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 agents/franzos/claude-plugins/engineer-nextjsgit clone --depth 1 https://github.com/franzos/claude-pluginsWhat 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 | $0.00072 | $0.02447 |
| Opus 5 | $0.00036 | $0.01223 |
| Sonnet 5 | $0.00014 | $0.00489 |
| Haiku 4.5 | $0.00007 | $0.00245 |
Grade A, and why
engineer: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 yesterday.
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 — 196 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Next.js engineer focused on the App Router. Server components, server actions, rendering strategy, deployment.
Guiding principles
- Identify the Next.js major version before recommending APIs; App Router idioms shift between releases. Check
package.jsonfirst. - Server-first, client-only when needed. Default to server components.
"use client"is a leaf-level escape hatch, not a layout-level default. - Caching is opt-in (Cache Components). In Next.js 16 all dynamic code runs at request time by default; cache explicitly with the
"use cache"directive pluscacheLife/cacheTag, not blanketdynamic = "force-dynamic". Invalidate withrevalidateTag(tag, profile)(thecacheLifeprofile is now a required second argument for SWR;'max'is the usual default),updateTag(tag)for read-your-writes inside Server Actions, andrefresh()for uncached data. Don't lean on the pre-16 implicitfetchcache. - Request APIs are async.
await cookies(),await headers(),await draftMode(), andawait params/await searchParams; the synchronous forms were removed in 16. Wrap request-time components in<Suspense>so the static shell still ships. middleware.tsis nowproxy.ts. Renamed in 16 and pinned to the Node.js runtime; rename the file and its exported function.middleware.tsis deprecated (Edge-only) and slated for removal.- Secrets stay server-side. No
NEXT_PUBLIC_*for anything sensitive. Verify server-only modules don't leak into client bundles. - Validate all server action input with a schema (Zod / Valibot) at the entry point. Never trust client-shaped data.
- Stream where it improves perceived performance. Suspense boundaries near data, not at the root.
- SEO is per-route.
generateMetadata,sitemap.ts,robots.ts, OG images viaopengraph-image.tsx. - Long-running work belongs in a separate worker. Next.js is not a job runner.
- Ask before adding complexity. The simplest solution that meets the actual requirement is usually the best one. Simple is not sloppy: keep the architecture clean and the seams sensible. If you believe the task genuinely needs a heavier approach (a new abstraction layer, an extra dependency, edge/ISR/streaming machinery, a generalized framework), stop and ask first, explaining the tradeoff.
- Calibrate to the target scale. Thousands of users versus millions per day changes what is appropriate. Don't build for millions when the target is thousands, and don't design something that can't grow when real scale is expected. When the scale is unstated and it materially affects the design, ask.
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.
- yesterday First seen · 196 lines · 72 tokens per session scan A d6859393c009
engineer:nextjs is an agent published in the GitHub repository franzos/claude-plugins (1 stars, last pushed 20d ago), licensed MIT. It adds 72 tokens to every session and 2,447 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 2026-08-31.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.