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 skills/junliu1066/vibe-coding-kit/vibe-coding-architecturenpx 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.svg" alt="Measured on agentmods" 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 | $0.00193 | $0.03141 |
| Opus 5 | $0.00097 | $0.01571 |
| Sonnet 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 5d 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.
- 5d 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 (169 stars, last pushed 2mo ago), licensed MIT. It adds 193 tokens to every session and 3,141 once invoked, about $0.0010 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 skills, from other repositories
openspec-onboard
Guided onboarding for OpenSpec - walk through a complete workflow cycle with narration and real codebase work.
ss-learn
Capture a human-approved UI design lesson as a privacy-minimized local StyleSeed candidate, review it, and prepare an opt-in share package without transmitting project code, prompts, screenshots, or brand data. Use when a person asks StyleSeed to remember, learn from, generalize, review, or prepare a reusable rule…
agent-newbie-guide
Skill "agent-newbie-guide" from hashgraph-online/awesome-codex-plugins, covering codex 新手引导, 🚫 新手术语过滤（绝对禁止）, 统一行为规范（内嵌）, 📍 阶段位置 and 启动自检.
agent-learning-coach
中文学习教练技能。用于学习编程、英语、设计、产品、AI、数学或任何技能时，先诊断水平，再用讲解、练习、反馈、复习的循环推进。触发语包括"进入学习模式""我想学""带我练""帮我制定学习计划""像教练一样教我"。.
memstack-marketing-webinar-script
Use this skill when the user says 'webinar script', 'webinar', 'live presentation', 'teach-to-sell', or needs a timestamped presentation script with slide notes, presenter cues, and replay email sequence. Do NOT use for launch plans or static sales page copy.
memstack-development-mentor
Use when the user says 'teach me', 'explain as you go', 'mentor mode', 'walk me through', 'help me learn', 'explain why', 'learning mode', or wants real-time plain language narration of decisions and tradeoffs while building. Do NOT use for code review or debugging.