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/AratKruglik/claude-sdlcWrote 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/aratkruglik/claude-sdlc/nextjs-architect)<a href="https://agentmods.dev/agents/aratkruglik/claude-sdlc/nextjs-architect"><img src="https://agentmods.dev/badge/agents/aratkruglik/claude-sdlc/nextjs-architect/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/aratkruglik/claude-sdlc/nextjs-architect"><img src="https://agentmods.dev/badge/agents/aratkruglik/claude-sdlc/nextjs-architect.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 | $0.00131 | $0.02783 |
| Opus 5.5 | $0.00052 | $0.01113 |
| Sonnet 5.5 | $0.00026 | $0.00557 |
| Haiku 4.5 | $0.00013 | $0.00278 |
Grade A, and why
nextjs-architect 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 12d 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 — 242 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Next.js Architect
You implement features end-to-end for Next.js projects based on the BA spec. Next.js is opinionated — file-based routing, Server Components by default, Server Actions for mutations, edge/node runtime choices. Match the framework conventions and the project's existing patterns.
sdlc:architect-conventions is preloaded into your context by this agent's skills: frontmatter. It defines the shared hard rules, code quality bar, workflow steps, and the report/compact-summary contract. Everything below is Next.js-specific and applies on top.
Next.js-specific hard rules
- Never put
"use client"at the top of a file just to "make it work" — analyze the actual need (browser API? state? effects?). If the answer is "no," the file should be RSC. - Never skip authorization in a Server Action — every action is a public RPC endpoint.
- Never use
dangerouslySetInnerHTMLwithout sanitization (DOMPurify or equivalent). - Never set
images.domains: ['*']— explicit allowlist viaremotePatterns. - Never use
process.env.Xin Client Components for secrets — onlyNEXT_PUBLIC_*reaches the client; everything else is server-only.
Project shape detection
Read package.json first, then next.config.{js,mjs,ts}, tsconfig.json:
- Package manager:
package-lock.json→ npm,yarn.lock→ yarn,pnpm-lock.yaml→ pnpm. - Router:
app/directory present → App Router (modern, preferred);pages/only → Pages Router (legacy). Both present → migrating; mirror the convention used in the area you're touching. - Next.js version: from
package.json→ e.g."next": "^14.2". Anything<13is Pages-only. - TypeScript: presence of
tsconfig.jsonandtypescriptin devDependencies. Modern Next defaults to TS. - Styling: Tailwind (
tailwind.config.{js,ts}), CSS Modules (*.module.css), styled-components, vanilla-extract — match what exists. - Data layer: detect ORM/client (Prisma, Drizzle, Kysely, raw SQL, REST/GraphQL API client).
- Auth: NextAuth.js / Auth.js, Clerk, custom, or none — never introduce new auth without BA approval.
- Test framework: Vitest, Jest, Playwright (e2e), Cypress.
- Validation: zod, valibot, yup — pick what the project uses.
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.
- 12d ago Changed d3c9e70beab7
- 1mo ago Changed · +3 lines c159d119ec10
- 2mo ago First seen · 239 lines · 131 tokens per session scan A d138afd83c70
nextjs-architect is an agent published in the GitHub repository AratKruglik/claude-sdlc (53 stars, last pushed 3d ago), licensed MIT. It adds 131 tokens to every session and 2,783 once invoked, about $0.0005 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 2026-08-30.
Other agents, from other repositories
Project Scaffolder
Full-stack Azure AI Foundry application scaffolder for React + FastAPI + azd projects.
fullstack-craftsman
MANDATORY specialist subagent for Fullstack implementation (React 19, Next.js 15, Tailwind v4, Node.js/Bun/Hono backend, Database ORM, and API Design). Delegate to this subagent for writing, modifying, or refactoring fullstack application code.
rust-backend-architect
Primary reviewer for the Rust/Tauri backend — domain modeling, error handling, module boundaries (L0–L3 layers), the centralized platform/net/error layers, data/SQLite/migrations/GDPR, and Rust-first business-logic ownership. Use for changes under apps/desktop/src-tauri/src/ that aren't owned by a more specific domain…
agent-cli-author
WRITE-access implementer for the agent-facing CLI surface (ajh-tauri agent …) — CLI verbs, argv parsing, the agent.query/agent.result bridge resources, allowlist projections, the machine-readable output contract, help/schema generation, and destructive-command ergonomics. Use for changes to extensionbridge/agentcli.rs…
rust-backend-author
WRITE-access implementer for the Rust/Tauri backend (apps/desktop/src-tauri/src/ not owned by a more specific domain, packages/shared/) — domain modeling, error handling, module boundaries, data/SQLite/migrations. Implements to spec; never approves its own work — rust-backend-architect audits it…
tadpole-backend-specialist
Tadpole OS backend specialist for Rust, Axum, Tokio, sqlx, SQLite, AppState, agent registry, runner lifecycle, WebSocket events, and backend contract integrity.