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 rules/thegoat395/codex-skills/codex-premium-website-skillsgit clone --depth 1 https://github.com/TheGoat395/Codex-SkillsWhat 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 | $0.00000 | $0.00610 |
| Opus 5 | $0.00000 | $0.00305 |
| Sonnet 5 | $0.00000 | $0.00122 |
| Haiku 4.5 | $0.00000 | $0.00061 |
Grade A, and why
codex-premium-website-skills 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 yesterday.
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 — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Codex Skills Rules
Use these rules when building or reviewing websites, landing pages, portfolios, product UI, frontend components, motion systems, or launch-ready web experiences.
Operating Standard
- Read the brief before building.
- Infer audience, product category, visual tone, content needs, and interaction depth.
- Make the first viewport visually decisive.
- Avoid generic AI website patterns: centered hero plus three feature cards, vague SaaS copy, decorative blobs, weak buttons, placeholder testimonials, fake metrics, and random gradients.
- Prefer concrete design decisions over vague adjectives.
Design Direction
- Establish a clear visual direction before implementation.
- Use typography, spacing, color, imagery, material, and layout as a coherent system.
- Use visual assets when the subject benefits from them.
- Keep mobile layouts intentionally composed, not merely stacked.
- Avoid one-note palettes and unsupported decorative effects.
Frontend Implementation
- Follow the project's existing framework and conventions.
- Prefer project-local dependencies.
- Use semantic structure, accessible controls, responsive constraints, and maintainable components.
- Add stable dimensions for fixed-format UI elements so states do not shift layout.
- Keep text readable and prevent overflow at common viewport sizes.
Motion
- Use motion to clarify sequence, depth, focus, state, or tactility.
- Respect
prefers-reduced-motion. - Prefer CSS for simple state transitions, Motion for React state/layout transitions, and GSAP only when timeline or scroll choreography needs it.
- Avoid janky scroll listeners and unnecessary animation on frequent or keyboard-driven actions.
QA And Handoff
- Inspect rendered output when frontend changes matter.
- Check desktop and mobile viewports.
- Check console/network errors when possible.
- Verify focus states, labels, contrast, reduced motion, and responsive media.
- End with changed files, commands run, checks passed, checks not run, known limitations, and next risks.
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.
- yesterday First seen · 66 lines · 0 tokens per session scan A 4785bbd9372c
codex-premium-website-skills is a cursor rule published in the GitHub repository TheGoat395/Codex-Skills (118 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 610 tokens. 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 cursor rules, from other repositories
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.
dev-standard
Apache Superset development standards and guidelines for Cursor IDE.
typescript
Changes to these high-fan-out internals can affect every message, delta, element, or rerun. Keep work in them minimal, and benchmark changes with representative stress-test apps.
coolify-ai-docs
Master reference to all Coolify AI documentation in .ai/ directory.
python_lib
Tips and guidelines specific to the development of the Streamlit Python library, not applicable to scripts and e2e tests.
specs
This directory contains product and tech specs for Streamlit features.