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 monkilabs/opencastle --skill nextjs-frameworkgit clone --depth 1 https://github.com/monkilabs/opencastleWrote 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/monkilabs/opencastle/nextjs-framework)<a href="https://agentmods.dev/skills/monkilabs/opencastle/nextjs-framework"><img src="https://agentmods.dev/badge/skills/monkilabs/opencastle/nextjs-framework/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/monkilabs/opencastle/nextjs-framework"><img src="https://agentmods.dev/badge/skills/monkilabs/opencastle/nextjs-framework.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 | $0.00047 | $0.00765 |
| Opus 5.5 | $0.00019 | $0.00306 |
| Sonnet 5.5 | $0.00009 | $0.00153 |
| Haiku 4.5 | $0.00005 | $0.00076 |
Grade A, and why
nextjs-framework scanned grade A with 1 finding 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 23d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
Tag with `fetch(url, { next: { tags: ['posts'] } })` (or `cacheTag`), invalidate from a Server Action with `revalidateTag` / `revalidatePath('/posts')`. How it starts
The opening of the file, as written. The whole thing — 43 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Next.js Framework
Check the next version in package.json first: caching and the request-interception file changed in 15 and 16.
The integration configures next-devtools-mcp (MCP server next-devtools). With the dev server running it reports build and runtime errors, logs, and route and page metadata — read those before guessing at a failure.
Critical rule
Never use next/dynamic with { ssr: false } inside a Server Component — it crashes at build/runtime. Extract it into a 'use client' wrapper and import that from the server normally.
// components/MapClient.tsx
'use client';
import dynamic from 'next/dynamic';
const Map = dynamic(() => import('./Map'), { ssr: false });
export function MapClient(props: MapProps) { return <Map {...props} />; }
Gotchas
error.tsxmust be a Client Component, and needs to exist per segment — otherwise an unhandled error takes down the page.template.tsxre-mounts on navigation wherelayout.tsxpersists.default.tsxis the parallel-route fallback.- Independent fetches awaited in sequence become a waterfall — use
Promise.all(). Fetching inuseEffectwhere a Server Component could fetch costs an extra roundtrip plus a loading flash. getServerSideProps/getStaticPropsare Pages Router only; App Router uses async Server Components.- 15+:
params,searchParams,cookies()andheaders()are async — await them. - Auth: check the session at the top of an async Server Component and
redirect('/login')before returning any UI. Request interception withmatcher: ['/dashboard/:path*']covers whole subtrees:middleware.tsup to 15,proxy.ts(exportingproxy) from 16. - Dynamic segments:
[slug], catch-all[...slug], optional catch-all[[...slug]]. - Put providers in a
ProvidersClient Component rather than growinglayout.tsx;'use client'on everything defeats RSC.
Caching, by version
- 14 and earlier:
fetchis cached by default (opt out withcache: 'no-store'), GET Route Handlers are static by default. - 15: nothing is cached unless you ask.
fetch, GET Route Handlers and client navigations are uncached by default; opt in withcache: 'force-cache',export const dynamic = 'force-static', orstaleTimes. - 16: the 15 defaults, plus Cache Components (
cacheComponents: true): opt in with"use cache"on a function or component,cacheLife()for lifetime andcacheTag()for tags.revalidateTag(tag, profile)takes acacheLifeprofile (e.g.'max') and serves stale while it refreshes;updateTag(tag), Server Actions only, expires the tag so the user reads their own write.
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.
- 23d ago Changed · +7 lines · -10 tokens per session d2020e8da95e
- 24d ago First seen · 36 lines · 57 tokens per session scan A c3b4832002cf
nextjs-framework is a skill published in the GitHub repository monkilabs/opencastle (80 stars, last pushed 7d ago), licensed MIT. It adds 47 tokens to every session and 765 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-04.
Other skills, from other repositories
product-architect
Complete product development system with 80 agents and 36 frameworks. Use when the user wants to build a product, write a PRD, plan an MVP or roadmap, design an app, research a market or check whether a feature already exists or is novel, do competitive analysis, run a security audit, build a financial model, plan…
cursor-prompting
Internal guidance for composing cursor-agent prompts and picking models for coding, review, diagnosis, and research tasks inside the Cursor Claude Code plugin.
goal-runner
Use when the user asks to advance, continue, or work on the project's long-horizon goal (or to set one up) — the policy for goal-driven increments driven through the goal companion, one increment at a time, delegated via the codex/cursor delegation skills, honestly recorded.
cursor-result-handling
Internal guidance for presenting Cursor helper output back to the user.
jira-ticket-builder
Turns rough input into structured Jira work. Two modes — single-ticket mode turns a bug description, meeting notes, Slack thread, incident writeup, or a few sentences into one fully-structured Jira ticket; decomposition mode turns a rough requirements doc or product brief with multiple asks and open questions into…
agentflow
Expert guidance for building, debugging, and extending applications with AgentFlow (10xscale-agentflow). Use when code imports from agentflow (e.g. from agentflow import, StateGraph, Agent, ToolNode, AgentState); when the user references agentflow.json or CLI commands (agentflow init, agentflow api, agentflow play…