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 TheGoat395/Codex-Skills --skill visual-polish-qagit clone --depth 1 https://github.com/TheGoat395/Codex-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/thegoat395/codex-skills/visual-polish-qa)<a href="https://agentmods.dev/skills/thegoat395/codex-skills/visual-polish-qa"><img src="https://agentmods.dev/badge/skills/thegoat395/codex-skills/visual-polish-qa/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/thegoat395/codex-skills/visual-polish-qa"><img src="https://agentmods.dev/badge/skills/thegoat395/codex-skills/visual-polish-qa.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00015 | $0.00500 |
| Opus 5 | $0.00008 | $0.00250 |
| Sonnet 5 | $0.00003 | $0.00100 |
| Haiku 4.5 | $0.00002 | $0.00050 |
Grade A, and why
visual-polish-qa 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 5d 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 — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Visual Polish QA
Principle
Inspect affected rendered output after implementation. Fix observed weaknesses within authorization and recheck affected behavior; stop when acceptance is met. An analysis-only review reports findings without edits.
Required Loop
- Start or locate the dev server when the project needs one.
- Open the site in a browser or capture screenshots when tooling is available.
- Check the accepted target viewports; route a systematic breakpoint problem to
responsive-visual-polish-qa. - Inspect hero, navigation, major sections, interactive states, forms, media, and footer.
- Fix obvious visual defects and weak polish.
- Run relevant required checks; repeat or broaden only after changes, failures or an unresolved risk.
- Report what was checked and what could not be checked.
What To Look For
- Text overflow, awkward line breaks, cramped labels, clipped buttons.
- Elements overlapping or drifting outside their intended layout.
- Hero media that is too dark, blurry, cropped, generic, or disconnected from the subject.
- Repetitive card grids and generic spacing.
- Typography that lacks hierarchy or scale discipline.
- Weak button states, missing focus styles, inert hover states.
- Motion that is too fast, too busy, inaccessible, or unrelated to hierarchy.
- Mobile layouts that simply stack without composition.
- Desktop layouts that stretch content too wide.
- Forms that look unstyled or have poor error/empty/loading states.
Fix Biases
- Prefer fewer, stronger visual moves.
- Tighten spacing before adding decoration.
- Improve copy specificity before adding sections.
- Use real media, generated bitmap imagery, or purposeful 3D when visuals matter.
- Make controls clear with icons and labels where appropriate.
- Preserve accessibility while polishing motion and visual style.
Verification
Use Playwright, browser tools, screenshots, or the in-app browser when available. For canvas/WebGL/Three.js work, verify that the canvas is nonblank, framed correctly, and active across desktop and mobile.
What ships with it
2 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.
- 5d ago Changed · +4 lines · -60 tokens per session f8e1d9213787
- 8d ago First seen · 49 lines · 75 tokens per session scan A 55d35938bc9b
visual-polish-qa is a skill published in the GitHub repository TheGoat395/Codex-Skills (122 stars, last pushed today), licensed MIT. It adds 15 tokens to every session and 500 once invoked, about $0.0001 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
design-pipeline
A build-and-test workflow for turning Figma designs into shadcn/ui components, a reusable set of interface components for React-based projects. It checks the result in a real browser at three screen sizes and runs accessibility checks.
web-typography
Expert front-end web typography — apply this whenever you are styling text on the web or making type decisions in HTML/CSS/JSX/Tailwind. Use it to choose and pair fonts, build a type scale, set body copy and headings, tune fluid/responsive type with clamp(), fix line-height, rhythm, measure and heading wraps, improve…
motion-foundations
Motion tokens, spring presets, performance rules, device adaptation, accessibility enforcement, and SSR safety for React / Next.js using motion/react. Foundation layer — all other motion skills depend on this.
motion-guide
Use when designing, adding, changing, suggesting, or reviewing UI motion. Motion Guide is a default-trigger motion decision advisor for AI coding agents: it decides whether motion should exist, selects an appropriate functional or expressive pattern, and constrains implementation with timing, easing, accessibility…
baseline-ui
Skill "baseline-ui" from humanerd-drew/opencode-drewgent, covering baseline ui, when to apply, rule categories by priority, 1. stack defaults and 2. html semantics.
conversion-accessibility-polish
Improve an existing website or web app's decision clarity, trust, forms, UX copy, and accessibility without dark patterns. Use when an agent must polish CTAs, navigation, pricing, onboarding, empty or error states, keyboard behavior, semantic HTML, focus, contrast, or the end-to-end conversion path.