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 GoldenWing-360/claude-security-skills --skill nextjs-securitygit clone --depth 1 https://github.com/GoldenWing-360/claude-security-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/goldenwing-360/claude-security-skills/nextjs-security)<a href="https://agentmods.dev/skills/goldenwing-360/claude-security-skills/nextjs-security"><img src="https://agentmods.dev/badge/skills/goldenwing-360/claude-security-skills/nextjs-security/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/goldenwing-360/claude-security-skills/nextjs-security"><img src="https://agentmods.dev/badge/skills/goldenwing-360/claude-security-skills/nextjs-security.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 | $0.00079 | $0.02509 |
| Opus 5 | $0.00039 | $0.01255 |
| Sonnet 5 | $0.00016 | $0.00502 |
| Haiku 4.5 | $0.00008 | $0.00251 |
Grade A, and why
nextjs-security 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 12d 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 — 254 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Next.js Security
Next.js moves fast and its security model has shifted with every major version. The most common failure mode is reaching for a familiar pattern from a year ago that no longer holds — middleware-only auth, naive Server Actions, NEXT_PUBLIC_ env handling. This skill is the spot-check list.
Tested patterns target App Router on Next.js 14+; most apply to 15/16 too. Pages Router callouts are marked.
When to invoke
- New Next.js app heading to production
- Major version upgrade (13 → 14 → 15 → 16)
- Adding authenticated routes, Server Actions, or new middleware logic
- Investigating an incident or suspicious request pattern
- Code review for an inherited Next.js codebase
1. Middleware is not authoritative auth
Middleware runs on every matched request, but it is a network-edge thing — not a substitute for per-route authorization. Treat middleware as a performance optimization for redirects and headers, not as a security boundary.
The 2025 middleware bypass class (CVE-2025-29927-style) showed that header smuggling can skip middleware entirely on misconfigured setups. Patch your Next.js to the fixed version and assume the bypass is possible — every protected route still re-checks auth server-side.
// app/admin/page.tsx — every protected route does its own check
import { redirect } from 'next/navigation';
import { getSession } from '@/lib/session';
export default async function AdminPage() {
const session = await getSession();
if (!session || session.role !== 'admin') redirect('/login');
// ... render
}
For Server Actions specifically, re-validate inside the action:
'use server';
export async function deletePost(id: string) {
const session = await getSession();
if (!session) throw new Error('unauthenticated');
if (!canDelete(session.userId, id)) throw new Error('forbidden');
// ... mutate
}
A Server Action is callable from any client that knows the action ID; middleware only sees the request, not the action target.
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.
- 12d ago First seen · 254 lines · 79 tokens per session scan A e10ff2fb1a8b
nextjs-security is a skill published in the GitHub repository GoldenWing-360/claude-security-skills (17 stars, last pushed 1mo ago), licensed MIT. It adds 79 tokens to every session and 2,509 once invoked, about $0.0004 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 2026-08-30.
Other skills, from other repositories
ux-audit
Walk through a live web app AS a real user to find usability + behavioural bugs that static reviews miss. REQUIRES proof of interaction (typing, clicking, sending, observing) before any verdict — a sweep that didn't interact terminates with verdict 'Incomplete'. Walks threads, exercises every element, runs the…
design-loop
Autonomous multi-page site builder using a baton-passing loop. Each iteration reads a task from .design/next-prompt.md, generates a page in HTML/Tailwind, integrates it into the site, verifies visually, then writes the next task to keep the loop alive. Use whenever the user asks to build an entire site autonomously…
product-showcase
Generate a comprehensive marketing website for a web app — multi-page with real screenshots, animated GIF walkthroughs, feature deep-dives, and workflow demonstrations. Browses the running app, captures screens and sequences, and produces a deployable site that actually teaches people what the product does. Especially…
tanstack-start
Build a full-stack TanStack Start app on Cloudflare Workers from scratch — SSR, file-based routing, server functions, D1+Drizzle, better-auth, Tailwind v4+shadcn/ui. Use whenever the user mentions TanStack Start, asks to scaffold a full-stack Cloudflare app with SSR, wants an SSR dashboard, or asks for a React 19 +…
color-palette
Generate complete, accessible colour palettes from a single brand hex. Produces 11-shade scale (50-950), semantic tokens, dark mode variants, Tailwind v4 CSS output, WCAG contrast checks. Use whenever the user supplies a brand hex and asks for a palette, mentions setting up a design system, wants Tailwind theme…
deep-research
Deep research and discovery before building something new. Explores local projects for reusable code, researches competitors, reads forums and reviews, analyses plugin ecosystems, investigates technical options, and produces a comprehensive research brief. Three depths: focused (30 min), wide (1-2 hours), deep (3-6…