Source Reading

What it does

When your agent uses it

• Writing & Content work in your project

Example prompts

• “/source-reading”

Requirements

• Python 3

Workflow steps

8 steps, taken from the first numbered list in SKILL.md.

1. 1每一处引用、每一个行号、每一个类型名与函数名，动笔前用读文件工具实读核实。 禁止凭印象、禁止根据文件名推测、禁止照抄大纲里的候选行号
2. 2代码块与源文件逐字节一致。 保留原始缩进、属性宏、注释、空行。禁止转译、禁止美化、禁止写「示意代码」
3. 3中间跳过内容必须显式写省略标记（含 ... 的整行注释）。静默删行会被校验器抓成 FABRICATION
4. 4找不到某个机制的实现，写明 未找到对应实现，检索关键词为 X、Y、Z。不许编一个看起来合理的
5. 5由推断得出的结论显式标注为推断
6. 6引用注释时说明这是注释，不要当成代码行为陈述
7. 7数字（行数、文件数、变体个数）必须统计过，统一用 splitlines() 口径
8. 8引用符号链接时引真实文件，并注明链接关系

What it can do on your machine

Read from SKILL.md and the folder at commit f45f579. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  Ships script files (Python, from the files we listed), which the agent can run.

  Shell commands in SKILL.md call:

  • python3
  • git
  • pip

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  No URLs in SKILL.md. Its commands use git and pip, which can reach the network depending on how they are called.

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names no API keys, tokens, secrets or passwords.

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Source Reading loads about 1.2k tokens when it runs. Until then it costs about 80 tokens; SKILL.md has 196 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~80

When it runs · the whole SKILL.md, loaded when a task matches

~1.2k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from itshen/source-reading-methodology at commit f45f579, republished under its MIT licence (© itshen). 196 words, ~1,214 tokens.

name

source-reading

description

带 AI 精读大型开源仓库，产出每句话都能回溯到源码具体行的书稿、课程或技术文档。核心是零幻觉：每一处引用逐字节核实、行号实读、静默删行由脚本抓出。覆盖锁版本锚点、写逐章大纲、八段结构写章节、编成带封面封底的 HTML 书、机器校验、并行子 Agent 生产六件事。当用户要读懂一个陌生的大型仓库、精读某个开源项目源码、把源码整理成一本书、整理成课程或系列文章、做源码解读、写架构分析、或者要派多个 Agent 并行写技术内容时使用。触发词：精读源码、读源码、源码解读、源码分析、拆解这个项目、这个仓库怎么读、把源码写成课、把源码写成书、写源码精读、架构分析、code walkthrough、带我读代码。

```153:160:core/src/session/turn.rs
pub(crate) async fn run_turn(
    sess: Arc<Session>,
    ...
) -> CodexResult<Option<String>> {
```

- [ ] 阶段一 语料准备：锁版本、备对比语料、建检索脚本
- [ ] 阶段二 大纲：立一个真问题 + 逐章源码锚点
- [ ] 阶段三 章节书稿：八段结构，每处论断带行号
- [ ] 阶段四 成书：编成带封面封底的 HTML 书
- [ ] 贯穿 机器校验（批量生产之前就要建好）

git -C <repo> tag course-anchor-$(date +%Y%m%d)
git -C <repo> rev-parse --short HEAD

pip install markdown
cp book/book.config.example.json book.config.json    # 填书名、作者、被读仓库与版本锚点
python3 book/build_book.py

python3 templates/style_scan.py path/to/chapters/

© itshen, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 46 other files (assets) in the repository root of itshen/source-reading-methodology.

• SKILL.md
• .gitignore
• AGENTS.md
• LICENSE
• METHODOLOGY.md
• PITFALLS.md
• README.md
• assets/group-qrcode.png
• assets/preview-cite.png
• assets/preview-colophon.png
• assets/preview-cover.png
• assets/qrcode.jpg
• assets/x-qrcode.png
• book/README.md
• book/book.config.example.json
• book/build_book.py
• book/shot_book.py
• book/theme/book.css
• … and 29 more

Open the folder on GitHubat commit f45f579