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/mrhinkle/vibecoding-a-website/site-interviewernpx skills add mrhinkle/VibeCoding-a-Website --skill site-interviewergit clone --depth 1 https://github.com/mrhinkle/VibeCoding-a-WebsiteWrote 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/mrhinkle/vibecoding-a-website/site-interviewer)<a href="https://agentmods.dev/skills/mrhinkle/vibecoding-a-website/site-interviewer"><img src="https://agentmods.dev/badge/skills/mrhinkle/vibecoding-a-website/site-interviewer.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 | $0.00029 | $0.02935 |
| Opus 5 | $0.00015 | $0.01468 |
| Sonnet 5 | $0.00006 | $0.00587 |
| Haiku 4.5 | $0.00003 | $0.00294 |
Grade A, and why
site-interviewer 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 — 234 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Site Interviewer Skill
This skill conducts a friendly, conversational interview with business professionals to gather everything needed to build their website. The interview is non-technical, organized, and produces a site-brief.json file that all other VibeCoding skills consume.
How This Works
Instead of asking users to fill out a form, this skill has a natural conversation. You'll ask about their business, goals, brand, and technical needs—but in a way that feels like talking to a strategic partner, not a bot.
Interview Sections (in order)
- Business Essentials — Business name, industry, mission
- Audience & Market — Target audience, competitors, unique value
- Website Pages — What pages they need and why
- Brand Identity — Colors, fonts, logo, tone/mood
- Features & Functionality — Contact forms, newsletters, analytics, etc.
- Content Strategy — Key messages, CTAs, testimonials
- SEO & Discovery — Keywords, location, meta descriptions
- Technical & Deployment — Domain, GitHub repo, hosting preference
Each section has 3-5 conversational questions. You guide the user through naturally, building on previous answers.
Interview Flow
How to Conduct This Interview
Opening:
- Greet the user warmly
- Explain what you're doing: "I'm going to ask you some questions about your business and what you need from your website. This should take about 30 minutes and feels more like a conversation than a form."
- Confirm they have time and are ready
Asking Questions:
- Ask one question at a time
- Listen to their answer fully
- Ask clarifying follow-ups if needed (don't feel constrained to the script)
- Use their language and examples to show you're paying attention
- Build momentum—each answer informs the next question
Taking Notes:
- Internally, map their answers to the
site-brief.jsonschema - If they give vague answers ("it should look modern"), ask for specifics ("what does modern mean to you—minimalist and clean, or bold with lots of color?")
- If they contradict themselves, gently clarify: "Earlier you said X, and now you're saying Y—which one feels right?"
What ships with it
1 file 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.
- 4d ago First seen · 234 lines · 29 tokens per session scan A 5af287961172
site-interviewer is a skill published in the GitHub repository mrhinkle/VibeCoding-a-Website (11 stars, last pushed 4mo ago), licensed MIT. It adds 29 tokens to every session and 2,935 once invoked, about $0.0001 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
brainstorming
You MUST use this before any creative work (features, products, content, strategy, systems, or behavior changes). Start by classifying what we’re brainstorming, then run thorough one-question-at-a-time discovery, propose 2–3 approaches, and converge on a validated plan/spec.
idea-to-mvp
Take a rough idea from the user (a few lines of text), summarize it, then act as a domain-expert product manager to interactively refine it into a full requirement document and MVP plan. Use when someone says "I have an idea", "help me build X", "turn this into a product", "what would the MVP look like", or provides a…
bilibili_search
Search for videos on Bilibili using keyword queries generated from user interests.
gsd:new-project
Initialize a new project with deep context gathering and PROJECT.md. Creates project structure, requirements, roadmap, and state.
gsd-roadmapper
Creates project roadmaps with phase breakdown, requirement mapping, success criteria derivation, and coverage validation. Spawned by /gsd:new-project orchestrator.
tao-list-capabilities
Answer what the TAO Skill Bank plugin can do by generating the response from packaged application, data, model, AutoML, and platform manifests. Use when the user asks "what can TAO Skill Bank do", "list TAO models", "which TAO workflows are available", or "what supports AutoML".