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 5.5 | $0.00006 | $0.00200 |
| Sonnet 5.5 | $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 1mo 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.
- 1mo ago Changed · +4 lines · -60 tokens per session f8e1d9213787
- 1mo 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 (134 stars, last pushed 6d ago), licensed MIT. It adds 15 tokens to every session and 500 once invoked, about $0.0001 per session on Opus 5.5. 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.
ios-accessibility
Build and audit SwiftUI, UIKit, and AppKit accessibility for VoiceOver, Voice Control, Switch Control, Full Keyboard Access, Dynamic Type, focus restoration, labels/traits/actions, traversal, custom rotors, NSAccessibility, XCTest checks, adaptive system preferences, and App Store accessibility declarations. Use when…
pencilkit
Add Apple Pencil drawing with PKCanvasView, PKToolPicker, PKDrawing serialization/export, stroke inspection, and PencilKit/PaperKit handoffs. Use when building drawing apps, annotation features, handwriting capture, signature fields, content-version-safe ink workflows, or Apple Pencil-powered experiences on…
scenekit
Maintain and extend existing SceneKit 3D scenes and visualizations. Use when working with SCNView, SCNScene, SCNNode scene graphs, SceneKit geometry/materials/lights/cameras, SCNAction animation, SCNPhysicsBody physics, SCNParticleSystem effects, .scn/.dae/.abc SceneKit assets, shader modifiers, or SwiftUI SceneView.…
frontend-engineer
!cat skills/shared/protocols/ux-protocol.md 2>/dev/null || true !cat skills/shared/protocols/input-validation.md 2>/dev/null || true !cat skills/shared/protocols/tool-efficiency.md 2>/dev/null || true !cat .production-grade.yaml 2>/dev/null || echo "No config — using defaults" !cat .forgewright/codebase-context.md…
swiftui-liquid-glass
Implement, review, or improve SwiftUI Liquid Glass effects for iOS 26+. Covers glassEffect modifier, GlassEffectContainer, glass button styles, glass toolbar/tab bar, static status badges vs interactive controls, morphing transitions, tinting, interactive glass, ToolbarSpacer, scrollEdgeEffectStyle…