Borrowing it
Nothing to install: this file belongs to heidihelena/vahtian. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/heidihelena/vahtian/main/.claude/skills/vahtian-site/SKILL.mdgit clone --depth 1 https://github.com/heidihelena/vahtianWrote 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/heidihelena/vahtian/vahtian-site)<a href="https://agentmods.dev/skills/heidihelena/vahtian/vahtian-site"><img src="https://agentmods.dev/badge/skills/heidihelena/vahtian/vahtian-site/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/heidihelena/vahtian/vahtian-site"><img src="https://agentmods.dev/badge/skills/heidihelena/vahtian/vahtian-site.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00152 | $0.02524 |
| Opus 5 | $0.00076 | $0.01262 |
| Sonnet 5 | $0.00030 | $0.00505 |
| Haiku 4.5 | $0.00015 | $0.00252 |
Grade A, and why
vahtian-site 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.
How it starts
The opening of the file, as written. The whole thing — 152 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Vahtian site — professional build & maintenance standard
The site already passes Lighthouse ~100. This skill is about everything Lighthouse does not measure: consistency, accessibility depth, AI-citability, security, editorial integrity, and drift prevention on a hand-maintained, zero-build, static HTML/CSS/vanilla-JS site hosted on Cloudflare Workers.
The site's invariant comes first. Vahtian records whether a cited source
supports a specific claim and keeps an auditable record; it does not certify
scientific truth, quality, or correctness. Every page must be consistent with
this. When in doubt about copy, run vahtian-brand-safety before shipping.
The golden rule: no page ships alone
The #1 failure mode on this site is drift — a new page or tool ships missing
the meta set, with a slightly different footer, or absent from the sitemap; or a
noindex page lands in the sitemap. Treat every page as part of a system, not a
one-off. Before any new page or tool is "done", run the checklist in
references/new-page-checklist.md — it is the single source of truth.
Copy the <head> from references/head-template.html rather than hand-writing
meta tags. The strongest existing pages to mirror are citevahti/ and
studyvahti/.
What "professional" means here, by dimension
Each item is tagged [do] (adopt — high impact-to-effort for a solo maintainer) or [grows] (worth it as the site/team grows; don't over-engineer yet).
1. Consistency & drift prevention [do]
- Every page carries the full head set:
title,description,canonical, full Open Graph (og:type/url/title/description/image+image:width/height/altsite_name),twitter:card, a JSON-LD block,theme-color, and a brand favicon. See the template.
- Every footer is identical in shape:
© <year> Vahtian · <context> · source · Cite · Privacy(About where relevant), plus the one-line invariant disclaimer. - Every page is added to
sitemap.xmlunless it isnoindex. - Run the audit grep (checklist §Verify) after any structural change — it catches drift in seconds.
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 · 152 lines · 152 tokens per session scan A ff90f443eccf
vahtian-site is a skill published in the GitHub repository heidihelena/vahtian (1 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 152 tokens to every session and 2,524 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 2026-08-31.
Other skills, from other repositories
link-evidence
Prevents fabricated URLs. Only use links that appear in the sources pool or are provided by the user.
zotero-plugin-toolkit
API reference for zotero-plugin-toolkit (v5.x). Covers UITool element creation, KeyboardManager, PromptManager (command palette), DialogHelper, SettingsDialogHelper, ProgressWindowHelper, FilePickerHelper, ClipboardHelper, ReaderTool, ExtraFieldTool, FieldHookManager, PatchHelper, LargePrefHelper…
zotero-plugin-dialogs
Create dialogs, menus, and preference panes in a Zotero 7+ plugin. Covers XHTML dialog structure, script loading, opening dialogs with window.openDialog(), chrome vs. rootURI URL patterns, dialog script patterns, XUL menu injection, and the preferences pane format. Use when adding UI to a Zotero plugin.
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.