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 premium-visual-reference-librarygit 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/premium-visual-reference-library)<a href="https://agentmods.dev/skills/thegoat395/codex-skills/premium-visual-reference-library"><img src="https://agentmods.dev/badge/skills/thegoat395/codex-skills/premium-visual-reference-library/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/premium-visual-reference-library"><img src="https://agentmods.dev/badge/skills/thegoat395/codex-skills/premium-visual-reference-library.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 | $0.00016 | $0.00684 |
| Opus 5.5 | $0.00006 | $0.00274 |
| Sonnet 5.5 | $0.00003 | $0.00137 |
| Haiku 4.5 | $0.00002 | $0.00068 |
Grade A, and why
premium-visual-reference-library 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 — 39 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Premium Visual Reference Library
Use this skill to pick reference sources before designing a premium website.
Workflow
- Identify the site category: product/devtool, luxury/editorial, portfolio, hospitality, commerce, personal, agency, or content/media.
- Read sources.md for the relevant source clusters.
- When the user names a creator, asks for many examples, or uses a style shorthand, also read creator-and-pattern-index.md and creator-methods-evidence.md.
- When Viktor Oddy or MotionSites is named, read motionsites-viktor-evidence.md and refresh any count or catalog claim that matters to the current project.
- Select enough distinct references for the open decision; 3–7 is a broad direction-study option, not a quota for a supplied exact reference.
- Extract concrete patterns: type, layout, density, media, motion, CTA, proof, navigation, section rhythm, and mobile behavior.
- State what not to copy.
- When implementation is in scope, add selected traits to the shared build spec; a reference-only request ends with the source-backed study.
Retrieve only the selected material
Use the bundled read-only helper from any working directory:
python3 "<skill-root>/scripts/query_catalog.py" --search "reorder" --limit 5
python3 "<skill-root>/scripts/query_catalog.py" --id M-01
Resolve <skill-root> to this skill's actual installation. Search returns bounded discovery results; exact ID returns the original record with its provenance and limitations. The helper checks source fingerprints against the overlay, makes no external requests and writes nothing. If Python is unavailable, search the named JSON file for the selected ID and read that record plus its matching overlay record; no helper installation is required.
The four raw catalogs preserve 50 author-created style playbooks, 100 implementation leads, 22 dated creator-method interpretations and 20 historical video-study records. Repeated mechanism text is generic inference, not verified example code; repeated video-study text is synthesis, not independent per-video observation. Fixed palette, timing, target-size, frame-time and DPR values are illustrative starting choices, not universal standards or measured budgets. Inspect the selected live source and current technical documentation before relying on its actual behavior. Do not load or recrawl every catalog for one reference.
What ships with it
11 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.
- agents/openai.yaml 268 B
- references/catalog-provenance-overlay.json 62 KB
- references/creator-and-pattern-index.md 4.1 KB
- references/creator-method-cards.json 18 KB
- references/creator-methods-evidence.md 5.9 KB
- references/motionsites-viktor-evidence.md 8.3 KB
- references/reference-example-patterns.json 79 KB
- references/sources.md 5.7 KB
- references/style-playbooks.json 89 KB
- references/viktor-visual-studies.json 50 KB
- scripts/query_catalog.py 3.9 KB runs code
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 · +11 lines a8c58bef5c6f
- 1mo ago Changed · +6 lines · -44 tokens per session cd910631ea70
- 1mo ago First seen · 22 lines · 60 tokens per session scan A c5d74ac02fd1
premium-visual-reference-library is a skill published in the GitHub repository TheGoat395/Codex-Skills (132 stars, last pushed 3d ago), licensed MIT. It adds 16 tokens to every session and 684 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 2026-08-30.
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.…
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…
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…