Codex 101 — OpenAI Codex Guide

A bilingual guide to using OpenAI Codex in real projects
CLI · Desktop App · IDE Extension · Web/Mobile

Last updated: July 5, 2026
Live Site · Korean README

---

About

Codex 101 is a practical, bilingual guide for people learning or rolling out OpenAI Codex. It covers the main Codex surfaces, setup decisions, safety controls, configuration, MCP, workflow automation, and prompt patterns.

The guide is written from the official OpenAI Codex documentation first, then manually reviewed before publishing. Because Codex changes quickly, treat the live guide as a learning companion and always confirm critical model, pricing, security, and availability details in the official docs.

Start Here

• First-time users: read sections 04-06 for setup and first run, then 10 for sandbox/approval basics, and 14 for OpenAI Docs MCP.
• Professional users: read sections 12-14 for AGENTS.md, config.toml, and MCP, then 15-17 for sessions, automation, and prompt contracts.
• Example-driven readers: open the live site and the use-case gallery to start from real workflows instead of feature lists.

July 5, 2026 Refresh Notes

• Rechecked developers.openai.com/codex/models first again. The recommended Codex lanes remain gpt-5.5, gpt-5.4, gpt-5.4-mini, and gpt-5.3-codex-spark; gpt-5.2 and gpt-5.3-codex are treated as deprecated for ChatGPT-authenticated Codex, not as fallback recommendations.
• Rechecked Quickstart, pricing, speed/Fast mode, best practices, config, Windows/Windows App/IDE/App features/App automations/cloud, remote connections, integrations, MCP, hooks, plugins, skills, Sites, OpenAI API changelog, and current Platform/API surfaces. No Codex activation-flow, model-order, remote-control procedure, Sites setup, or Windows setup change was needed.
• Pricing now needs the Free/Go/Plus/Pro split to stay visible: codex/pricing lists Free $0, Go $8, Plus $20, Pro from $100, Business, Enterprise & Edu, and API Key. Fast mode remains a ChatGPT-sign-in feature for Codex app, CLI, and IDE extension: it speeds GPT-5.5/GPT-5.4 by 1.5x while consuming 2.5x/2x standard credits respectively; API-key Codex uses standard API pricing instead.
• Rechecked recent developers.openai.com/blog and openai.com/index surfaces. Mastering Codex Remote for engineering reinforces the phone-as-control-center pattern already documented in Remote connections, and Making private MCP servers reachable without making them public stays in the Platform/API Secure MCP Tunnel lane. The Simplex customer story was added as enterprise adoption and measurable AI-first delivery context, not a Codex model, plan, preview/GA, feature flag, activation, credential, or permission change.
• Rechecked broader OpenAI product posts. Dreaming: Better memory for a more helpful ChatGPT is a ChatGPT memory update, not a Codex configuration or API/Codex model change, so it is kept out of Codex setup guidance.
• Kept the June 26 GPT-5.6 Sol preview as a separate Platform/API and limited-preview model announcement for select trusted partners/organizations, with broader ChatGPT/Codex/API availability described as coming soon; it is not promoted into the general Codex model picker guidance.
• Kept the June 28 HP Frontier partnership as enterprise adoption context only: OpenAI says HP is deploying ChatGPT Enterprise and Codex to thousands of employees across roles, but this is not a new Codex model, consumer plan, activation step, local app setting, or credential/permission change.
• Kept the June 24 AWS announcement and Workspace Agents announcement in separate enterprise/provider and ChatGPT research-preview lanes, not mixed into Codex App local automation, remote-control, or model-order guidance.
• Audited the official use-case catalog again: 60 official cards after excluding collection pages, 60 local cards, 0 missing local/extra IDs, 0 local promptEn/promptKo gaps, 0 official prompt mismatches, and 0 multiline Korean prompt regressions.
• Used the saved social research note as the baseline. Chrome-specific control was not exposed in this session; Playwright fallback could not use its bundled Chromium, and system Chrome public pages redirected X/LinkedIn to login while Threads showed noisy public posts. No unverified X, Threads, or LinkedIn claim was promoted into the public guide.

June 12, 2026 Refresh Notes

• Rechecked developers.openai.com/codex/models first: gpt-5.5 remains the top Codex recommendation, with gpt-5.4, gpt-5.4-mini, and gpt-5.3-codex-spark in their existing fallback/fast/research-preview lanes.
• Reflected the June 11 Codex app 26.609 release: rate-limit reset banking, Developer mode for Browser/CDP work, /init in the app composer, expanded Enterprise Computer Use, and Windows Computer Use per-app access controls.
• Rechecked pricing, quickstart, config/profile, app settings/features, remote connections, Sites, Bedrock, MCP, hooks, plugins, and skills through the fresh Codex manual. No model-order, remote-control, or Sites setup reversal was needed, but Quickstart now clearly foregrounds the standalone installers.
• Rechecked OpenAI Platform/API docs and kept those notes separate from Codex product guidance. GPT-5.5 remains the latest API model guidance, while Codex pricing/API-key availability still needs scope-specific reading.
• Audited all 60 official Codex use cases after excluding collection pages. The catalog count, local/official IDs, promptEn, promptKo, and multiline Korean prompt shape are clean.
• Rechecked OpenAI launch/customer-story surfaces. The June 11 Ona acquisition announcement is captured only as pre-closing enterprise execution direction, not as an enabled feature, model, plan, platform, preview/GA, or feature-flag change.
• Chrome social checks for X, Threads, and LinkedIn were kept conservative in that run; the June 13 follow-up used logged-in X/LinkedIn people pages and moved the sourced people/tips into a separate research note.

What's Covered

Section	Topic
Start Here	Quick paths for beginners and teams
01-03	Codex ecosystem, product surfaces, supported models
04-05	Requirements, pricing, installation, authentication
06-09	CLI, Desktop App, IDE Extension, Web/Mobile
10-14	Approvals, sandboxing, slash commands, AGENTS.md, config.toml, MCP
15-17	Session strategy, automation, prompt contracts
18-21	Advanced usage, FAQ, references, practitioner tips

Languages

The site currently supports Korean and English. Use the language toggle in the top-right corner of the live page, or update the translation blocks in i18n.js when contributing.

Local Preview

This is a static site. No build step is required for basic review.

open index.html
open use-cases.html

Project Structure

codex-101/
├── index.html          # Main Codex 101 guide
├── use-cases.html      # Use-case gallery
├── app.js              # Theme, language, navigation, interactions
├── i18n.js             # Korean/English translation content
├── use-cases-data.js   # Use-case gallery data
├── style.css           # Responsive styling
└── images/             # Screenshots and explainer visuals

Contributing

Contributions are welcome for corrections, translations, screenshots, examples, and workflow tips.

git clone https://github.com/<your-username>/codex-101.git
cd codex-101
open index.html

After reviewing your change locally, open a pull request with a short explanation of what changed and which page or section you checked.

License

This project is released under the MIT License.

---

Made by @swhan0329
Built with the help of AI. Pull requests are welcome.