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/awesome-embedded-learning-studio/tutorial_awesomemoderncpp/claude-mdgit clone --depth 1 https://github.com/Awesome-Embedded-Learning-Studio/Tutorial_AwesomeModernCPPWhat 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 | $0.01047 | $0.01047 |
| Opus 5 | $0.00524 | $0.00524 |
| Sonnet 5 | $0.00209 | $0.00209 |
| Haiku 4.5 | $0.00105 | $0.00105 |
Grade A, and why
Tutorial_AwesomeModernCPP CLAUDE.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 3d 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.
How it starts
The opening of the file, as written. The whole thing — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
Claude Code 在本项目的专属补充。通用项目信息(架构 / 命令 / 校验 / 金科玉律)见 AGENTS.md —— 先读它。本文件只放 Claude 特有的。
写作纪律(必须遵守)
- 写作前 MUST 先查 .claude/style/writing-style.md(人格、语气、文章骨架、代码风格)
- 写作前 MUST 先 web search,准确性优先,token 成本其次
- 完成后 MUST 自查,而非留给作者;自查后告知如何验证
- 完成一个文件夹下的文章,MUST 顺手建
index.md,确保每篇都能被 VitePress 访问 - 计划模式用中文写计划文件
- 审查文章准确性,用 .claude/prompts/ 下的 prompt:
article-factcheck-audit.md—— 事实准确性 + 引用验证(人名 / 日期 / 规格 / 代码行为)article-rigor-audit.md—— 编译器行为 + 技术断言验证(强制编译 / 汇编佐证)
规划命令(skills,规划者模式 —— 只规划不执行)
确认讨论后产出【总结 + 迭代 Issue】到聊天框,套本地 .claude/templates/iteration-issue.md。不调 gh、不开 issue。
实用命令(skills,执行型)
/audit—— 对一篇文章跑事实 + 严谨双审查并修正/verify-claim—— 编译最小例子 + 查 cppreference,验证一条 C++ 断言/explain—— 给学习者讲一个概念(定位 → 验证 → 项目声音讲解)/new-article—— 按骨架起一篇新文章/preflight—— 提交前自检(frontmatter / lint / 链接 / 索引)
记忆系统
Claude Code 有持久记忆(跨会话保留用户偏好、项目进展、踩坑),由 MEMORY.md 索引;具体存储位置在本地 Claude 配置,因人而异。
添加贡献者
用户说"添加贡献者"时:① 问 GitHub URL + 贡献内容 + 是否匿名;② 同步更新 CONTRIBUTORS.md + documents/team/index.md + documents/en/team/index.md;③ 卡片格式(<a class="contributor-card">)参照 documents/team/index.md 现有条目。
配置
- .claude/settings.json —— 权限 allowlist + PreToolUse hook
- .claude/hooks/block-bare-python.sh —— 强制
.venv/bin/python .claude/settings.local.json—— 本地覆盖(不入库)
参考文件索引
| 文件 | 用途 |
|---|---|
| AGENTS.md | 跨 agent 通用入口(架构 / 命令 / 金科玉律) |
| .claude/style/writing-style.md | 写作人格 / 语气 / 骨架 / 代码风格 |
| .claude/rules/documents-frontmatter.md | Frontmatter 字段与标签 |
| .claude/commands/ | /patch /minor 规划 skills |
| .claude/prompts/ | 文章审查 prompt(事实 / 严谨) |
| CONTRIBUTING.md | 贡献流程一条龙 |
site/.vitepress/config/ |
VitePress 配置(nav / sidebar / theme) |
scripts/build.ts |
分卷并行构建 |
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.
- 3d ago First seen · 57 lines · 1,047 tokens per session scan A 5844aed20b36
Tutorial_AwesomeModernCPP CLAUDE.md is an instructions file published in the GitHub repository Awesome-Embedded-Learning-Studio/Tutorial_AwesomeModernCPP (250 stars, last pushed 3d ago), licensed MIT. It adds 1,047 tokens to every session, about $0.0052 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
nim_duilib CLAUDE.md
Instructions for rhett-lee/nim_duilib, covering nimduilib - 跨平台 c++ ui 库, 项目概述, 项目结构, 开发模式（xml + c++） and xml 布局文件.
cpp-lectures-mcp CLAUDE.md
Claude Code instructions for Alexvozhak/cpp-lectures-mcp, covering cpp-lectures-mcp, старт сессии, распределение ответственности по докам, рабочий цикл (кратко; полно — в skill.md) and инструменты (зафиксировано планом).
ai-for-modern-cpp AGENTS.md
AGENTS.md instructions for thecompez/ai-for-modern-cpp, covering agents.md, modern c++ agent knowledge contract, 1. normative language and authority, 2. repository knowledge model and project initiation gate.
ai-for-modern-cpp CLAUDE.md
Claude Code instructions for thecompez/ai-for-modern-cpp, a project described as: A template repository for guiding AI coding agents to write safe, modern C++20/23/26 code using modules, concepts, modern CMake, Core Guidelines, tests, and repeatable build-test-review loops.
SQLiteCpp copilot-instructions.md
Instructions for SRombauts/SQLiteCpp, covering sqlitecpp llm coding guide, non-negotiables (must follow), workflow (common tasks), add a method and add a class.
qgroundcontrol mavlink-includes.instructions.md
When performing a code review on C++ headers, enforce the MAVLink lightweight include hierarchy to keep moc parse times fast.