next line.
- Reach for the agent when the unit of work is a task, not a line — “fix the date bug and add a test,” “add a CSV importer for this new bank’s format,” “find why this report total is off by a few cents.”
You don’t choose between them any more than you choose between autocomplete and a code review. The engineer who gets the most out of this stack runs completion in the gutter for speed and Codex in the terminal for tasks, and lets each do what it’s good at.
The hour, closed
Section titled “The hour, closed”Step back and look at what the first hour actually contained. You installed the agent and learned it’s one tool behind several surfaces, scoped to the directory you launch it in. You authenticated, and learned that the door you came in through has a capability ceiling — and that the automation door is a different door. You watched one turn of the loop on a harmless question — read, propose, approve, apply — then watched all four beats close on a real CSV date bug in code you didn’t write. You read the diff instead of trusting the summary, kept your eyes on the money path while you were in there, and committed the moment it was right. And now the agent is sitting in your editor, next to the completion you already had, doing the job completion can’t.
That’s the foundation. But you fixed exactly one bug, and budgetcli is a week’s worth of work — recategorising years of history, taming each bank’s CSV, reaching an external rate API, generating monthly reports. That work won’t fit in one sitting, which means the next thing you need isn’t another feature; it’s a way to keep a session alive and coherent across days. Next chapter: sessions and context — resuming yesterday’s work and keeping the agent’s attention where it belongs.