# What is OpenAI Codex, and what can a marketing team do with it?

Published: 2026-11-09. Updated: 2026-11-09. Written by: Framepx Team.

OpenAI Codex is OpenAI's coding agent: you describe a task, and it inspects your project, edits files and runs commands, in a terminal, a code editor, the ChatGPT desktop app or a cloud environment ([quickstart](https://learn.chatgpt.com/docs/quickstart), [Codex CLI docs](https://learn.chatgpt.com/docs/codex/cli)). Claude Code, Anthropic's tool, does the same kind of job, so for a marketing or content team the choice is mostly about where each one runs and how you review its work.

![Codex at a glance: you give a task, Codex works locally in a terminal, editor or desktop app, or remotely in a cloud environment, and you review the changes before anything is committed.](/blog/codex-lead-en.svg "Codex in one picture: a task in, a reviewable change out.")

## What Codex is

OpenAI's CLI page describes Codex as a way to "inspect code, make changes, run commands, and automate repeatable work without leaving your terminal" ([Codex CLI](https://learn.chatgpt.com/docs/codex/cli)). It works against your local repository, you control the model, permissions and commands, and it fits scripts and CI. Like Claude Code, it is built for software work; what we say about marketing use goes beyond the docs, and we mark it as our reading.

A note on where the docs live. The old address `developers.openai.com/codex` now redirects to `learn.chatgpt.com/docs`, a ChatGPT documentation site where Codex sits beside ChatGPT itself. The pricing page says "ChatGPT Work and Codex share usage" ([pricing](https://learn.chatgpt.com/docs/pricing)). In the desktop app you pick **Codex** for software development, or **ChatGPT** and then **Work** for "research, analysis, or deliverables such as documents, presentations, spreadsheets, and Sites" ([quickstart](https://learn.chatgpt.com/docs/quickstart)). Our reading: a marketer who wants a deck or a spreadsheet will use Work, not Codex. Codex is the part for a team that keeps files in a repository.

## Where you run it

![Four places to run Codex: the terminal CLI, an IDE extension, the ChatGPT desktop app, and Codex Cloud. The first three work on local files; the cloud runs in its own environment.](/blog/codex-surfaces-en.svg "Codex runs locally in three places and remotely in the cloud.")

| Surface | What the docs say |
| --- | --- |
| Codex CLI | Works against your local repository; install with a script, npm or Homebrew; run `codex` in a project folder ([CLI](https://learn.chatgpt.com/docs/codex/cli)) |
| IDE extension | Starts with the open files and selections; works in VS Code, Cursor and Windsurf; Xcode and JetBrains provide their own integrations ([IDE](https://learn.chatgpt.com/docs/codex/ide)) |
| Desktop app | For macOS, Windows and Linux; choose Codex or ChatGPT when you start a chat ([quickstart](https://learn.chatgpt.com/docs/quickstart), [app](https://learn.chatgpt.com/docs/app)) |
| Codex Cloud | Tasks run in a cloud environment; "each task has its own workspace and can keep working while your computer is asleep" ([cloud](https://learn.chatgpt.com/docs/cloud)) |

You sign in with a ChatGPT account, and the quickstart adds that you may also use Codex with an API key, with some features then unavailable ([quickstart](https://learn.chatgpt.com/docs/quickstart)). For a first try, the desktop app is the gentler start.

## How a task works

You open a project and describe the task. The CLI page suggests starting small: ask Codex to explain the project, make a focused change or help debug an issue ([CLI](https://learn.chatgpt.com/docs/codex/cli)). Codex then inspects files, edits them and runs the tools on your machine. The same page advises Git checkpoints before and after a task, so you can revert.

![A task as a loop: you give a task, Codex inspects files, edits and runs commands inside a sandbox, asks for approval at the boundary, and you review the diff.](/blog/codex-task-loop-en.svg "Codex works inside a sandbox and asks at the edge; you review the result.")

Two layers decide what it may do alone ([agent approvals and security](https://learn.chatgpt.com/docs/agent-approvals-security)):

1. **Sandbox mode:** what Codex can do technically, such as where it can write and whether it can reach the network. Locally, the defaults are no network access and writes limited to the active workspace.
2. **Approval policy:** when Codex must stop and ask you. In the `Auto` preset it can read files, edit and run commands in the working directory, and it asks before editing outside the workspace or using the network.

To plan without changing anything, switch to `read-only` mode with the `/permissions` command. The security page also says that by default "the agent runs with network access turned off."

## Instructions it reads first: AGENTS.md

Codex "reads `AGENTS.md` files before doing any work" ([AGENTS.md guide](https://learn.chatgpt.com/docs/agent-configuration/agents-md)). This is where a team writes its rules once: tone, naming, the checks to run, the folders to leave alone.

![AGENTS.md layering: a global file in the Codex home, then the repository root file, then a nested folder file; files closer to your folder come later and override earlier ones.](/blog/codex-agents-md-en.svg "Instruction files stack from global to project to folder; the closest one wins.")

The guide gives the order:

- A global file in your Codex home directory (`~/.codex` by default).
- Then, from the project root down to your working directory, one file per folder, where `AGENTS.override.md` wins over `AGENTS.md`.
- Files are joined from the root down, so the closest file overrides earlier guidance. Combined size stops at 32 KiB by default (`project_doc_max_bytes`).

This is the counterpart of Anthropic's `CLAUDE.md`, which Claude Code "reads at the start of every session." Anthropic also says that if your repository already has an `AGENTS.md`, Claude Code can read it in place of a `CLAUDE.md` ([Claude Code overview](https://code.claude.com/docs/en/overview)). Our reading: a team that tries both tools can keep one `AGENTS.md` and avoid writing the rules twice. Our own walk through the Claude side is in [what Claude Code is and what a marketer can do with it](/blog/what-is-claude-code-and-what-can-a-marketer-do-with-it).

## What a marketing team can do with it

The docs list these capabilities for developers. The right column is our reading of what carries over.

| Capability | What the docs say | Our reading for marketing work |
| --- | --- | --- |
| Skills | A skill packages "instructions, resources, and optional scripts" so the product can follow a workflow, built on an open standard ([skills](https://learn.chatgpt.com/docs/build-skills)) | A weekly report layout or an ad-copy check, written once |
| MCP | Lets Codex use tools and information from other systems; `codex mcp` adds servers ([MCP](https://learn.chatgpt.com/docs/extend/mcp), [CLI](https://learn.chatgpt.com/docs/codex/cli)) | Bring briefs and tickets into the session |
| Subagents | Delegate focused work to specialized agents and bring findings back ([CLI](https://learn.chatgpt.com/docs/codex/cli)) | Let one helper read a long export |
| Scripts and CI | `codex exec` runs non-interactively and prints the final message to `stdout`, so it can be piped ([non-interactive mode](https://learn.chatgpt.com/docs/non-interactive-mode)) | Bulk edits on ad copy variants stored as files |
| Scheduled tasks | Recurring tasks run in the background; in the desktop app, keep the computer on when a task needs local files ([scheduled tasks](https://learn.chatgpt.com/docs/automations)) | A weekly check of a reports folder |
| Review | A dedicated review reports prioritized findings "without modifying your working tree" ([CLI](https://learn.chatgpt.com/docs/codex/cli)) | A second look at changed copy before it ships |

Our piece on [subagents and hooks in Claude Code](/blog/claude-code-subagents-and-hooks-explained) explain the same ideas from the other side.

## Codex and Claude Code side by side

![A two-column comparison of Codex and Claude Code on four questions: where it runs, how you give it work, what it can touch, how you review its work.](/blog/codex-compare-en.svg "The same four questions, answered by each tool's own docs.")

| Question | Codex | Claude Code |
| --- | --- | --- |
| Where it runs | Terminal, IDE extension, ChatGPT desktop app, Codex Cloud ([CLI](https://learn.chatgpt.com/docs/codex/cli), [IDE](https://learn.chatgpt.com/docs/codex/ide), [cloud](https://learn.chatgpt.com/docs/cloud)) | Terminal, VS Code, JetBrains, desktop app, web ([overview](https://code.claude.com/docs/en/overview)) |
| How you give it work | Describe a task in plain language; `codex exec` for scripts; `AGENTS.md` for standing rules | Describe a task in plain language; `claude -p` for scripts; `CLAUDE.md` for standing rules, or `AGENTS.md` read in its place |
| What it can touch | Locally, a sandbox: writes limited to the workspace, network off by default; cloud tasks get their own workspace | Your codebase and your development tools ([overview](https://code.claude.com/docs/en/overview)); the overview page gives no sandbox detail |
| How you review | Inspect commands and diffs as they appear; a dedicated review without edits; commit or open a pull request from a cloud task | Inline diffs and plan review in VS Code, visual diff review in the desktop app ([overview](https://code.claude.com/docs/en/overview)) |

The Codex cells come from the pages cited above. The Claude Code cells come only from Anthropic's overview page, and where that page is silent we say so rather than fill the cell. Both offer a terminal, an editor, a desktop app and a remote option, so surfaces alone decide nothing. The visible difference is the account: ChatGPT for Codex, a Claude subscription or Anthropic Console account for Claude Code.

## What it needs and what to watch

| It needs | Watch for |
| --- | --- |
| A ChatGPT account, or an API key with fewer features ([quickstart](https://learn.chatgpt.com/docs/quickstart)) | Usage is shared with ChatGPT Work, and API token prices are separate from subscription usage ([pricing](https://learn.chatgpt.com/docs/pricing)) |
| A project folder or a connected GitHub repository | In a cloud task, network access and credentials are set in the environment settings; review the setup before you publish it ([cloud](https://learn.chatgpt.com/docs/cloud)) |
| Short, specific instructions in `AGENTS.md` | Once the combined files reach 32 KiB, later files are left out by default ([AGENTS.md guide](https://learn.chatgpt.com/docs/agent-configuration/agents-md)) |
| Your approval at the boundary | A rule in `AGENTS.md` is guidance; the sandbox and approvals are the controls |

## How to start

1. Install Codex from the [CLI page](https://learn.chatgpt.com/docs/codex/cli), or open the ChatGPT desktop app and choose **Codex**.
2. Open a folder that holds one real piece of work, a copy rather than your only version.
3. Write a short `AGENTS.md` with your tone, naming and checks.
4. Start in `read-only` mode, ask for a plan, then let it edit.
5. Add a skill or one connection only when you feel a repeated chore.

Both Codex and Claude Code are tools you steer yourself. If you want finished product ads rather than a workshop, that is what we do at Framepx: an AI system that turns product feeds into ads; [here is how it works](/how-it-works). More guides are in the [blog](/blog).

## FAQ

**Is Codex free?** The pricing page lists a Free plan to "Explore Codex capabilities on quick coding tasks." and a Go plan for "lightweight coding tasks" ([pricing](https://learn.chatgpt.com/docs/pricing)). Plans change, so check the page before you decide.

**Do I need to know how to code?** The tool is built for software work, and its docs are written for developers. A marketer who keeps ad copy, feed files or site content in a folder can use it with plain-language tasks. That is our reading, not a claim of the docs.

**Can Codex change files without asking?** Locally it can edit and run commands in the working directory in the `Auto` preset, and it asks before leaving the workspace or using the network ([security](https://learn.chatgpt.com/docs/agent-approvals-security)).

**Can I use Codex and Claude Code in the same project?** Anthropic says Claude Code can read an existing `AGENTS.md` in place of a `CLAUDE.md` ([overview](https://code.claude.com/docs/en/overview)), so one instruction file can serve both. Which of them you prefer is a question for a small trial on your own files.

## Sources

- [Codex CLI](https://learn.chatgpt.com/docs/codex/cli)
- [Codex IDE extension](https://learn.chatgpt.com/docs/codex/ide)
- [Quickstart](https://learn.chatgpt.com/docs/quickstart)
- [ChatGPT desktop app](https://learn.chatgpt.com/docs/app)
- [Codex Cloud](https://learn.chatgpt.com/docs/cloud)
- [Agent approvals and security](https://learn.chatgpt.com/docs/agent-approvals-security)
- [Custom instructions with AGENTS.md](https://learn.chatgpt.com/docs/agent-configuration/agents-md)
- [Build skills](https://learn.chatgpt.com/docs/build-skills)
- [Model Context Protocol](https://learn.chatgpt.com/docs/extend/mcp)
- [Non-interactive mode](https://learn.chatgpt.com/docs/non-interactive-mode)
- [Scheduled tasks](https://learn.chatgpt.com/docs/automations)
- [Pricing](https://learn.chatgpt.com/docs/pricing)
- [Claude Code overview](https://code.claude.com/docs/en/overview)