Report · marked 9 Oct 2026

carbon-language/carbon-lang

An agent can work here, but it will waste turns finding its footing.

C++ · 33,900 stars · 5,572 files · branch trunk

69 /100 B

Instructions 21/27Whether the repo tells an agent how to behave before it starts guessing. Losing marks on instruction quality.Setup 8/14Whether an agent can install the project and get it running without a human. Losing marks on deterministic install.Verification loop 13/22Whether an agent can check its own work. This is the category that most decides whether agent output is trustworthy. Losing marks on tests exist and test command is discoverable.Context economy 15/20Whether the repo fits in a context window, or fights it. Losing marks on file sizes fit in context and repository weight.Navigability 7/10How quickly anything new can orient itself. Losing marks on license.

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

Fix these first

Test command is discoverable

Add a `test` script or a `test` target that runs the whole suite with no arguments. The convention is the interface — an agent tries `npm test` and `make test` before it tries reading your CI config.

Deterministic install

Commit the lockfile your package manager generates. Without it, an agent's install and your install are different builds, and 'works on my machine' becomes unfalsifiable.

Instruction quality

Worth fixing: it never states a build, test, or run command; has no code blocks.

The full marking

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

Instructions 21/27 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 6/12

Real instructions, with gaps.

Worth fixing: it never states a build, test, or run command; has no code blocks.

1,070 characters, a workable length

uses headings, so an agent can skim it

✓README as an entry point 3/3

README has a clear getting-started section.

Setup 8/14 B-

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

✗Deterministic install 0/6

No lockfile. An agent installing dependencies may not get what CI got.

Commit the lockfile your package manager generates. Without it, an agent's install and your install are different builds, and 'works on my machine' becomes unfalsifiable.

✓Discoverable commands 6/6

Commands are declared where an agent will look for them.

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.

Found .python-version

–Reproducible environment n/a

Not applicable — a library doesn't need a container to be worked on.

Verification loop 13/22 B-

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

✗Tests exist 6/8

95 test files against 805 source files.

e.g. bazel/cc_toolchains/cc_tools_test.py, common/array_stack_test.cpp, common/build_data_test.cpp

✗Test command is discoverable 0/7

There's no obvious way to run the tests. Even if tests exist, an agent won't reliably find the entry point.

✓Continuous integration 4/4

12 GitHub Actions workflows define what "passing" means.

✓Lint and format rules 3/3

pyproject.toml encodes the house style.

–Static type checking n/a

Not applicable — the C++ compiler type checks every build.

Context economy 15/20 B+

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 23 patterns.

✗File sizes fit in context 2/6

5 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.

toolchain/check/import_ref.cpp — 219KB

toolchain/check/eval.cpp — 163KB

toolchain/check/convert.cpp — 123KB

✗Repository weight 4/5

About 133.7MB checked out, which is comfortable.

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 carbon-language/carbon-lang

# AGENTS.md

Carbon Language's main repository: documents, design, implementation, and related tools. (NOTE: Carbon Language is experimental; see README)

## Setup

```
# TODO: the install command. No lockfile was found, so this could not be inferred.
```

## Commands

```
ruff check .   # lint
```

## Layout

- `toolchain/` 608 source files
- `common/`    101 source files
- `scripts/`   28 source files
- `testing/`   27 source files
- `utils/`     12 source files
- `proposals/` 9 source files

## Conventions

- Tests live alongside the code they cover, following `bazel/cc_toolchains/cc_tools_test.py`.
- CI defines what passing means. See `.github/workflows/auto_label_prs.yaml`, and keep it green.
- TODO: add the two or three conventions a newcomer always gets wrong here.

## Gotchas

- `toolchain/check/import_ref.cpp` is 219KB. It will not fit comfortably in context, so read it in parts.
- No lockfile is committed, so an install here may not match what CI produced.

---

Drafted by agentreadme.com from what is in this repository. Everything marked TODO
needs a human. Check it in as AGENTS.md at the root.

Open the raw markdown or curl -o AGENTS.md agentreadme.com/draft/carbon-language/carbon-lang.md

A draft gets the commands right and stops at the things only a maintainer knows. What a good C++ AGENTS.md looks like covers what to add by hand, and what AGENTS.md is explains the format itself.

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/carbon-language/carbon-lang.svg)](https://agentreadme.com/carbon-language/carbon-lang)

Other C++ repositories, marked

tensorflow/tensorflow 34 D ggml-org/llama.cpp 74 B+ react/react-native 73 B+ electron/electron 85 A godotengine/godot 39 D microsoft/terminal 56 B-

All C++ 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