Skip to content
Agent Friendly Code

Cursor vs Codex: which do top repos set up for?

Codex averages higher: 63.5 for Cursor and 70.5 for Codex, across 402 repos. Cursor scores higher on 14, Codex on 388, and 0 tie.

Scores measure how well each repo is set up for an agent: instruction files, tests, CI and the other checks, weighted by what each agent's docs say it uses, not which agent writes better code.

Which files does each one read?

Reads from the repo
Cursor: .cursor/rules/*.mdcAGENTS.mdCLAUDE.md.agents/skills/
Codex: AGENTS.mdAGENTS.override.md.agents/skills/
Reads AGENTS.md
Cursor: Always
Codex: Always
Reads CLAUDE.md
Cursor: Yes
Codex: No
From its docs
Cursor: Project rules are .mdc files in .cursor/rules/, subfolders included; a plain .md there is ignored. AGENTS.md is read at the root and in subdirectories, combined, the more specific winning. CLAUDE.md is read the same way; the docs describe one at the root. A root .cursorrules is legacy and will be deprecated.
Codex: Reads AGENTS.md before any work, one per directory from the repo root down to the working directory, up to 32 KiB combined; AGENTS.override.md replaces the AGENTS.md beside it.
Repos with its own file
Cursor: .cursor/rules or .cursorrules: 18 of 402 (4%)
Codex: AGENTS.md: 207 of 402 (51%)

AGENTS.md and CLAUDE.md mean the file at the repo root; a repo with both counts under AGENTS.md, and empty files don't count. Every agent's files.

Which checks does each weigh more?

Share of each agent's score that a check carries, where Cursor and Codex differ most
CheckCursorCodex
Cursor rules (.cursor/rules)11%0%
CI configuration5%9%
Reproducible dev env6%9%
Type configuration11%9%
AGENTS.md / CLAUDE.md9%11%
Test suite8%10%

Each figure is the check's share of the agent's total weight, from the docs linked below. A check few repos pass, such as an agent's own file, lowers that agent's scores wherever it carries weight. The methodology lists every weight.

Which repos are set up better for Cursor than Codex?

Which repos are set up better for Codex than Cursor?

Which one leads in each language?

Average Cursor and Codex scores of the repos in each language; the higher is in bold
LanguageReposCursorCodex
TypeScript8368.375.7
Python5666.974.1
Rust4567.874.0
Go4067.674.6
Java2858.465.5
C++2154.962.4
JavaScript1569.477.1

What if I use both?

  1. Write the shared instructions once, in AGENTS.md at the repo root. What to put in it.
  2. Cursor: put rules in .cursor/rules/*.mdc; a plain .md there is ignored. It reads AGENTS.md too.
  3. Codex: reads AGENTS.md before any work, up to 32 KiB combined across directories.

AGENTS.md vs CLAUDE.md · Which files each agent reads · Make a repo agent-ready

From the docs: cursor.com/docs/rules (new tab) · cursor.com/skills (new tab) · cursor.com/context/rules (new tab) · cursor.com/customization/rules (new tab) · cursor.com/using (new tab) · learn.chatgpt.com/agents-md (new tab) · learn.chatgpt.com/build-skills (new tab)

Boards: best set up for Cursor · best set up for Codex

More comparisons: Claude Code vs Cursor · Claude Code vs Codex · Gemini CLI vs Claude Code · Aider vs Claude Code · OpenHands vs Claude Code · Pi vs Claude Code · Kimi Code CLI vs Claude Code · Devin vs Claude Code · Codex vs Gemini CLI