Claude Code vs Codex: which do top repos set up for?
Claude Code averages higher: 71.9 for Claude Code and 70.5 for Codex, across 402 repos. Claude Code scores higher on 287, Codex on 107, and 8 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
- Claude Code:
CLAUDE.md.claude/CLAUDE.md.claude/rules/CLAUDE.local.mdAGENTS.md.claude/AGENTS.md - Codex:
AGENTS.mdAGENTS.override.md.agents/skills/ - Reads AGENTS.md
- Claude Code: Only when there is no CLAUDE.md
- Codex: Always
- Reads CLAUDE.md
- Claude Code: Yes
- Codex: No
- From its docs
- Claude Code: Reads AGENTS.md only when no CLAUDE.md,
.claude/CLAUDE.mdor CLAUDE.local.md is found (v2.1.277 and later). A CLAUDE.md that imports@AGENTS.mdloads both, as does a setting. - 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.
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?
| Check | Claude Code | Codex |
|---|---|---|
| Skills (.agents/skills) | 0% | 5% |
| Test suite | 13% | 10% |
| Reproducible dev env | 12% | 9% |
| CI configuration | 7% | 9% |
| AGENTS.md / CLAUDE.md | 13% | 11% |
| Type configuration | 8% | 9% |
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 Claude Code than Codex?
- calcom/cal.diy86.8 vs 81.0 for Codex
- directus/directus83.6 vs 77.8 for Codex
- TheOrcDev/8bitcn-ui79.5 vs 73.7 for Codex
- kubernetes/kubernetes71.4 vs 65.7 for Codex
- guzzle/guzzle81.6 vs 75.9 for Codex
Which repos are set up better for Codex than Claude Code?
- symfony/symfony50.6 vs 43.4 for Claude Code
- flutter/flutter57.7 vs 52.6 for Claude Code
- championswimmer/TwoFac65.7 vs 60.9 for Claude Code
- pandas-dev/pandas79.9 vs 75.7 for Claude Code
- dart-lang/sdk60.8 vs 56.6 for Claude Code
Which one leads in each language?
| Language | Repos | Claude Code | Codex |
|---|---|---|---|
| TypeScript | 83 | 77.0 | 75.7 |
| Python | 56 | 75.6 | 74.1 |
| Rust | 45 | 74.9 | 74.0 |
| Go | 40 | 76.7 | 74.6 |
| Java | 28 | 66.9 | 65.5 |
| C++ | 21 | 64.0 | 62.4 |
| JavaScript | 15 | 79.2 | 77.1 |
What if I use both?
- Write the shared instructions once, in AGENTS.md at the repo root. What to put in it.
- Claude Code: import
@AGENTS.mdin a CLAUDE.md; without that, a CLAUDE.md hides AGENTS.md from it. - 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: code.claude.com/memory (new tab) · code.claude.com/skills (new tab) · learn.chatgpt.com/agents-md (new tab) · learn.chatgpt.com/build-skills (new tab)
Boards: best set up for Claude Code · best set up for Codex
More comparisons: Claude Code vs Cursor · Gemini CLI vs Claude Code · Cursor vs Codex · 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