今日热榜中文

Codex: understand, edit and check a project

Explore OpenAI Codex in the terminal and editor, choose a first development task, and understand how skills and MCP extend it.

What does it do?

Codex is OpenAI’s development assistant. Codex CLI works with local files, edits and installed development tools. The editor extension lets you include open files and selected code in a request and review edits beside the code.

Which task should you try?

Start with understanding a part of an existing project, fixing a known issue or making a focused change. The CLI fits a terminal workflow; the extension fits reviewing changes beside files. This is a choice of working style, not a quality ranking.

How do you get started?

Access and permissions depend on the current product entry point and account. No fixed plan prices or quotas are assumed here.

  1. Follow the official setup guide for the CLI or extension and an available sign-in method.
  2. Open a project you can change and check. Ask about relevant files, then describe one focused task.
  3. Review edits and commands, then run existing project checks before accepting the result.

How do skills and MCP help?

Skills provide repeatable instructions and resources. MCP connects Codex to external tools and data, such as documentation retrieval. Add the capability you need and check its configuration and authorization requirements; inclusion here does not guarantee compatibility with every entry point.

Sources and ranking

This directory lists AI development plugins with public source code and a clear purpose. Browse by task, then open an introduction to learn what a project does, who it is for, and what you need to get started. It covers selected projects, not every AI plugin.

How do the three plugin types differ?

Tool connections (MCP) let AI assistants use external tools such as browsers, code repositories and databases. MCP is the protocol used for these connections.

Reusable skills give a compatible AI assistant instructions and guidance for a particular task.

Editor plugins run inside the software you use to write code, adding AI chat, completions or suggested edits.

How does “Most starred” work?

Projects are sorted by their total GitHub stars. Stars indicate interest; they are not downloads, active users or quality scores. A skill pack counts as one project. Daily star growth is not shown without historical records.

What does “Recently updated” mean?

It uses the most recent code push, which may not be a new release. The 7-day filter checks that project update time; ranking still uses all-time stars. Each introduction shows when its star count was collected. Failed updates keep the last saved data.

Introductions are based on public project documentation. These projects have not each been installed and tested here. Check the project documentation for setup, compatibility and service costs. Refreshing this list only reads saved data; it does not start collection.

UTC+8