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 skills add Junliu1066/vibe-coding-kit --skill vibe-coding-architecturegit clone --depth 1 https://github.com/Junliu1066/vibe-coding-kitWrote 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/skills/junliu1066/vibe-coding-kit/vibe-coding-architecture)<a href="https://agentmods.dev/skills/junliu1066/vibe-coding-kit/vibe-coding-architecture"><img src="https://agentmods.dev/badge/skills/junliu1066/vibe-coding-kit/vibe-coding-architecture/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/skills/junliu1066/vibe-coding-kit/vibe-coding-architecture"><img src="https://agentmods.dev/badge/skills/junliu1066/vibe-coding-kit/vibe-coding-architecture.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 | $0.00193 | $0.03141 |
| Opus 5.5 | $0.00077 | $0.01256 |
| Sonnet 5.5 | $0.00039 | $0.00628 |
| Haiku 4.5 | $0.00019 | $0.00314 |
Grade A, and why
vibe-coding-architecture 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 1mo 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 — 161 lines — stays where its author put it; the contents beside it link to each section on GitHub.
架构选型：从看不懂，到自己会判断
这是 vibe-coding-kit 里负责"让你成长"的 Skill。目标不是教你写代码，而是给你一套看懂任何技术方案、拷问任何选型的框架。用得越多，你越不需要照搬话术——因为你已经懂了。
前一步是
vibe-coding-requirements（把需求说清）。选完技术后，去vibe-coding-production处理上线。开发全程配合vibe-coding-survival避坑。
给使用者的话
技术上的事，你不需要会写，但要逐步学会看懂和判断。一开始你靠下面的话术问 AI，几个项目之后，你会发现自己已经能直接看穿方案好坏——那就是这个 Skill 想把你带到的地方。
准入检查（开始本阶段前必做）
本 skill 是流程第二阶段 S2·架构选型。开始前：
- 读
docs/进度账本.md。 确认 S1 需求对齐的出口门已过（prd.md / 需求基准描述齐了）。没过就别开始选型——需求没定，方案必然脱离现实；先回vibe-coding-prd或vibe-coding-requirements补完 S1。 - 向用户报一句："需求已就绪，进入 S2 架构选型。"
- 本阶段三步对应账本：S2.1 六维度拷问 → S2.2 五步选型 → S2.3 项目结构（
可选）。每过一步回写账本。
一、架构素养速成：看懂任何方案的 6 个维度 ★（对应 S2.1）
所谓"看懂架构"，本质上就是看懂下面这 6 个维度。 AI 给你的任何方案，都可以拿这 6 条逐条拷问——拷问得多了，你就成行家了。
| 维度 | 大白话是什么 | 它决定你该问什么 |
|---|---|---|
| 1. 数据存哪、留不留得住 | 数据是写进硬盘/数据库（关机还在），还是只在内存里（关机就没）？ | "关机重开后数据还在吗？存在哪？" 这是 demo 和正式系统最大的分水岭。 |
| 2. 在谁的机器上跑 | 跑在你自己电脑上，还是一台一直开着的服务器上？要联网才能用，还是离线也行？ | "这东西要一直开机才能用吗？谁来开着它？没网能用吗？" |
| 3. 一坨还是拆开 | 整个程序是一个进程（单体），还是拆成好几个服务各跑各的（拆分/微服务）？ | "能不能一个进程就跑起来？" 对个人维护者，一坨通常远好过拆开——拆开是给大团队准备的负债。 |
| 4. 依赖了多少外部东西 | 这方案站在多少"别人造的东西"上：第三方库、外部 API、云服务？ | "它依赖哪些外部东西？哪个挂了我就跟着挂？少装点行不行？" 每个依赖都是未来可能坏掉、可能收费的点。 |
| 5. 即时还是排队 | 用户一点就要马上出结果（同步），还是可以先收下、后台慢慢处理（异步/队列）？ | "如果某一步很慢，会不会卡住整个系统？慢操作能不能放后台？" 简单场景别提前上队列。 |
| 6. 多少人用才扛不住 | 现在的方案，1 个人用没问题，那 100 个、10000 个同时用呢？ | "大概多少人同时用会扛不住？" 但新手最常见的错是过度担心这个——先按真实人数设计，扛不住了再升级，别为想象中的百万用户提前把方案搞复杂。 |
怎么用： 让 AI 列方案后，对每个方案用这 6 个维度问一遍，尤其第 1、3、4 条——这是个人项目最容易出事的地方。能把这 6 条问顺，你就有了基本的架构判断力。
隐藏好处：看懂架构，你能更准地判断"这件事我到底能不能自己搞定"——包括什么时候该收手找真人工程师（见
vibe-coding-survival的「红线」）。会判断边界，也是行家的一部分。
二、把 AI 当老师：边做边学
你身边坐着一个不嫌烦、随叫随到的技术老师。别只让它干活，要让它教你。每个项目都这么做，几个项目下来你就脱胎换骨：
- 要大白话解释："用一个生活里的例子解释这个方案，假设我完全不懂技术。"
- 逼它讲取舍："为什么选这个方案，不选另一个？它好在哪、差在哪？"——行家和小白的区别，就在于懂不懂"为什么"。
- 攒自己的词汇表： 遇到不懂的词，让 AI 一句话解释，记进项目说明书。同一个词见三次，你就记住了。
- 项目结束做复盘："把这个项目我们做的架构决定和原因列一遍，我想记住这套思路，下次自己也能判断。"
三、技术选型五步决策法（对应 S2.2）
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.
- 1mo ago First seen · 161 lines · 193 tokens per session scan A d7e837f3a044
vibe-coding-architecture is a skill published in the GitHub repository Junliu1066/vibe-coding-kit (99 stars, last pushed 3mo ago), licensed MIT. It adds 193 tokens to every session and 3,141 once invoked, about $0.0008 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.
Other skills, from other repositories
meta-prompt
Meta-prompting framework for critiquing responses, analyzing solution trajectories, and evaluating AI-generated content quality.
anthropic-skilljar-extractor
Extracts any Anthropic Academy (Skilljar) course into a structured markdown folder. Triggers when the user provides an anthropic.skilljar.com URL and asks to extract, research, download, or convert a course to markdown. Produces one markdown file per lesson organized into section folders, with course diagrams…
react-senior-interview
Interactive 10-question multiple-choice React interview, by theSeniorDev — drawn from the same principles as react-senior-code-review. Asks which level you're interviewing for (junior/mid/senior) and shifts difficulty to match. Per-question feedback. Final score with a breakdown by dimension and personalized study…
baoyu-comic
A tool for creating original educational comics that explain knowledge or ideas through multiple illustrated panels. It supports different art styles and tones and can create several comics in one batch.
skill-creation-walkthrough
Step-by-step guide for creating your own Claude Skills, from deciding whether a skill is the right tool to writing the SKILL.md file, structuring reference material, and making it trigger reliably. Use when you want to package a workflow, framework, or repeated task into a reusable Skill, when an existing skill is not…
elixir-idioms
OTP/BEAM patterns and Elixir idioms — GenServer, Supervisor, Task, Registry, pattern matching, with chains, pipes. Use when designing processes or debugging BEAM issues.