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 SohailKhan0525/skills --skill premium-next-reactgit clone --depth 1 https://github.com/SohailKhan0525/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/sohailkhan0525/skills/premium-next-react)<a href="https://agentmods.dev/skills/sohailkhan0525/skills/premium-next-react"><img src="https://agentmods.dev/badge/skills/sohailkhan0525/skills/premium-next-react/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/sohailkhan0525/skills/premium-next-react"><img src="https://agentmods.dev/badge/skills/sohailkhan0525/skills/premium-next-react.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00121 | $0.02194 |
| Opus 5.5 | $0.00048 | $0.00878 |
| Sonnet 5.5 | $0.00024 | $0.00439 |
| Haiku 4.5 | $0.00012 | $0.00219 |
Grade A, and why
premium-next-react 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 — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Premium Next.js & React
Build a website with a recognizable point of view and a complete visitor journey. Treat “premium” as a standard of composition, detail, behavior, and speed. Do not equate it with dark mode, expensive libraries, spectacle, or an award claim.
Read only what the task needs
| Task | Resource |
|---|---|
| Choose concept, composition, typography, copy, and responsive behavior | Art direction |
| Turn the concept into reusable tokens, component states, and finished routes | Design system and states |
| Learn from the supplied references without copying their identity | Research notes |
| Implement in Next.js or an existing React project | Framework tracks |
| Build animation with Motion or an installed Framer Motion version | Motion |
| Create original illustrations or justify optional WebGL | Illustration and 3D |
| Review before delivery | Quality gates |
| Record decisions for a substantial build | Design brief template |
For a small correction, read the affected reference and make the correction. Do not turn every task into a redesign. For a new site or substantial redesign, follow the sequence below.
1. Establish the website's job
Inspect repository instructions, package manifest, lockfile, router, existing components, assets, fonts, and content before choosing tools. Preserve working behavior and the user's existing brand unless asked to change it. This skill targets Next.js and React; do not silently migrate a different framework.
Identify the audience, subject, primary visitor action, required pages, available evidence/assets, and constraints. Distinguish a portfolio, editorial publication, service business, brand site, and product launch. A SaaS reference does not make the requested website a SaaS application. Do not add authentication, billing, subscriptions, or dashboards unless requested separately.
What ships with it
9 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 307 B
- assets/design-brief.md 2.2 KB
- references/art-direction.md 11 KB
- references/design-system-and-states.md 6.9 KB
- references/frameworks.md 11 KB
- references/illustration-and-3d.md 5.3 KB
- references/motion.md 7.4 KB
- references/quality-gates.md 6.8 KB
- references/research-notes.md 9.4 KB
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 First seen · 103 lines · 121 tokens per session scan A 16806562fec1
premium-next-react is a skill published in the GitHub repository SohailKhan0525/skills (0 stars, last pushed 6d ago), licensed MIT. It adds 121 tokens to every session and 2,194 once invoked, about $0.0005 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 2026-11-01.
premium-next-react compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| premium-next-reactSohailKhan0525/skills | Skill | 0 | 6d ago | MIT | A | 121 | Codex |
| build-ghost-appTryGhost/Ghost | Skill | 56k | yesterday | MIT | A | 44 | Claude Code, Codex |
| chakra-ui-builderchakra-ui/chakra-ui | Skill | 41k | yesterday | MIT | A | 214 | Claude Code, Codex |
| material-ui-tailwindmui/material-ui | Skill | 99k | yesterday | MIT | A | 67 | Claude Code, Codex |
| fuzzy-rankingTanStack/table | Skill | 29k | 4d ago | MIT | A | 62 | Claude Code, Codex |
| r3f-best-practiceszebbern/claude-code-guide | Skill | 4.7k | 3d ago | MIT | A | 74 | Claude Code, Codex |
| git-safetytamagui/tamagui | Skill | 14k | today | MIT | A | 0 | Claude Code |