Guide the Codex with AGENTS.md

AGENTS.md Writing Principles

AGENTS.md is the description that should be read first after entering the Codex project. It’s not marketing copy, nor a complete tutorial, but a how-to manual for engineering collaborators. The content should be short, clear, stable, and actionable.

Suggestions include: project overview, directory boundaries, installation commands, development commands, build commands, test commands, coding style, design rules, prohibitions, submission or deployment requirements. Subdirectories can contain more specific AGENTS.md to override or supplement upper-level rules.

Don't write about keys, cookies, temporary accounts, and outdated status; don't explain every file. Codex can read the information obtained by the code without writing all the information into AGENTS.md.

Study Checklist

After reading this page, do not just remember the concept name. You should be able to place "Guide the Codex with AGENTS.md" back into a real Codex engineering workflow: where the task starts, what context the system loads, which actions need approval, how the result is verified, and how to roll back when it fails.

If this is a configuration or reference page, be specific about where the configuration is placed, whether it will be submitted, whether it contains sensitive information, whether it will extend the default permissions, and how to troubleshoot the settings that actually took effect in the event of a failure.

• Be able to describe in your own words the specific problem this page solves, rather than just reciting the title.
• Able to write a minimal example task with goals, scope, prohibitions, and acceptance criteria.
• Be able to determine which information should be put into the current prompt and which should be captured as project rules or configurations.
• Be able to explain which long-term rules should go into AGENTS.md, and which runtime behavior should be handled by config.toml, permission profile, skills and MCP.
• Ability to check diffs, command output, test results, screenshots or PR notes after a task is completed instead of just trusting the natural language summary.

If this page is used for team training, ask learners to complete a small task with Codex: read and explain first, submit a plan, make the smallest useful change, and close with real verification commands plus human diff review.

Codex Practical Notes

This page affects the default behavior of Codex. Before configuring, determine whether it will expand file writing, network access, tool invocation, or silent execution capabilities, and retain audit and rollback methods for the team.

When handling tasks related to "Guide the Codex with AGENTS.md", always confirm the current Git status and working directory first. Codex can make changes quickly, but it does not automatically know which uncommitted edits came from the user, which files are off limits, or which commands may affect production.

• Prioritize using low-risk branches or working trees for local tasks, and review them with git diff after completion.
• When it comes to installation dependencies, networking, databases, deployment, push, deletion, and reset, Codex must first be asked to explain the impact before approval.
• Results generated by remote or collaborative portals must also be confirmed back to PR, CI, build logs and test evidence.
• Automated tasks must define failure output and exit conditions in advance to avoid Codex repeatedly trying in the wrong direction.

Think of Codex as an engineering teammate who can execute commands, rather than an assistant who can only write text. The closer you get to a real system, the greater the need for clear boundaries, evidence, and rollbacks.