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 oil-oil/vibe-hub-skill --skill vibehubgit clone --depth 1 https://github.com/oil-oil/vibe-hub-skillWrote 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/oil-oil/vibe-hub-skill/vibehub)<a href="https://agentmods.dev/skills/oil-oil/vibe-hub-skill/vibehub"><img src="https://agentmods.dev/badge/skills/oil-oil/vibe-hub-skill/vibehub/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/oil-oil/vibe-hub-skill/vibehub"><img src="https://agentmods.dev/badge/skills/oil-oil/vibe-hub-skill/vibehub.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00175 | $0.00971 |
| Opus 5 | $0.00088 | $0.00485 |
| Sonnet 5 | $0.00035 | $0.00194 |
| Haiku 4.5 | $0.00017 | $0.00097 |
Grade A, and why
vibehub 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 12d 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.
What it actually says
VibeHub
在不打断开发任务的前提下做两件事：
- 把模糊描述改成可以直接交给 Agent 的准确需求。
- 主动指出用户刚刚描述但没有说出名称的技术概念。
不要生成学习路线、课程、练习或术语清单。一个简单需求只提示最有帮助的术语。
每轮都检查
发送进度或完成结果前，检查用户本轮新增的话：
- 用户正在追加或修改代码，但用表象描述了某个效果：照常完成代码，并在结果里顺手点出术语。
- 用户准备把需求发给另一个 Agent：给出可直接复制的准确表达。
- 用户询问名称、含义或贴出 Agent 回复：解释最影响下一步判断的术语。
- 用户已经准确使用术语：正常处理任务，不重复教学。
不要因为前几轮已经开始编程，就跳过本轮的术语检查。
完成开发任务时
先完成用户要求，再把最相关的一个术语自然写进进度或结果。第一次出现时使用解析器返回的 Markdown 内链，并用一句话说明它在当前场景中的含义。
例如：
已为下载按钮添加[文字提示（Tooltip）](https://vibe-hub.org/tooltip)：悬停或键盘聚焦时显示“下载”。
不要单独开课，不要为了凑数量追加 Hover、Icon 等次要术语。
规范表达
先写用户可以直接使用的结果，再按需补充术语：
可以直接这样对 Agent 说：
“<保持原意、可直接复制的自然表达>”
术语提示：
- <术语>：<一句通俗解释>
- 保留原意、语气和约束，不擅自增加框架、组件库、参数或实现方案。
- 优先写可观察的行为和结果；只有用户正在讨论实现时才补实现细节。
- 最多提示 1–3 个真正影响沟通的术语。
- 推荐替代控件或方案时说明适用前提。
一次查询候选
先根据上下文推断 1–3 个稳定术语，再用一个命令批量验证：
node "<skill-root>/scripts/vibehub.mjs" resolve \
--query "<候选术语 1>" \
--query "<候选术语 2>" \
--compact
- 高置信度时只传一个候选；存在歧义时才增加候选，最多三个。
- 不要把用户整句原话直接当作搜索词。
- 比较标题、别名、定义和匹配字段，只采用真正符合当前场景的结果。
--compact足以确认时直接完成回答；只有摘要无法判断边界时，才对最终候选去掉--compact再查一次。- 只使用解析器返回的
url，不要自行拼接或伪造链接。 - 没有可靠匹配时，仍先完成当前任务；只有用户明确索要词条时才说明暂无页面。
查询只传脱敏后的短术语，不传源代码、密钥、客户信息、内部网址、邮箱、本地路径或项目材料。
表达原则
- 先交付任务结果，再补术语。
- 使用自然、通俗的中文或英文。
- 一个判断只说一次。
- 术语用于帮助下一次表达，不用于展示专业感。
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 12d ago First seen · 82 lines · 175 tokens per session scan A 51587bb75722
vibehub is a skill published in the GitHub repository oil-oil/vibe-hub-skill (172 stars, last pushed 2d ago), licensed MIT. It adds 175 tokens to every session and 971 once invoked, about $0.0009 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
context7-docs
Fetch up-to-date documentation and code examples for any library, framework, SDK, CLI tool, or cloud service. Use whenever the user asks about a specific library — even well-known ones like React, Next.js, Prisma, Express, Tailwind, Django, or Spring Boot — because training data may not reflect recent API changes or…
frontend-design-saas
S-tier SaaS dashboard and product UI reference. Use this skill when building application shells, data tables, settings panels, billing pages, dashboards, auth flows, admin tools, or any internal/customer-facing SaaS product UI. Inspired by Stripe, Linear, Vercel, Airbnb, Notion. Covers neutral-led design tokens…
design-review
Designer's eye QA: finds visual inconsistency, spacing issues, hierarchy problems, AI slop patterns, and slow interactions — then fixes them. Iteratively fixes issues in source code, committing each fix atomically and re-verifying with before/after screenshots. For plan-mode design review (before implementation), use…
miniapp-dev
A development guide for BitFun MiniApps, which are small applications that run inside BitFun. It covers creating new MiniApps as well as maintaining the MiniApp framework.
moai-design-tools
Design tool integration specialist covering Figma MCP, Pencil renderer, and Pencil-to-code export. Use when fetching design context from Figma, rendering Pencil designs, or exporting to React/Tailwind code.
paper-explainer
A research-content workflow that turns an arXiv paper or a local PDF into an explanation for a video or written article. arXiv is a public online archive of research papers.