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 marcoguillermaz/Tierward --skill ui-auditgit clone --depth 1 https://github.com/marcoguillermaz/TierwardWrote 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/marcoguillermaz/tierward/ui-audit)<a href="https://agentmods.dev/skills/marcoguillermaz/tierward/ui-audit"><img src="https://agentmods.dev/badge/skills/marcoguillermaz/tierward/ui-audit/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/marcoguillermaz/tierward/ui-audit"><img src="https://agentmods.dev/badge/skills/marcoguillermaz/tierward/ui-audit.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 | $0.00035 | $0.03243 |
| Opus 5 | $0.00017 | $0.01622 |
| Sonnet 5 | $0.00007 | $0.00649 |
| Haiku 4.5 | $0.00003 | $0.00324 |
Grade A, and why
ui-audit 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 10d 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 — 241 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Configuration (fill in before first run)
Replace these placeholders:
[SITEMAP_OR_ROUTE_LIST]- e.g.docs/sitemap.md,docs/routes.md,src/router/index.ts[APP_SOURCE_GLOB]- fallback if no sitemap:app/**/page.tsx,src/**/*.vue,templates/**/*.html[DYNAMIC_ROUTE_PATTERN]- pattern for dynamic route segments. Examples: Next.js/[id], SvelteKit/[id], Django<int:pk>, Rails:id, native: "detail view controllers"If
[SITEMAP_OR_ROUTE_LIST]is not filled, the skill reports an explicit error and exits. If filled but the file does not exist on disk, the skill falls back to[APP_SOURCE_GLOB].
Critical constraint: [SITEMAP_OR_ROUTE_LIST] is the authoritative inventory of every page file and key component. Read it first and derive the file target list from it. Do NOT run free-form grep -r across source directories - scope every check to the files listed in the sitemap.
Scope boundary: this skill covers design-token compliance and component adoption only. Accessibility (aria, tabindex, focus, labels, axe-core WCAG scan, APCA contrast) lives in /accessibility-audit - run it alongside /ui-audit for any UI change.
Static-only skill - no dev server required. Can run concurrently with browser-based skills per pipeline.md.
Step 0 - Target resolution
Parse $ARGUMENTS for a target: token.
| Pattern | Meaning |
|---|---|
target:section:<name> |
Restrict to routes whose path contains <name> |
| No target argument | Full audit - ALL routes in [SITEMAP_OR_ROUTE_LIST] |
STRICT PARSING - mandatory: derive target ONLY from the explicit text in $ARGUMENTS. Do NOT infer target from conversation context, recent work, active block names, or project memory. If $ARGUMENTS contains no target: token → full audit, all routes.
Target scoping - comparative vs independent checks (mandatory): some audit skills contain comparative checks that derive a project-wide convention by counting usage across the whole inventory - those must ignore the target: filter. This skill has none: every check flags matches against a fixed design-system rule, with no adoption-rate denominator or majority-usage count.
- Comparative checks - full-project by design; the
target:filter does NOT apply to them: none. No check derives its baseline by counting across the page inventory. - Independent checks - target-safe: all checks (CHECK 1-12, S1-S4) evaluate individual files in isolation and safely honor the
target:filter. - When a
target:is given: apply the filter to the page and component file list in Step 1 - with one input exception: S1 and S4 inspect shared layout/navigation files that render on every route, so keep those files in scope even when they fall outside the target path. This is an input-scoping detail, not a comparative baseline.
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.
- 10d ago First seen · 241 lines · 35 tokens per session scan A a9cb1c1f4dd1
ui-audit is a skill published in the GitHub repository marcoguillermaz/Tierward (4 stars, last pushed 3d ago), licensed MIT. It adds 35 tokens to every session and 3,243 once invoked, about $0.0002 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
frontend-taste
Premium frontend design skills that override LLM defaults. Prevents generic 'AI-looking' UI. Enforces deterministic typography, calibrated color, asymmetric layouts, spring physics, hardware-accelerated motion. Triggers: 'UI tasarla', 'design a UI', 'premium landing page', 'frontend taste', 'anti-slop', 'dashboard…
design-tokens
Project-level DESIGN.md tokens reference. When the project has a DESIGN.md file, agents producing UI / components / visuals must consult this skill to use canonical color/typography/spacing tokens rather than inventing new ones. Triggers on: UI generation, component creation, design brief, visual asset, tailwind…
design-taste-frontend
Anti-slop frontend skill for landing pages, portfolios, and redesigns. The agent reads the brief, infers the right design direction, and ships interfaces that do not look templated. Real design systems when applicable, audit-first on redesigns, strict pre-flight check.
design-taste-frontend-v1
The original v1 taste-skill, preserved for projects depending on its exact behavior. The current default is design-taste-frontend (v2 experimental), which is a substantial rewrite. Use this v1 install name only if you need exact backward compatibility.
high-end-visual-design
Teaches the AI to design like a high-end agency. Defines the exact fonts, spacing, shadows, card structures, and animations that make a website feel expensive. Blocks all the common defaults that make AI designs look cheap or generic.
gpt-taste
Elite UX/UI & Advanced GSAP Motion Engineer. Enforces Python-driven true randomization for layout variance, strict AIDA page structure, wide editorial typography (bans 6-line wraps), gapless bento grids, strict GSAP ScrollTriggers (pinning, stacking, scrubbing), inline micro-images, and massive section spacing.