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-productionnpx skills add Junliu1066/vibe-coding-kit --skill vibe-coding-productiongit 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-production)<a href="https://agentmods.dev/skills/junliu1066/vibe-coding-kit/vibe-coding-production"><img src="https://agentmods.dev/badge/skills/junliu1066/vibe-coding-kit/vibe-coding-production.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 | $0.00161 | $0.02519 |
| Opus 5 | $0.00081 | $0.01260 |
| Sonnet 5 | $0.00032 | $0.00504 |
| Haiku 4.5 | $0.00016 | $0.00252 |
Grade A, and why
vibe-coding-production 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 4d 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 — 153 lines — stays where its author put it; the contents beside it link to each section on GitHub.
上线准备:从 demo 到正式系统
这是 vibe-coding-kit 里负责"上线"的 Skill。只想验证想法的人用不到它——决定把项目做成能长期运行、给别人用的正式系统时,再来。
前置:先用
vibe-coding-requirements说清需求、vibe-coding-architecture选好技术。开发全程配合vibe-coding-survival避坑。
每个环节都配了直接发给 AI 的话术和你用来验收的标准——你不需要会写代码,只需会问、会检查。
准入检查(开始本阶段前必做)
本 skill 是流程第三阶段 S3·上线准备。开始前:
- 读
docs/进度账本.md。 确认 S2 架构选型出口门已过(技术栈已选定),且用户明确确认"要做成正式系统、给别人用"。只想跑 demo 的人不进 S3。 - 任一条不满足就别开始:需求/选型没定完,先回 S1/S2;用户只想验证想法,就停在 demo,别硬上线。
- 本阶段步骤对应账本:S3.1 开发规范 → S3.2 安全基线 → S3.3 部署 → S3.4 测试验收 →(
可选)S3.5 文档。每过一步回写账本。
一、开发规范(对应 S3.1)
把下面四段整理成一份"规范说明",每次让 AI 写代码时贴上,确保风格一致、日后好维护。
1.1 Git 分支策略(最简版)
main 分支 ← 永远是能稳定部署的版本
└── dev 分支 ← 日常开发,AI 写的代码先合到这
└── feat/xxx 分支 ← 每个新功能开一个,做完合回 dev
"每次写新功能时,顺便告诉我:① 该建什么分支名 ② commit message 写什么。"
(完全不用 git 也没关系,但至少要做 vibe-coding-survival 里的"保住能用的版本"——那是 git 的朴素替代。)
1.2 日志规范
"所有关键操作必须打日志,格式统一为
[时间] [级别] [模块] 内容。级别分三级:INFO(正常流程)、WARN(异常但能自动恢复)、ERROR(需我人工处理)。至少记录:请求进入、鉴权结果、数据库操作、外部调用、返回结果。卡密、密码等敏感信息脱敏,只显示前 4 位和后 4 位,中间用 *** 代替。"
1.3 错误处理规范
"所有可能出错的地方都要显式处理。错误信息必须含三要素:① 哪里出错(模块/函数名)② 为什么出错(具体原因)③ 建议怎么解决。绝不要把错误悄悄吞掉(catch 了却什么都不做)。"
1.4 代码风格
"代码注释用中文。每个函数上方注释说明:这函数做什么、输入什么、输出什么。变量名和函数名用英文,但要见名知意。"
二、安全基线(对应 S3.2)
▸ 过门:8 条逐条确认(标"已做"或"不适用")→ 账本 S3.2 标 ✅。涉及钱/别人隐私的,触发 survival 红线、提示找真人。
逐条把要求提给 AI,再逐条确认它做没做到。
| # | 安全要求 | 对 AI 说的话 |
|---|---|---|
| 1 | 鉴权 | "所有接口都要验证身份,没通过的直接拒绝,返回 401。" |
| 2 | 防暴力破解 | "同一 IP 连续失败 N 次后,锁定 M 分钟。" |
| 3 | 输入校验 | "所有用户输入都要校验和清理,防止注入攻击。" |
| 4 | HTTPS | "生产环境必须用 HTTPS。" |
| 5 | 敏感信息保护 | "密钥、密码用环境变量或配置文件读取,绝不写死在代码里。" |
| 6 | 日志脱敏 | "敏感数据在日志里脱敏。" |
| 7 | 最小权限 | "数据库连接用最小必要权限,不要用 root。" |
| 8 | 错误信息 | "对外返回的错误信息不要暴露内部实现细节。" |
开源专属提醒: 把代码公开(push 到 GitHub 等)之前,务必再确认一遍:代码里、配置里、提交历史里,没有任何密钥、密码、token。一旦推到公开仓库,就当全世界都看到了——即使事后删除也来不及,必须立刻作废并更换那个密钥。最稳妥的做法是把密钥放进一个单独的配置文件,并让 AI 帮你把它加进
.gitignore(让 git 永远忽略它)。
注意红线: 涉及真实收付款、存别人的个人信息等,别独自硬上——见 vibe-coding-survival 的「红线」。
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.
- 4d ago First seen · 153 lines · 161 tokens per session scan A 57cb95a5d70f
vibe-coding-production is a skill published in the GitHub repository Junliu1066/vibe-coding-kit (169 stars, last pushed 2mo ago), licensed MIT. It adds 161 tokens to every session and 2,519 once invoked, about $0.0008 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
automation-flows
Use when building or fixing a no-code automation on n8n, Make, or Zapier — trigger to multi-app steps with data mapping, dedup, retries and an error path — or picking the platform by billing unit (task vs credit vs execution). NOT a typed API client in code (that is api-connector-builder), NOT a webhook receiver in…
ai-delivery-spec
Use for creating, changing, reviewing, reverse-engineering or accepting requirements, PRDs, prototypes, competitor material or existing systems, including any small UI, field, column, tab, dropdown or legacy-HTML change. Supports /ads, /dig, /prd and /proto intent shortcuts where the host routes them. Always invoke…
mvp-build-tickets
Generate implementation task tickets for a Web MVP. Use after AGENTS.md and agentdocs exist when the user needs small Codex-executable task files with required reading, scope, acceptance criteria, implementation plan, verification checks, risks, and done conditions.
mvp-agent-context
Generate Codex-first agent context files for a Web MVP. Use after the PRD and Technical Blueprint exist when the user needs AGENTS.md, REVIEW-CHECKLIST.md, and agentdocs for project brief, requirements, tech stack, page map, data model, build tasks, testing, and reusable prompts.
mvp-workflow
Orchestrate a Codex-first Web MVP planning workflow from rough idea to build-ready artifacts. Use when the user wants to turn an app idea into a structured MVP plan, PRD, technical blueprint, AGENTS.md context, and implementation tickets.
mvp-idea-brief
Create an Idea Brief for a Web MVP. Use when the user has a rough app idea and needs to clarify the target user, problem, current workaround, smallest useful outcome, platform choice, budget, and MVP exclusions before research or PRD work.