agentreadme

Report · marked 25 Aug 2026

SagerNet/sing-box

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

Go · 37,269 stars · 1,534 files · branch testing

63 /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 16/20Whether an agent can install the project and get it running without a human. Losing marks on environment config.Verification loop 20/22Whether an agent can check its own work. This is the category that most decides whether agent output is trustworthy. Losing marks on tests exist.Context economy 18/20Whether the repo fits in a context window, or fights it. Losing marks on file sizes fit in context.Navigability 6/10How quickly anything new can orient itself. Losing marks on repository description and license.

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

Fix these first

01
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.
02
Instruction quality
Instructions earn their keep by naming exact commands. 'Run the tests with `pnpm test`' beats three paragraphs of philosophy.
03
Environment config
Add a .env.example listing every variable with a safe placeholder value. It's the cheapest possible fix and it unblocks the whole first run.

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 16/20 A-

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 6/6
Commands are declared where an agent will look for them.
Makefile
✗Environment config 0/4
Nothing documents the environment this needs. An agent will get a runtime error it can't diagnose.
Add a .env.example listing every variable with a safe placeholder value. It's the cheapest possible fix and it unblocks the whole first 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 20/22 A

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

✗Tests exist 6/8
124 test files against 1156 source files.
e.g. adapter/inbound_test.go, common/badversion/version_test.go, common/convertor/adguard/convertor_test.go
✓Test command is discoverable 7/7
An agent can find and run `make test`.
✓Continuous integration 4/4
6 GitHub Actions workflows define what "passing" means.
✓Lint and format rules 3/3
.golangci.yml encodes the house style.
–Static type checking n/a
Not applicable — the Go compiler type checks every build.
Context economy 18/20 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 23 patterns.
✗File sizes fit in context 4/6
2 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.
common/certificate/mozilla.go — 239KB
common/certificate/chrome.go — 148KB
✓Repository weight 5/5
About 25.4MB 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 SagerNet/sing-box 
# AGENTS.md

The universal proxy platform

## Setup

```
go mod download
```

## Commands

```
make build                  # produce a build
make race
make ci_build
make generate_completions
make schema
make install
```

## Layout

- `common/`       241 source files
- `experimental/` 163 source files
- `cmd/`          113 source files
- `protocol/`     107 source files
- `route/`        83 source files
- `option/`       67 source files

## Conventions

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

## Gotchas

- `common/certificate/mozilla.go` is 239KB. It will not fit comfortably in context, so read it in parts.

---

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/SagerNet/sing-box.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 63 out of 100

[![agent ready](https://agentreadme.com/badge/SagerNet/sing-box.svg)](https://agentreadme.com/SagerNet/sing-box)

Other Go repositories, marked

avelino/awesome-go 78 A- ollama/ollama 85 A golang/go 30 D kubernetes/kubernetes 72 B+ microsoft/TypeScript 82 A- fatedier/frp 96 A+

All Go 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