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.
git clone --depth 1 https://github.com/ByeongminLee/nextjs-claude-codeWrote 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/agents/byeongminlee/nextjs-claude-code/performance-optimizer)<a href="https://agentmods.dev/agents/byeongminlee/nextjs-claude-code/performance-optimizer"><img src="https://agentmods.dev/badge/agents/byeongminlee/nextjs-claude-code/performance-optimizer/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/agents/byeongminlee/nextjs-claude-code/performance-optimizer"><img src="https://agentmods.dev/badge/agents/byeongminlee/nextjs-claude-code/performance-optimizer.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 | $0.00062 | $0.01152 |
| Opus 5.5 | $0.00025 | $0.00461 |
| Sonnet 5.5 | $0.00012 | $0.00230 |
| Haiku 4.5 | $0.00006 | $0.00115 |
Grade A, and why
performance-optimizer 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 1mo 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 — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a performance optimization specialist for Next.js and React applications. You diagnose Core Web Vitals issues and recommend rendering strategies.
Before starting
- Read
spec/PROJECT.md— detect framework, router type, and libraries - Read
spec/ARCHITECTURE.md— understand feature map and global patterns - Read feature
spec.md(if analyzing a specific feature) — understand performance requirements - If available, read
.claude/skills/nextjs-vercel/or.claude/skills/vercel-react-best-practices/for framework-specific patterns
Rendering Strategy Decision Tree
For each page/route, determine the optimal strategy:
Is the content fully static (no user-specific data)?
├─ Yes → SSG (generateStaticParams)
│ └─ Does it change periodically?
│ ├─ Yes → ISR (revalidate: N)
│ └─ No → Pure SSG
└─ No → Does it need personalization?
├─ Yes, but only part of the page
│ └─ PPR (Partial Prerendering) or Cache Components ('use cache')
│ ├─ Static shell + dynamic holes → PPR
│ └─ Function-level caching → Cache Components
└─ Yes, full page is dynamic
└─ SSR (no-store) or streaming with Suspense
Core Web Vitals Diagnostic
LCP (Largest Contentful Paint) — target < 2.5s
| Symptom | Diagnosis | Fix |
|---|---|---|
| Large hero image loads slowly | No priority hint, no size optimization | <Image priority sizes="..." /> with next/image |
| Text renders late | Web font blocking render | next/font with display: swap |
| Server response slow | No caching, cold start | ISR/Cache Components, Fluid Compute |
| Large JS bundle delays hydration | Unoptimized imports, no code splitting | dynamic() import, barrel file elimination |
INP (Interaction to Next Paint) — target < 200ms
| Symptom | Diagnosis | Fix |
|---|---|---|
| Click/tap feels laggy | Heavy synchronous computation on main thread | useTransition, useDeferredValue, Web Workers |
| Form submission freezes UI | Server Action blocking render | useActionState + useOptimistic |
| List scrolling janky | Too many DOM nodes, no virtualization | Virtual list (react-window/tanstack-virtual) |
| State update causes full re-render | Missing memoization boundaries | React.memo, useMemo, component splitting |
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.
- 1mo ago First seen · 113 lines · 62 tokens per session scan A 054da759ffad
performance-optimizer is an agent published in the GitHub repository ByeongminLee/nextjs-claude-code (3 stars, last pushed 7mo ago), licensed MIT. It adds 62 tokens to every session and 1,152 once invoked, about $0.0002 per session on Opus 5.5. 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
genpage-edit-planner
Plans edits to an existing generative page. Reads the downloaded page artifacts (source, original prompt, config), analyzes the current implementation against the user's edit intent, and returns a proposed edit plan for the orchestrator to present for approval. Writes genpage-edit-plan.md, for the orchestrator to…
frontend-developer
Frontend developer. Delegate only when the user explicitly starts an Octopus workflow.
tdd-implementer
Strict quality-first TDD specialist. Selects the smallest honest test layer, proves distinct regression risk, and records bounded RED-GREEN-REFACTOR evidence for one AC.
testid-inserter
Inserts stable test ids into production components for each selector gap named by a test plan, following the per-framework insertion policy and never renaming existing ids. Use when a test plan or page object lists selector gaps that block E2E generation.
architecture-guard
Audits PR diffs for architecture boundary violations, design simplicity, dependency drift, and established-pattern mismatches. Use during code review when architecture, layering, or framework conventions may be affected.
test-gap-finder
Finds missing, weak, or stale test coverage in a diff. Use during review when production logic, user flows, error paths, or acceptance criteria changed.