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 skills/techtankto/techtank-site/nextjsnpx skills add techtankto/techtank-site --skill nextjsgit clone --depth 1 https://github.com/techtankto/techtank-siteWrote 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/techtankto/techtank-site/nextjs)<a href="https://agentmods.dev/skills/techtankto/techtank-site/nextjs"><img src="https://agentmods.dev/badge/skills/techtankto/techtank-site/nextjs.svg" alt="Measured on agentmods" 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 | $0.00063 | $0.00881 |
| Opus 5 | $0.00032 | $0.00441 |
| Sonnet 5 | $0.00013 | $0.00176 |
| Haiku 4.5 | $0.00006 | $0.00088 |
Grade A, and why
nextjs 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 — 50 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Next.js
How the framework is used: App Router, rendering, and the built-in primitives.
Foundations
Runtime, language, and what "done" requires.
- pnpm only. Never npm or yarn. Node ≥ 24.
- TypeScript strict. No
anyescape hatches; domain types live intypes/. - Exported constants, hooks, types, and utils carry TSDoc. Every export in
constants/,hooks/,types/, andutils/opens with a/** */block: a one-line summary, plus@param/@returnsfor functions where the signature does not already say it, and per-member docs on non-obvious type fields; the doc is the contract a caller reads without opening the body. Components document themselves through their props types, not TSDoc. - A server started for verification is killed when the check ends: a
pnpm devorpnpm startrun to confirm a change holds the port and outlives the task otherwise, so the next run collides or, worse, verifies against stale output. Long-running servers the human started are theirs to stop. - A verification server runs on its own port and dies by its own pid. Start it with an explicit
-pwell clear of3000, capture the pid (pnpm start -p 3987 & echo $!), and kill that pid. Neverpkill -f next-serveror any name match: it matches every Next process on the machine, including the human's dev server, and rule 4 leaves that one theirs to stop.
Concepts
- App Router conventions. One root layout; pages compose section components inside
<main>; theapp/route tree mirrors the site's information architecture. - Server components by default.
'use client'only where state or browser APIs demand it (overlays, accordions, marquees, motion-driven sections), and as low in the tree as possible. - Static generation everywhere. No runtime content fetching. Dynamic routes prebuild with
generateStaticParamsover their id lists and returnnotFound()for unknown ids. - All images render through
next/imagewith explicit width and height. (Video loops are not images; they render as media elements with their own posters and dimensions.) - Fonts load through
next/font/local, exposed as CSS variables and applied on<body>. - Metadata via the Metadata API
: a full root export plus per-page overrides (never hand-rolled
<head>tags).
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 · 50 lines · 63 tokens per session scan A 37ed99a9c177
nextjs is a skill published in the GitHub repository techtankto/techtank-site (5 stars, last pushed today), licensed MIT. It adds 63 tokens to every session and 881 once invoked, about $0.0003 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…