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 pledgeandgrow/pledge-skills --skill nextjsgit clone --depth 1 https://github.com/pledgeandgrow/pledge-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/pledgeandgrow/pledge-skills/nextjs)<a href="https://agentmods.dev/skills/pledgeandgrow/pledge-skills/nextjs"><img src="https://agentmods.dev/badge/skills/pledgeandgrow/pledge-skills/nextjs/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/pledgeandgrow/pledge-skills/nextjs"><img src="https://agentmods.dev/badge/skills/pledgeandgrow/pledge-skills/nextjs.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 | $0.00138 | $0.02406 |
| Opus 5 | $0.00069 | $0.01203 |
| Sonnet 5 | $0.00028 | $0.00481 |
| Haiku 4.5 | $0.00014 | $0.00241 |
Grade A, and why
nextjs-docs 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 9d 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 — 256 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Next.js 16.2.7 Reference Skill
Official Documentation: https://nextjs.org/docs
This skill ensures Claude always uses the latest Next.js 16.2.7 patterns, APIs, and best practices.
Version Context
- Next.js: 16.2.7
- React: 19.2 (Canary in App Router)
- Bundler: Turbopack (stable, default)
- Router: App Router (default for all new projects)
- Node.js: >= 20.9 (minimum)
- Browsers: Chrome 111+, Edge 111+, Firefox 111+, Safari 16.4+
Project creation: npx create-next-app@latest my-app — includes AGENTS.md and CLAUDE.md by default. Options: TypeScript, ESLint, Tailwind CSS v4, App Router, Turbopack, @/* alias.
Quick Reference
For detailed deep-dives on each topic, read the bundled reference files:
| File | Topic |
|---|---|
project-structure.md |
App Router file conventions, dynamic routes, route groups, parallel routes, intercepted routes |
server-client-components.md |
Server vs Client Components, interleaving patterns, context providers, bundle optimization |
data-fetching.md |
Server Component fetching, streaming, parallel/sequential fetching, client fetching, mutations |
caching.md |
Cache Components ("use cache"), cacheLife profiles, updateTag, refresh, invalidation |
error-handling.md |
Expected errors (useActionState), error boundaries (error.tsx), notFound(), unstable_catchError |
server-functions.md |
Server Functions vs Server Actions, auth verification, progressive enhancement, passing actions as props |
forms-validation.md |
Form validation with Zod, useActionState, useFormStatus, optimistic updates with useOptimistic |
styling.md |
Tailwind CSS v4, CSS Modules, Global CSS |
image-font-optimization.md |
next/image (local/remote), next/font/google, next/font/local |
metadata-seo.md |
Static/dynamic metadata, generateMetadata, ImageResponse for OG images, file-based metadata |
turbopack-config.md |
Turbopack, React Compiler, proxy.ts, next.config.ts, self-hosting, instrumentation |
authentication-security.md |
Session management, authorization (DAL pattern), CSP, tainting, rate limiting |
navigation-hooks.md |
useRouter, usePathname, useSearchParams, useParams, useLinkStatus, redirect, notFound, forbidden, unauthorized |
advanced-apis.md |
after(), connection(), cacheTag(), draftMode(), generateSitemaps(), JSON-LD |
components-next.md |
<Form>, <Script>, <ViewTransition>, <Suspense>, loading.js vs <Suspense> |
static-exports.md |
output: 'export', Docker self-hosting, production checklist, multi-server deployments |
instrumentation-mcp.md |
instrumentation.ts, instrumentation-client.ts, MCP server, OpenTelemetry, Speed Insights |
internationalization.md |
i18n routing, dictionaries, proxy.ts locale detection, RTL, Intl formatting |
mdx.md |
MDX setup, custom components, frontmatter, remark/rehype plugins, Tailwind typography |
testing.md |
Unit, component, E2E testing with Vitest, Playwright, Cypress, Jest |
advanced-deployment.md |
Multi-tenant, multi-zones, bundle analyzer, PWA, sitemap, robots, video |
prefetching-ppr.md |
<Link> prefetching, manual prefetch, Partial Prerendering (PPR), rendering philosophy |
preserving-ui-state.md |
React <Activity>, state preservation across navigations, form state, testing |
environment-variables.md |
.env files, NEXT_PUBLIC_, runtime variables, load order, TypeScript types |
css-in-js.md |
styled-components, styled-jsx, emotion status, Tailwind hybrid, CSS Modules comparison |
lazy-loading.md |
next/dynamic, React.lazy(), ssr: false, magic comments, Server Component code-split |
custom-server.md |
Express integration, custom routing, when to avoid, existing backend proxy |
third-party-backend.md |
@next/third-parties, BFF pattern, Route Handlers, webhooks, rate limiting |
streaming.md |
Streaming architecture, <Suspense>, loading.js, use() promise, Route Handler streams, Web Vitals |
redirecting.md |
redirect(), permanentRedirect(), NextResponse.redirect, bulk redirects at scale |
debugging-memory.md |
VS Code debugger, DevTools server-side, React DevTools, heap profiles, memory optimization |
edge-runtime.md |
Edge Runtime APIs, proxy.ts, NextRequest/NextResponse, Adapters, @next/routing |
breaking-changes.md |
Full migration guide from Next.js 15 to 16.2.7 |
What ships with it
33 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.
- advanced-apis.md 4.8 KB
- advanced-deployment.md 5.8 KB
- authentication-security.md 6.7 KB
- breaking-changes.md 6.0 KB
- caching.md 14 KB
- components-next.md 6.8 KB
- css-in-js.md 3.2 KB
- custom-server.md 3.1 KB
- data-fetching.md 7.1 KB
- debugging-memory.md 6.2 KB
- edge-runtime.md 8.8 KB
- environment-variables.md 3.7 KB
- error-handling.md 3.6 KB
- forms-validation.md 4.9 KB
- image-font-optimization.md 9.0 KB
- instrumentation-mcp.md 5.9 KB
- internationalization.md 5.2 KB
- lazy-loading.md 4.4 KB
- mdx.md 4.8 KB
- metadata-seo.md 5.3 KB
- navigation-hooks.md 4.1 KB
- prefetching-ppr.md 4.0 KB
- preserving-ui-state.md 4.2 KB
- project-structure.md 6.8 KB
- redirecting.md 7.6 KB
- server-client-components.md 7.0 KB
- server-functions.md 3.6 KB
- static-exports.md 3.5 KB
- streaming.md 8.6 KB
- styling.md 3.4 KB
- testing.md 5.8 KB
- third-party-backend.md 5.8 KB
- turbopack-config.md 13 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.
- 9d ago First seen · 256 lines · 138 tokens per session scan A 1ca8d0035011
nextjs-docs is a skill published in the GitHub repository pledgeandgrow/pledge-skills (10 stars, last pushed 1mo ago), licensed MIT. It adds 138 tokens to every session and 2,406 once invoked, about $0.0007 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 2026-08-31.
Other skills, from other repositories
nextjs-expert
Expert knowledge in Next.js framework, Server-Side Rendering, Static Site Generation, App Router, Server Components, and full-stack React applications. Use when the user mentions React, SSR, SSG, the App Router, React Server Components, or full stack, or when the task involves Next.js Fundamentals, App Router…
nextjs-development
Comprehensive Next.js development skill covering App Router, Server Components, data fetching, routing patterns, API routes, middleware, and full-stack Next.js applications.
nextjs-patterns
Next.js App Router — Server Components, Actions, streaming, caching. Use when building or migrating Next.js apps.
Next.js App Patterns
Use this skill when working in a Next.js App Router codebase (Next.js 14+) and you need safe patterns for server vs client components, data fetching, routing, and deployment without introducing hydration bugs or accidental client bundles.
nextjs
Next.js App Router best practices — Server Components, data fetching, caching, routing, middleware, metadata, error handling, streaming, Server Actions, and performance optimization for Next.js 14-16+.
nifra-web
Use when building the full-stack side of a Nifra app - file routes, layouts, loaders and actions, forms, server functions, streaming SSR, islands, SSG and ISR, the query cache, and the React, Vue, Solid, Svelte, or Preact render adapters. Covers the client/server boundary rules and the hydration errors that boundary…