Report · marked 25 Aug 2026

songquanpeng/one-api

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

JavaScript · 36,576 stars · 564 files · branch main

60 /100 B-

Instructions 2/27Whether the repo tells an agent how to behave before it starts guessing. Losing marks on agent instruction file and instruction quality.Setup 14/20Whether an agent can install the project and get it running without a human. Losing marks on discoverable commands.Verification loop 15/22Whether 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 lint and format rules.Context economy 20/20Whether the repo fits in a context window, or fights it. Full marks.Navigability 8/10How quickly anything new can orient itself. Losing marks on written documentation.

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

Fix these first

Agent instruction file

Add an AGENTS.md at the root: what the project is, how to install, how to run, how to test, and the two or three conventions a newcomer always gets wrong.

Instruction quality

Instructions earn their keep by naming exact commands. 'Run the tests with `pnpm test`' beats three paragraphs of philosophy.

Discoverable commands

Declare the handful of commands that matter in package.json scripts, a Makefile, or a justfile. Naming them turns guesswork into a lookup.

The full marking

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

Instructions 2/27 F

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

✗Agent instruction file 0/12

None found. Every agent that opens this repo starts from zero.

Add an AGENTS.md at the root: what the project is, how to install, how to run, how to test, and the two or three conventions a newcomer always gets wrong.

Looked for AGENTS.md, CLAUDE.md, .github/copilot-instructions.md, .cursorrules

✗Instruction quality 0/12

Nothing to judge, since there are no instructions.

Instructions earn their keep by naming exact commands. 'Run the tests with `pnpm test`' beats three paragraphs of philosophy.

✗README as an entry point 2/3

README exists but never explains how to get the thing running.

Give the README an Install and a Usage heading with real commands under each. Agents pattern-match on those headings.

Setup 14/20 B+

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

✓Deterministic install 6/6

go.sum pins the dependency tree.

Found go.sum

✗Discoverable commands 0/6

No declared commands. An agent has to infer how to build and run this from the file tree.

Declare the handful of commands that matter in package.json scripts, a Makefile, or a justfile. Naming them turns guesswork into a lookup.

✓Environment config 4/4

.env.example documents what the app needs to run.

✓Pinned runtime version 2/2

The language runtime version is pinned.

go.mod declares a Go version

✓Reproducible environment 2/2

dockerfile gives a known-good environment.

Verification loop 15/22 B

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

✗Tests exist 4/8

7 test files against 481 source files.

Coverage is thin enough that an agent can break real behavior and still see green.

e.g. bin/time_test.sh, common/image/image_test.go, common/network/ip_test.go

✓Test command is discoverable 7/7

An agent can find and run `go test ./...`.

✓Continuous integration 4/4

5 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 n/a

Not applicable — the Go compiler type checks every build.

Context economy 20/20 A+

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 15 patterns.

✓File sizes fit in context 6/6

No source file is large enough to crowd out a context window.

✓Repository weight 5/5

About 16.0MB 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 songquanpeng/one-api

# AGENTS.md

LLM API 管理 & 分发系统，支持 OpenAI、Azure、Anthropic Claude、Google Gemini、DeepSeek、字节豆包、ChatGLM、文心一言、讯飞星火、通义千问、360 智脑、腾讯混元等主流模型，统一 API 适配，可用于 key 管理与二次分发。单可执行文件，提供 Docker 镜像，一键部署，开箱即用。LLM API management & key redistribution system, unifying multiple providers under a single API. Single binary, Docker-ready, with an English UI.

## Setup

```
go mod download
```

## Commands

```
go test ./...   # run the test suite
```

## Layout

- `web/`        243 source files
- `relay/`      152 source files
- `common/`     35 source files
- `controller/` 17 source files
- `middleware/` 12 source files
- `model/`      10 source files

## Conventions

- Tests live alongside the code they cover, following `bin/time_test.sh`.
- CI defines what passing means. See `.github/workflows/ci.yml`, and keep it green.
- TODO: add the two or three conventions a newcomer always gets wrong here.

## Gotchas

- Copy `.env.example` before running anything that needs configuration.

---

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/songquanpeng/one-api.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/songquanpeng/one-api.svg)](https://agentreadme.com/songquanpeng/one-api)

Other JavaScript repositories, marked

react/react 71 B+ affaan-m/ECC 90 A trekhleb/javascript-algorithms 69 B Snailclimb/JavaGuide 53 C+ airbnb/javascript 54 C+ vercel/next.js 77 B+

All JavaScript 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