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/aziontech/webkit/webkit-impeccable-polishnpx skills add aziontech/webkit --skill webkit-impeccable-polishgit clone --depth 1 https://github.com/aziontech/webkitWrote 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/aziontech/webkit/webkit-impeccable-polish)<a href="https://agentmods.dev/skills/aziontech/webkit/webkit-impeccable-polish"><img src="https://agentmods.dev/badge/skills/aziontech/webkit/webkit-impeccable-polish.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 | $0.00104 | $0.01472 |
| Opus 5 | $0.00052 | $0.00736 |
| Sonnet 5 | $0.00021 | $0.00294 |
| Haiku 4.5 | $0.00010 | $0.00147 |
Grade A, and why
webkit-impeccable-polish 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 3d 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 — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill: webkit-impeccable-polish
Purpose
The last 10% that separates "functional" from "finished". This is a sign-off, not a rulebook: it
runs after /webkit-ux-heuristics, /webkit-baseline-ui, and /webkit-motion-polish, and checks the
things each of those touches but none guarantees end-to-end — a coherent scale across the whole
screen, every state accounted for, and optical balance. It names the axis and points at the skill
that owns the rule; it deliberately does not re-enumerate token sets (that is
/webkit-baseline-ui's job — restating them here would only let the two drift).
How to use
/webkit-impeccable-polish— hold UI work in this conversation to the checklist below./webkit-impeccable-polish <file>— review the file and report, per issue: the quoted line, why it falls short (one sentence), and the concrete fix.
The sign-off checklist
Each item is a cross-screen check. Where a token set or rule is involved, the owning skill is named — go there for the allowed values; here you only confirm the screen as a whole holds together.
- Typography hierarchy is coherent across the screen. No inverted or skipped levels; a heading is
never smaller than a label;
text-balanceon headings,text-prettyon body,tabular-numson aligned figures,truncate/line-clampin dense areas. Allowed token set:/webkit-baseline-ui. - Spacing rhythm is steady. One predictable step between related elements; consistent section
padding; related items grouped tighter than unrelated (proximity reads as grouping). Scale:
/webkit-baseline-ui. - State completeness — the part no single skill guarantees end-to-end:
- Every interactive element has hover, focus-visible, active, disabled (visible focus ring).
- Every async surface has loading, empty, error — cross-check
/webkit-ui-states. - Selected / current states are visible (not just inferable). This is the highest-value check here: a screen usually fails "finished" on a missing state, not on a wrong token.
- Shape & elevation are coherent per role. All cards share one radius, all inputs another;
elevation is monotonic with stacking (overlays sit above cards), not every surface floating.
Token roles:
/webkit-baseline-ui. - Optical balance & restraint. Shared edges and consistent optical centers; icons aligned to the
text baseline; one accent per view, the rest on surface/text/border tokens; no gradient/glow
unless requested; nothing that doesn't earn its place. Motion is smooth and reduced-motion-safe —
confirm via
/webkit-motion-polish. - Two themes hold. The screen reads correctly in light and dark without per-theme edits — confirm
via
/webkit-theming-dark-mode, and observe it for real with/webkit-ui-verify.
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.
- 3d ago First seen · 100 lines · 104 tokens per session scan A b1b28d08a0da
webkit-impeccable-polish is a skill published in the GitHub repository aziontech/webkit (2 stars, last pushed 6d ago), licensed MIT. It adds 104 tokens to every session and 1,472 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 2026-08-31.
Other skills, from other repositories
add-component
Add a SwiftUI component from ShipSwift. Use when the user says "add component", "add a view", "add X view", "I need a chart", "add animation", or wants a specific UI element.
better-design
Build, improve, and review production interfaces with the Better Design MCP. Use for frontend design, UI, UX, interactions, flows, forms, navigation, components, styling, design systems, accessibility, responsive layouts, motion, React Native, Expo, Shopify, Three.js, and product video work, especially when creating…
monorepo-management
Sets up or audits a monorepo workspace: tool selection, package naming, shared tooling, inter-package dependencies, selective CI, and versioning strategy. Invoked when the user asks to set up a monorepo, add a workspace, or manage multiple packages in a single repository.
design-component
Design a UI component spec to the house quality bar — anatomy, variants, sizes, the 8 states, token mapping, and accessibility. Use when the user wants to design or document a component (button, input, tabs, toast, combobox, date picker, modal, etc.) at the spec level before or alongside code. For generating framework…
design-code
Generate production-ready, accessible, token-driven component code for ANY framework — React+Tailwind, Next.js, SwiftUI, Vue, Svelte, Angular, Solid, Web Components/Lit, React Native, Flutter, Jetpack Compose, vanilla CSS, or CSS-in-JS. Use when the user wants working UI code for a component or screen in a specific…
releasing
Authoring a changeset, or cutting a release for @vuetify/v0 and the @paper/ design systems. Use when writing a .changeset/.md file, deciding what belongs in changelog copy, re-entering or exiting changesets pre/beta mode, or reviewing a Version Packages PR. Covers the changeset content contract, the two version…