Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add instructions/itshen/source-reading-methodology/agents-mdgit clone --depth 1 https://github.com/itshen/source-reading-methodologyWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00539 | $0.00539 |
| Opus 5 | $0.00269 | $0.00269 |
| Sonnet 5 | $0.00108 | $0.00108 |
| Haiku 4.5 | $0.00054 | $0.00054 |
Grade A, and why
source-reading-methodology AGENTS.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
给 AI 的入口
这个仓库是一套源码精读方法论：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。
要用这套方法论干活
动手之前先完整读 SKILL.md。 它是唯一入口，一份文件讲完整套流程：四阶段工作流、零幻觉铁律、引用格式、文风约束、机器校验、并行生产。需要细节时再去读 templates/、PITFALLS.md 和 book/README.md，不要凭印象补。
一条不可妥协：每一个技术论断都可回溯到源码的具体行。 代码块必须与源文件逐字节一致，行号动笔前用读文件工具实读核实，中间跳过内容要写显式省略标记，查不到就写明「未找到对应实现，检索关键词为 X、Y」。编一个看起来合理的，整份产出的可信度就是零。
接到任务先问清产出形态和规模再动手。读懂一个模块、写一篇架构分析、做一门几十节的课，该走的阶段数完全不同，四阶段全流程很重，小任务不需要。
要改这个仓库本身
- 方法论正文改
METHODOLOGY.md，改完确认SKILL.md里的对应段落没跟它矛盾。两份都是入口，漂移了后来的人会按错的那份做 - 新踩的坑加进
PITFALLS.md，写清现象、原因、怎么防。不写抽象教训 - 动过
book/的主题或sample/chapters/，重建样张并确认产物正常：
python3 book/build_book.py --config sample/book.config.json # 产物在 docs/，提交后 Pages 自动发布
python3 book/shot_book.py docs -c ch-02.html # 截图校对，同时报告页面 JS 报错
- 面向读者的正文交付前跑
python3 templates/style_scan.py <路径>，句式禁忌必须清零。不要用同义替换绕过正则，禁的是那种表达方式，不是那几个字
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2d ago First seen · 25 lines · 539 tokens per session scan A 3ce4d045aaa2
source-reading-methodology AGENTS.md is an instructions file published in the GitHub repository itshen/source-reading-methodology (127 stars, last pushed 8d ago), licensed MIT. It adds 539 tokens to every session, about $0.0027 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
docs-mcp CLAUDE.md
Claude Code instructions for base-kit/docs-mcp, covering docs-mcp 工具开发规范, 项目定位与架构, 开发规范, 索引构建与维护 and 重 build 索引.
codetape AGENTS.md
AGENTS.md instructions for 888wing/codetape, covering codetape — agent instructions, for ai coding agents, available commands, data directory and behavior guidelines.
liam AGENTS.md
Instructions for liam-hq/liam, covering repository guidelines, project structure & modules, build, test, and development, coding style & naming and testing guidelines.
project-os-for-codex AGENTS.md
Instructions for herry2059/project-os-for-codex, covering ai contributor rules, product truth, architecture and security, development workflow and agent integration contract.
living-manual CLAUDE.md
Instructions for dougstanford/living-manual, covering living-manual, start of every session, how work lands — non-negotiable, user's manual (living-manual) and releasing.
AmbyKit CLAUDE.md
Instructions for ambystechcom/AmbyKit, covering claude code — notes for the ambykit repo and claude-specific.