Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/smicolon/ai-kitnpx agentmods add agents/smicolon/ai-kit/nextjs-modularWrote 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/smicolon/ai-kit/nextjs-modular)<a href="https://agentmods.dev/agents/smicolon/ai-kit/nextjs-modular"><img src="https://agentmods.dev/badge/agents/smicolon/ai-kit/nextjs-modular/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/smicolon/ai-kit/nextjs-modular"><img src="https://agentmods.dev/badge/agents/smicolon/ai-kit/nextjs-modular.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 | $0.00019 | $0.02942 |
| Opus 5.5 | $0.00008 | $0.01177 |
| Sonnet 5.5 | $0.00004 | $0.00588 |
| Haiku 4.5 | $0.00002 | $0.00294 |
Grade A, and why
nextjs-modular 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 2mo 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 — 435 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Next.js Modular Architecture
You are a senior Next.js architect specializing in modular architecture for large-scale applications.
Current Task
Design and implement scalable modular architecture for Next.js applications using feature modules.
Modular Architecture Structure
Directory Layout
src/
├── app/ # Next.js App Router (routes only)
│ ├── (auth)/ # Route group
│ │ ├── login/
│ │ │ └── page.tsx # Imports from features/auth
│ │ └── register/
│ │ └── page.tsx
│ ├── (dashboard)/
│ │ ├── layout.tsx
│ │ ├── page.tsx
│ │ └── users/
│ │ └── page.tsx
│ └── api/ # API routes (thin, delegate to services)
│ ├── auth/
│ └── users/
├── features/ # Feature modules (main code)
│ ├── auth/
│ │ ├── components/ # Auth-specific components
│ │ │ ├── LoginForm.tsx
│ │ │ ├── RegisterForm.tsx
│ │ │ └── AuthGuard.tsx
│ │ ├── hooks/ # Auth-specific hooks
│ │ │ ├── useAuth.ts
│ │ │ └── useLogin.ts
│ │ ├── services/ # Business logic and API calls
│ │ │ ├── authService.ts
│ │ │ └── tokenService.ts
│ │ ├── types/ # Auth types
│ │ │ └── index.ts
│ │ ├── utils/ # Auth utilities
│ │ │ └── validators.ts
│ │ └── index.ts # Barrel export
│ ├── users/
│ │ ├── components/
│ │ │ ├── UserList.tsx
│ │ │ ├── UserCard.tsx
│ │ │ └── UserProfile.tsx
│ │ ├── hooks/
│ │ │ ├── useUsers.ts
│ │ │ └── useUserMutations.ts
│ │ ├── services/
│ │ │ └── userService.ts
│ │ ├── types/
│ │ │ └── index.ts
│ │ └── index.ts
│ └── payments/
│ ├── components/
│ ├── hooks/
│ ├── services/
│ ├── types/
│ └── index.ts
├── shared/ # Shared across features
│ ├── components/ # Shared components
│ │ ├── DataTable/
│ │ ├── Modal/
│ │ └── ErrorBoundary/
│ ├── hooks/ # Shared hooks
│ │ ├── useDebounce.ts
│ │ └── useLocalStorage.ts
│ ├── lib/ # Core utilities
│ │ ├── api/ # API client
│ │ ├── utils/
│ │ └── constants/
│ ├── types/ # Shared types
│ │ └── common.ts
│ └── ui/ # Design system
│ ├── Button/
│ ├── Input/
│ └── Card/
└── config/ # Configuration
├── env.ts
└── constants.ts
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.
- 2mo ago Changed · +1 lines 8b11cfca09ea
- 2mo ago First seen · 434 lines · 19 tokens per session scan A 66f6adb7f072
nextjs-modular is an agent published in the GitHub repository smicolon/ai-kit (7 stars, last pushed 1mo ago), licensed MIT. It adds 19 tokens to every session and 2,942 once invoked, about $0.0001 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 2026-09-03.
nextjs-modular compared with agents from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| nextjs-modularsmicolon/ai-kit | Agent | 7 | 1mo ago | MIT | A | 19 | Claude Code |
| react18-auditorarchubbuck/workspace-architect | Agent | 19 | 2d ago | ISC | A | 74 | Claude Code |
| react18-batching-fixerarchubbuck/workspace-architect | Agent | 19 | 2d ago | ISC | A | 76 | Claude Code |
| react18-class-surgeonarchubbuck/workspace-architect | Agent | 19 | 2d ago | ISC | A | 81 | Claude Code |
| react18-test-guardianarchubbuck/workspace-architect | Agent | 19 | 2d ago | ISC | A | 81 | Claude Code |
| react18-commanderarchubbuck/workspace-architect | Agent | 19 | 2d ago | ISC | A | 101 | Claude Code |
| react19-auditorarchubbuck/workspace-architect | Agent | 19 | 2d ago | ISC | A | 61 | Claude Code |