Agent Friendly Code
← back to leaderboard

openai/codexGitHub

https://github.com/openai/codex
Stars:
77.1k
Default branch:
main
Last scored:
3h ago
Overall

Strengths

  • AGENTS.md / CLAUDE.md
  • CI configuration
  • CONTRIBUTING guide
  • Dependency manifest
  • Reproducible dev env

Gaps

  • Linter / formatter config
  • Pre-commit / git hooks
  • Type configuration

Suggestions to improve for a specific model

  1. 1
    Linter / formatter config
    Configure a linter/formatter (ESLint+Prettier, Biome, Ruff, rustfmt+clippy, golangci-lint) and commit the config.
    +7.9 pts
  2. 2
    Type configuration
    Add a type config (tsconfig.json for JS/TS, mypy.ini or pyrightconfig.json for Python). Rust/Go are typed by default.
    +7.9 pts
  3. 3
    Pre-commit / git hooks
    Set up pre-commit (.pre-commit-config.yaml), husky, or lefthook to run format+lint on every commit.
    +5.3 pts

Per-model scores

Claude Code
Weights AGENTS.md and tests heavily — Claude Code leans on an instructions file and a fast feedback loop.
71.7
Cursor
Weights type config and a detailed README highly — Cursor's inline edits benefit from static types and skim-readable docs.
64.6
Devin
Weights CI and reproducible envs highly — Devin runs in a sandboxed VM and needs end-to-end automation.
74.1
GPT-5 Codex
Balanced profile as a reference point.
70.0

Signal breakdown

AGENTS.md / CLAUDE.md· 100% pass
Substantive (17049 chars)
AGENTS.md
CI configuration· 100% pass
19 GitHub Actions workflow(s)
.github/workflows
CONTRIBUTING guide· 100% pass
Guide present
docs/CONTRIBUTING.md
Dependency manifest· 100% pass
Manifest present
package.json
Reproducible dev env· 100% pass
3 env artifacts (.devcontainer/devcontainer.json, flake.nix)
.devcontainer/devcontainer.json
License file· 100% pass
License present
LICENSE
Linter / formatter config· 0% pass
No linter/formatter config found
Pre-commit / git hooks· 0% pass
No pre-commit / husky / lefthook found
README· 100% pass
README detailed (2626 chars)
README.md
Manageable size· 50% pass
3805 files — large
Test suite· 70% pass
Test files detected (.github/scripts/test_rusty_v8_bazel.py)
.github/scripts/test_rusty_v8_bazel.py
Type configuration· 0% pass
No type config found