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 glebis/claude-skills --skill site-diagnosisgit clone --depth 1 https://github.com/glebis/claude-skillsWrote 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/glebis/claude-skills/site-diagnosis)<a href="https://agentmods.dev/skills/glebis/claude-skills/site-diagnosis"><img src="https://agentmods.dev/badge/skills/glebis/claude-skills/site-diagnosis/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/glebis/claude-skills/site-diagnosis"><img src="https://agentmods.dev/badge/skills/glebis/claude-skills/site-diagnosis.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium analysis-evasion · line 1 Suspicious Unicode normalization or mixed-script contentFix: Review the flagged content for security risks. Ensure no credentials, secrets, or sensitive data are exposed.
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 | $0.00109 | $0.02399 |
| Opus 5 | $0.00055 | $0.01200 |
| Sonnet 5 | $0.00022 | $0.00480 |
| Haiku 4.5 | $0.00011 | $0.00240 |
Grade A, and why
site-diagnosis 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 8d 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 — 207 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Site Diagnosis — Pre-Consultation Questionnaire
You are conducting a structured diagnostic interview to prepare for a website consultation. The client is building (or has built) a website using AI coding tools and has concerns about the result. Your job is to collect enough context so the consultant can prepare effectively.
How This Works
Walk the client through 5 rounds of questions using AskUserQuestion. Round 0 picks the language; Rounds 1–4 cover the diagnostic themes. After all rounds, generate a structured consultation brief in markdown.
Keep the tone professional but warm — these are people who may feel anxious about their project going sideways.
If the client picks "Other" on any question, their free-text answer is often the most valuable signal — capture it verbatim in the summary.
Round 0: Language
Ask this question alone, before anything else:
Question 0 — "Language / Язык"
- header: "Язык"
- question: "На каком языке вам удобнее проходить анкету? / Which language do you prefer?"
- options:
- "Русский" — Russian
- "English" — English
- multiSelect: false
Store the chosen language. All subsequent questions, option labels, and the final consultation brief must be presented in this language. The skill body below shows Russian text with English annotations — if the client chose English, translate the user-facing strings (questions, option labels) to English. The structural format and field names in the output brief stay in English regardless.
Round 1: Project & Background
Ask these 3 questions together:
Question 1 — "Что вы делаете?"
- header: "Проект"
- question: "Какой сайт вы делаете или уже сделали?"
- options:
- "Лендинг / одностраничник" — single page, usually for a product or service launch
- "Сайт-визитка / портфолио" — personal or business card site, portfolio
- "Интернет-магазин" — e-commerce with catalog and payments
- "Блог / контентный сайт" — content-driven, articles, media
- multiSelect: false
Question 2 — "Ваш технический уровень"
- header: "Опыт"
- question: "Как бы вы описали свой технический уровень?"
- options:
- "Полный ноль — до ИИ не писал(а) код" — no prior coding experience
- "Базовый — могу поправить HTML/CSS" — can do basic edits
- "Средний — понимаю фреймворки, могу разобраться" — comfortable with frameworks
- "Продвинутый — программирую профессионально" — professional developer
- multiSelect: false
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.
- 8d ago First seen · 207 lines · 109 tokens per session scan A b4c31278c08d
site-diagnosis is a skill published in the GitHub repository glebis/claude-skills (375 stars, last pushed 9d ago), licensed MIT. It adds 109 tokens to every session and 2,399 once invoked, about $0.0005 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 2026-09-03.
Other skills, from other repositories
visual-ralph
Visual Ralph orchestration for frontend UI from generated references, static references, or live URL targets, using $ultragoal with built-in visual verdict and pixel-diff evidence until the implementation matches and leaves a reproducible design system.
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
repro-admin
Reproduce an EmDash admin UI bug. Attach a container, start the demo dev server, drive the admin with agent-browser using the dev-bypass session, and capture the reproduction as screenshots plus a replayable transcript.
create-site
Creates a new Power Pages code site (SPA) using React, Angular, Vue, or Astro. Guides through the full process from initial concept to deployed site: requirements discovery, scaffolding, component planning, design, implementation, validation, and deployment. Use when the user wants to create, build, or scaffold a new…
prototype-web
A clickable, high-fidelity web product prototype with navigation, a hero section, feature cards, steps, social proof, and optional pricing. It is designed to resemble a finished landing page while remaining a prototype.
menu-transitions-rtl
Animate react-horizontal-scrolling-menu scrolling and build right-to-left menus: noPolyfill defaults to true since v8, so transitionDuration (default 500), a custom-easing-function transitionBehavior, and per-call ScrollOptions { duration, boundary } on scrollToItem/scrollNext/scrollPrev are silently ignored unless…