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 skills add stareezy-1/frontend-architecture-skill --skill frontend-architecturegit clone --depth 1 https://github.com/stareezy-1/frontend-architecture-skillWrote 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/stareezy-1/frontend-architecture-skill/frontend-architecture)<a href="https://agentmods.dev/skills/stareezy-1/frontend-architecture-skill/frontend-architecture"><img src="https://agentmods.dev/badge/skills/stareezy-1/frontend-architecture-skill/frontend-architecture/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/skills/stareezy-1/frontend-architecture-skill/frontend-architecture"><img src="https://agentmods.dev/badge/skills/stareezy-1/frontend-architecture-skill/frontend-architecture.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 | $0.00170 | $0.05362 |
| Opus 5.5 | $0.00068 | $0.02145 |
| Sonnet 5.5 | $0.00034 | $0.01072 |
| Haiku 4.5 | $0.00017 | $0.00536 |
Grade A, and why
frontend-architecture 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 — 406 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Frontend Architecture (portable, module-based)
Portable skill — readable by Claude Code, OpenCode, Codex, Cursor, Windsurf, and others. This skill describes a structure and a set of rules, not a component library, a state library, or a visual style. It is deliberately global: the same module/page/state model maps onto Next.js (App Router), React + Vite (SPA), Remix, and Expo / React Native, and it works with any state-management and styling stack.
The goal: a codebase where any contributor can instantly answer three questions — "where does this code live?", "what is allowed to import what?", and "is this server state or UI state?" — without asking anyone. The structure makes the answers obvious.
0. The five core ideas
- Feature modules own their world. Each feature is a self-contained
modules/{feature}/folder with its own pages, components, hooks, state, types, and a single public barrel. - Pages/screens are directories, not files. A route is a folder that co-locates its component, its styles, and the components/hooks used only by it.
- State is split by origin. Server data lives in a query/cache layer. UI/client state lives in a store. They never overlap — regardless of which libraries you pick.
- Imports cross boundaries only through barrels. Reaching into another module's internals is forbidden; you import from
@/modules/{feature}and nothing deeper. - Code is promoted, not pre-placed. It starts as local as possible and moves outward only when a second consumer appears.
Everything below is the mechanical application of these five ideas. None of it is tied to a specific library — pick your stack in Sections 4 and 6.
1. Directory layout
The shape is identical across frameworks; only the routing layer on top differs (see Section 7).
src/
├── app/ or routes/ or navigation/ ← framework routing layer (thin — see §7)
├── modules/ ← feature modules (the heart of the app)
│ └── {feature}/
│ ├── index.ts ← PUBLIC BARREL — the only cross-module entry point
│ ├── README.md ← what this module owns, its routes, its data deps
│ ├── components/ ← components reused by 2+ pages IN THIS MODULE
│ ├── pages/ ← page/screen directories (one per route)
│ │ └── {page}/
│ │ ├── {page}.tsx ← the page/screen component
│ │ ├── {page}.styles.ts ← ALL styling for this page
│ │ ├── index.ts ← re-exports the page component
│ │ ├── components/ ← components used ONLY by this page
│ │ ├── hooks/ ← hooks used ONLY by this page
│ │ ├── constants/
│ │ └── README.md ← route, params, permissions, data deps
│ ├── hooks/ ← data hooks (query/mutation) + module hooks
│ ├── stores/ ← UI/client state store(s) — never server data
│ ├── services/ ← data-access (API calls) for this feature
│ ├── utils/ ← pure module utilities (co-located *.test.ts)
│ ├── constants/
│ └── types/ ← module request/response + view-model types
└── shared/ ← cross-module building blocks
├── components/ ← components used by 2+ MODULES
├── hooks/ ← cross-cutting hooks
├── api-client/ ← one typed client; the only place that talks to the network
├── store/ ← root store wiring (if your state lib needs one — see §4)
├── utils/ ← formatters, cn()/clsx, helpers
├── constants/
└── types/
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 First seen · 406 lines · 170 tokens per session scan A b8c976ee796e
frontend-architecture is a skill published in the GitHub repository stareezy-1/frontend-architecture-skill (10 stars, last pushed 4mo ago), licensed MIT. It adds 170 tokens to every session and 5,362 once invoked, about $0.0007 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.
frontend-architecture compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| frontend-architecturestareezy-1/frontend-architecture-skill | Skill | 10 | 4mo ago | MIT | A | 170 | Claude Code, Codex |
| vercel-react-best-practicescalesthio/OpenMontage | Skill | 77k | 3d ago | AGPL-3.0 | A | 67 | Claude Code, Codex |
| vercel-composition-patternscalesthio/OpenMontage | Skill | 77k | 3d ago | AGPL-3.0 | A | 58 | Claude Code, Codex |
| frontendcode-yeongyu/oh-my-openagent | Skill | 71k | yesterday | none | A | 79 | Claude Code, Codex |
| implement-featureHoangNguyen0403/agent-skills-standard | Skill | 583 | today | MIT | A | 25 | Codex |
| implementation-readinessHoangNguyen0403/agent-skills-standard | Skill | 583 | today | MIT | A | 27 | Codex |
| common-session-retrospectiveHoangNguyen0403/agent-skills-standard | Skill | 583 | today | MIT | A | 48 | Claude Code, Codex |