Report · marked 25 Aug 2026

openai/codex

Solid foundations, held back in a few specific places.

Rust · 118,001 stars · 6,609 files · branch main

82 /100 A-

Instructions 25/27Whether the repo tells an agent how to behave before it starts guessing. Losing marks on instruction quality.Setup 16/16Whether an agent can install the project and get it running without a human. Full marks.Verification loop 21/25Whether an agent can check its own work. This is the category that most decides whether agent output is trustworthy. Losing marks on lint and format rules and static type checking.Context economy 9/20Whether the repo fits in a context window, or fights it. Losing marks on file sizes fit in context and repository weight.Navigability 9/10How quickly anything new can orient itself. Losing marks on repository description.

Higher is better. Accent marks what is costing you most.

Fix these first

File sizes fit in context

A single file that fills the context window forces an agent to work from fragments, and it will confidently edit code it never saw. Splitting the worst offenders pays for itself immediately.

Repository weight

Large binaries and vendored trees slow every operation an agent performs. Git LFS or a separate assets repo keeps the working tree navigable.

Lint and format rules

A formatter config is the cheapest way to stop reviewing whitespace in agent diffs. It moves style from opinion to a command.

The full marking

Every deduction below names the file or setting it came from.

Instructions 25/27 A+

Whether the repo tells an agent how to behave before it starts guessing.

✓Agent instruction file 12/12

AGENTS.md is present, which is the format the most tools read.

✗Instruction quality 10/12

Specific enough that an agent can act on it.

Worth fixing: it's 22k characters, which burns context on every single turn.

names the actual commands to run

uses headings, so an agent can skim it

includes copyable code blocks

✓README as an entry point 3/3

README has a clear getting-started section.

Setup 16/16 A+

Whether an agent can install the project and get it running without a human.

✓Deterministic install 6/6

pnpm-lock.yaml pins the dependency tree.

Found pnpm-lock.yaml

✓Discoverable commands 6/6

Commands are declared where an agent will look for them.

package.json scripts (format, format:fix, write-hooks-schema)

justfile

scripts/ directory

–Environment config n/a

Not applicable — this reads as a library, with no environment to configure.

✓Pinned runtime version 2/2

The language runtime version is pinned.

package.json engines.node >=22

✓Reproducible environment 2/2

.devcontainer/devcontainer.json gives a known-good environment.

Verification loop 21/25 A-

Whether an agent can check its own work. This is the category that most decides whether agent output is trustworthy.

✓Tests exist 8/8

754 test files against 4269 source files.

e.g. .codex/skills/babysit-pr/scripts/test_gh_pr_watch.py, .github/scripts/macos-signing/test_notarize_with_akv.py, .github/scripts/test_macos_signing_entitlements.py

✓Test command is discoverable 7/7

An agent can find and run `pytest`.

✓Continuous integration 4/4

27 GitHub Actions workflows define what "passing" means.

✗Lint and format rules 0/3

No linter or formatter config. Style is tribal knowledge, so agent output will drift from yours.

A formatter config is the cheapest way to stop reviewing whitespace in agent diffs. It moves style from opinion to a command.

✗Static type checking 2/3

Type checking is configured, but not in strict mode.

A type checker gives an agent an error message instead of a runtime surprise. It's the second-fastest feedback loop after the compiler.

Context economy 9/20 C

Whether the repo fits in a context window, or fights it.

✓No committed build output 6/6

No generated directories committed.

✓.gitignore hygiene 3/3

.gitignore covers 56 patterns.

✗File sizes fit in context 0/6

73 source files are over 100KB.

A single file that fills the context window forces an agent to work from fragments, and it will confidently edit code it never saw. Splitting the worst offenders pays for itself immediately.

codex-rs/tui/src/bottom_pane/chat_composer.rs — 499KB

codex-rs/core/src/session/tests.rs — 419KB

codex-rs/core/src/config/config_tests.rs — 394KB

✗Repository weight 0/5

About 573MB checked out. Large enough that cloning and searching are both slow.

Large binaries and vendored trees slow every operation an agent performs. Git LFS or a separate assets repo keeps the working tree navigable.

Here is your AGENTS.md

Drafted from what is actually in this repository: the install command from your lockfile, the commands you already declare, your real directory layout. Anything marked TODO needs a person. Save it at the root as AGENTS.md.

AGENTS.md — drafted for openai/codex

undefined

Open the raw markdown or curl -o AGENTS.md agentreadme.com/draft/openai/codex.md

Show the mark

The badge re-checks daily, so it keeps up as the repository changes. Use mark again to force it now.

[![agent ready](https://agentreadme.com/badge/openai/codex.svg)](https://agentreadme.com/openai/codex)

Other Rust repositories, marked

ultraworkers/claw-code 69 B farion1231/cc-switch 64 B rustdesk/rustdesk 68 B rust-lang/rust 65 B tauri-apps/tauri 62 B denoland/deno 67 B

All Rust repositories

Think this mark is wrong?

Every deduction above names the file it came from, so this can be settled by looking. If a check missed something, that is a rule worth fixing.

Open an issue, already filled in