Category
Coding agents
Agents that operate on a repository you already have: an editor, a terminal agent, and a ChatGPT-plan agent.
Answer
This category is Cursor, Claude Code, and OpenAI Codex. They are grouped because their public products work inside or against an existing codebase. Lovable and v0 are in app builders instead, because they generate an app from a prompt.
Tools in this category
Claude Code is Anthropic's coding agent for the terminal and several other surfaces. It is included with paid Claude plans and shares those plans' usage limits. A Console account bills API tokens instead.
coding-agentsOpenAI CodexCodex is included with ChatGPT plans rather than sold as its own subscription. Plus is $20 a month and adds the CLI, IDE, web, iOS, and cloud integrations. An API key bills platform token rates and does not include cloud features.
coding-agentsCursorCursor is a desktop coding editor sold as part of The X Subscription. Paid plans share a weekly usage pool with Grok. Plus is Grok-only. Premium and above can call third-party models at API list price, billed separately.
Use a tool page for prices. Use the Cursor and Claude Code comparison when the decision is editor versus terminal. The best-of page for Next.js explains why these three are listed ahead of the app builders for work in an existing repo.
Questions
Why is this not sorted by a score?
No hands-on test has been run. The category page lists the tools and links to the research pages. The Next.js best-of page is the only ordered list, and it explains its ordering rule.
Do these share one price?
No. Cursor is The X Subscription, Claude Code is included with paid Claude plans, and Codex is included with ChatGPT plans or billed as API usage. Each tool page has the source link and the date checked.