Report · marked 9 Oct 2026

bojieli/ai-agent-book

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

Python · 53,104 stars · 11,245 files · branch main

57 /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 pinned runtime version and reproducible environment.Verification loop 24/25Whether an agent can check its own work. This is the category that most decides whether agent output is trustworthy. Losing marks on static type checking.Context economy 6/20Whether the repo fits in a context window, or fights it. Losing marks on no committed build output and file sizes fit in context.Navigability 10/10How quickly anything new can orient itself. Full marks.

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.

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.

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

uv.lock pins the dependency tree.

Found uv.lock

✓Discoverable commands 6/6

Commands are declared where an agent will look for them.

scripts/ directory

✓Environment config 4/4

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

✗Pinned runtime version 0/2

No pinned runtime version.

Add a .nvmrc, .python-version, or equivalent so the agent's toolchain matches yours.

✗Reproducible environment 0/2

No container or devcontainer definition.

A Dockerfile or devcontainer removes an entire class of 'it won't install' failures.

Verification loop 24/25 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

660 test files against 2014 source files.

e.g. book-ar/test_svg_lib.py, chapter1/context/test_experiment_1_1.py, chapter1/context/test_grounding.py

✓Test command is discoverable 7/7

An agent can find and run `pytest`.

✓Continuous integration 4/4

7 GitHub Actions workflows define what "passing" means.

✓Lint and format rules 3/3

pyproject.toml encodes the house style.

✗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 6/20 D

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

✗No committed build output 3/6

Generated output is committed: __pycache__/.

Add these to .gitignore and `git rm -r --cached` them. Generated files pollute search results, so an agent grepping for a function finds the compiled copy and edits the wrong file.

✓.gitignore hygiene 3/3

.gitignore covers 58 patterns.

✗File sizes fit in context 0/6

4 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.

chapter2/prompt-engineering/tau_bench/envs/retail/tasks_train.py — 461KB

chapter2/prompt-engineering/tau_bench/envs/retail/tasks.py — 175KB

chapter2/prompt-engineering/tau_bench/envs/retail/tasks_test.py — 166KB

✗Repository weight 0/5

About 796MB 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 bojieli/ai-agent-book

# AGENTS.md

《深入理解 AI Agent：设计原理与工程实践》（李博杰 著）开源主仓库：全书正文、编译版 PDF 与按章配套代码

## Setup

```
uv sync
```

## Commands

```
ruff check .   # lint
```

## Layout

- `chapter9/` 363 source files
- `chapter5/` 257 source files
- `chapter3/` 226 source files
- `chapter2/` 223 source files
- `chapter4/` 146 source files
- `chapter6/` 124 source files

## Conventions

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

## Gotchas

- `chapter2/prompt-engineering/tau_bench/envs/retail/tasks_train.py` is 461KB. It will not fit comfortably in context, so read it in parts.
- 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/bojieli/ai-agent-book.md

A draft gets the commands right and stops at the things only a maintainer knows. What a good Python 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/bojieli/ai-agent-book.svg)](https://agentreadme.com/bojieli/ai-agent-book)

Other Python repositories, marked

vinta/awesome-python 81 A- NousResearch/hermes-agent 84 A- TheAlgorithms/Python 89 A yt-dlp/yt-dlp 54 C+ microsoft/markitdown 48 C+ Significant-Gravitas/AutoGPT 65 B

All Python 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