Vibe Coding is a Chinese-language guide to developing software through structured collaboration with AI, covering planning, architecture, implementation, debugging, and iteration. It is intended for developers who want to turn ideas into software while keeping AI-assisted work organized. The catalogue contains skills and an instruction related to this workflow.
Borrowing it
Nothing to install: this file belongs to 2025Emma/vibe-coding-cn. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/2025Emma/vibe-coding-cn/main/AGENTS.mdgit clone --depth 1 https://github.com/2025Emma/vibe-coding-cnWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/instructions/2025emma/vibe-coding-cn/agents-md)<a href="https://agentmods.dev/instructions/2025emma/vibe-coding-cn/agents-md"><img src="https://agentmods.dev/badge/instructions/2025emma/vibe-coding-cn/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/2025emma/vibe-coding-cn/agents-md"><img src="https://agentmods.dev/badge/instructions/2025emma/vibe-coding-cn/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What 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 5.1 | $0.03650 | $0.03650 |
| Opus 5.5 | $0.01460 | $0.01460 |
| Sonnet 5.5 | $0.00730 | $0.00730 |
| Haiku 4.5 | $0.00365 | $0.00365 |
Grade A, and why
vibe-coding-cn 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 2mo 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 — 196 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repository Guidelines
Project Structure & Module Organization
- 根目录：
README.md给出全貌，Makefile封装日常命令，CONTRIBUTING.md说明贡献流程，LICENSE载明协议。保持根目录扁平，避免巨石文件。 - 多语言 i18n：
i18n/<lang>/统一三层结构（documents / prompts / skills）。现有语言：中文zh、英文en、希伯来语he，以及高频/常用的es、hi、ar、pt、ru、fr、de、ja、ko、it、tr、nl、pl、id、vi、th、fa、uk、bn、ta、ur、ms、sw、ha；新增语言遵循同样层级。 - 文档库：
i18n/zh/documents/仍是默认中文方法论入口（如i18n/zh/documents/Templates and Resources/代码组织.md等），新增语言文档按需在对应documents/下创建并保持同步。 - 提示词资产：
i18n/zh/prompts/按角色拆分（system / assistant / coding / user），libs/external/prompts-library/提供 Excel ↔ Markdown 互转工具与脚本目录，便于批量维护提示词，适合作为“单一真实来源”。 - 代码与集成：
libs/预留核心实现骨架，common/、database/、external/分别对应通用模型、存储适配与外部依赖登记；新增模块需保持分层边界与单一职责，避免跨层调用。 - 备份：
backups/内含一键备份.sh与快速备份.py，用于本地快照或同步，请先在隔离目录试跑，确认输出路径与权限。
Build, Test, and Development Commands
make help：列出所有 Make 目标，是新人快速上手的入口。make lint：使用markdownlint-cli校验全仓库 Markdown，一旦新增文档请先跑通（需本地 Node/npm 环境，可用npm install -g markdownlint-cli安装）。make build/make test/make clean：目前为占位，落地具体实现后务必更新脚本和说明；建议在Makefile旁补充注释并保持幂等，避免修改全局状态。- 提示词转换：进入
libs/external/prompts-library/后执行python main.py按交互提示进行转换，运行前请确认虚拟环境、依赖与输出目录，并在完成后检查生成 Markdown 是否符合 lint 规则。
Coding Style & Naming Conventions
- 文字层：文档、注释、日志使用中文；代码符号（函数 / 变量 / 模块）统一英文且语义直白，避免晦涩缩写。
- 缩进与排版：全仓保持空格缩进（2 或 4 空格任选其一但不得混用）；Markdown 列表、代码块与表格对齐清晰，行宽控制在 120 列内。Git diff 可读性优先。
- 设计品味：优先消除分支与重复；函数力求单一职责且短小；命名遵循小写加中划线或下划线，不使用空格与特殊字符；跨模块接口保持稳定签名。
- 依赖管理：新增工具或库时记录安装方式、最小版本与来源，必要时在
i18n/zh/documents/Templates and Resources/工具集.md或 README 中补充，并说明为何需要它（性能、兼容、功能）。
Testing Guidelines
- 当前无实测用例；引入代码时请至少提供最小可复现测试。推荐 Python 使用
pytest，文件命名test_*.py，夹具精简可读，遵循 red-green-refactor 循环。 - 文档与提示词改动：提交前运行
make lint；如转换脚本涉及数据，附带示例输入 / 输出说明或最小数据样例，确保可重复。 - 覆盖率基线由模块维护者设定；若暂无标准，确保主流程和边界条件均可被测试验证，必要时在 PR 描述中写明未覆盖的风险，并建议后续补测计划。
Commit & Pull Request Guidelines
- Commit 建议遵循简化 Conventional Commits：
feat|fix|docs|chore|refactor|test: scope – summary，一句话说明行为与范围；避免笼统的 “update”。 - PR 必填：变更摘要、动机或关联 Issue、测试与验证步骤（列出运行的命令与结果概览）；涉及文档 / UI 的修改应附对比截图或链接，方便 reviewer 快速复核。
- 提交前清单：跑通
make lint；若新增脚本 / 依赖，更新对应文档与Makefile目标；确认不携带临时文件或机密数据，并在描述中注明潜在风险或需要 reviewer 特别关注的点。
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.
- 2mo ago First seen · 196 lines · 3,650 tokens per session scan A c0ddd70f3d9a
vibe-coding-cn AGENTS.md is an instructions file published in the GitHub repository 2025Emma/vibe-coding-cn (23,144 stars, last pushed 10mo ago), licensed MIT. It adds 3,650 tokens to every session, about $0.0146 per session on Opus 5.5. 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.
vibe-coding-cn AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| vibe-coding-cn AGENTS.md2025Emma/vibe-coding-cn | Instructions file | 23k | 10mo ago | MIT | A | 3,650 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | today | MIT | A | 7,461 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 5,516 | GitHub Copilot |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | today | MIT | A | 4,680 | Codex, OpenCode |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |