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-ux-auditor/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-ux-auditor)<a href="https://agentmods.dev/skills/heidihelena/vahtian/vahtian-ux-auditor"><img src="https://agentmods.dev/badge/skills/heidihelena/vahtian/vahtian-ux-auditor/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-ux-auditor"><img src="https://agentmods.dev/badge/skills/heidihelena/vahtian/vahtian-ux-auditor.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 | $0.00113 | $0.00923 |
| Opus 5 | $0.00056 | $0.00462 |
| Sonnet 5 | $0.00023 | $0.00185 |
| Haiku 4.5 | $0.00011 | $0.00092 |
Grade A, and why
vahtian-ux-auditor 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 — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Vahtian UX auditor
Your job is to find the highest-impact comprehension and decision-path
problems on a Vahtian page — and only that. You diagnose; you don't implement
(that's vahtian-frontend-implementer) and you don't bless wording (that's
vahtian-brand-safety).
See the page before you judge it. Don't audit from HTML source. Render it:
node .claude/skills/run-vahtian/driver.mjs / # or any path
Then open .claude/skills/run-vahtian/shots/<slug>.desktop.png and
<slug>.mobile.png. A UX finding you can't point to in a screenshot isn't real.
The one rule
Every UX improvement must make the human decision path clearer. Polish is never the goal; comprehension is. No visual polish before message clarity.
The 10-second test — answer these from the first screen alone
A first-time researcher should be able to answer, without scrolling:
- What is this?
- Who is it for?
- What problem does it solve?
- What should I click first?
- Which product should I use?
- What does the agent do? What does the human decide?
- What is local / private? What is free? What is institutional?
For each: can they answer it in ≤10s? If not, that's a finding. Rank findings by how many researchers hit them × how badly it blocks the decision.
Review checklist
- Can a first-time researcher understand the site in 10 seconds?
- Is the first CTA obvious and singular (not three equal-weight buttons)?
- Is the product ladder scannable — uniform cards, one CTA each?
- Is the "Which Vahti should I use?" chooser visible and quick to parse?
- Is the agentic workflow credible and bounded (says what the agent may do and what only the human decides)?
- Are the safety invariants (local-first, human-first, audit trail, "does not decide truth") visible, not buried?
- Does the mobile layout work — readable line length, tap targets, no horizontal scroll, hero legible at 390px?
- Do the a11y semantics hold — heading order, descriptive links, buttons
distinguishable from body links? (Diagnose only; the fix-side rules live in
vahtian-frontend-implementer.) - Is the page still static, fast, and tracker-free?
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 · 84 lines · 113 tokens per session scan A c358f54aba1b
vahtian-ux-auditor is a skill published in the GitHub repository heidihelena/vahtian (1 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 113 tokens to every session and 923 once invoked, about $0.0006 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.
webgl-holographic-foil
A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
html-ppt-taste-brutalist
16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).
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.
accessibility
Consolidated accessibility skill entrypoint for WCAG 2.2, ARIA Authoring Practices, cognitive accessibility, Section 508, EN 301 549, design intent verification, and the Accessibility Planner workflow.