Borrowing it
Nothing to install: this file belongs to AlphaBitCore/nexus-gateway. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/AlphaBitCore/nexus-gateway/main/.claude/skills/frontend-arch-review/SKILL.mdgit clone --depth 1 https://github.com/AlphaBitCore/nexus-gatewayWrote 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/alphabitcore/nexus-gateway/frontend-arch-review)<a href="https://agentmods.dev/skills/alphabitcore/nexus-gateway/frontend-arch-review"><img src="https://agentmods.dev/badge/skills/alphabitcore/nexus-gateway/frontend-arch-review/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/alphabitcore/nexus-gateway/frontend-arch-review"><img src="https://agentmods.dev/badge/skills/alphabitcore/nexus-gateway/frontend-arch-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00265 | $0.04099 |
| Opus 5 | $0.00133 | $0.02049 |
| Sonnet 5 | $0.00053 | $0.00820 |
| Haiku 4.5 | $0.00026 | $0.00410 |
Grade A, and why
frontend-arch-review 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 — 297 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Frontend Architecture Review
Verifies that every visual value in packages/control-plane-ui/,
packages/agent/ui/frontend/, and packages/ui-shared/ resolves through
the documented design-token layers — and that the recently-introduced
Tailwind v4 + shadcn surface stays inside the token system instead of
escaping back to raw palette utilities.
Current layer map:
- Layer 1 — raw tokens.
packages/ui-shared/src/styles/global.css(--g-*legacy palette + spacing/radius/shadow/transition constants). - Layer 1.5 — Tailwind v4
@theme {}raw palette. Defined inpackages/ui-shared/src/styles/prime-shadcn-tokens.css(--color-navy-900,--color-brand,--color-text-secondary,--font-sans, …). Tailwind resolves utilities liketext-foregroundand arbitrary values likebg-[var(--color-primary)]against this block. - Mode flip.
prime-shadcn-tokens.css:rootdefines light values for the shadcn vars (--background,--foreground,--card,--primary,--sidebar, …);.dark, [data-theme="dark"]re-binds them. Theme switching is driven by<html data-theme="…">AND<html class="dark">(set together byThemeProvider). - Layer 2 — semantic bridge.
light.css/dark.cssmap the legacy--color-*/--sidebar-*/--shadow-*names onto the shadcn vars so the 230+ existing CSS Modules keep working. - Component surface. Mostly
*.module.css(~234 files) plus a small but growing set of shadcn-style components inpackages/ui-shared/src/shadcn/that use Tailwind utility classes, all of which must resolve through the token layers (never rawbg-white/text-gray-500).
This skill is the user's single entry point for "is the frontend architecturally clean for theme + mode switching, including the new Tailwind v4 + shadcn surface".
What it detects
| Category | Where | Why it matters |
|---|---|---|
Hex / rgba / hsla literals in *.module.css |
*.module.css outside theme-definition files |
Doesn't flip with data-theme="dark" / .dark → wrong contrast in dark mode |
Hex / rgba inside style={{}} in .tsx |
All *.tsx |
Same — inline styles bypass token system |
Numeric padding/margin/gap/fontSize/fontWeight/borderRadius/transition/zIndex in inline styles |
All *.tsx |
Doesn't break mode but breaks density/skin variation; structural inconsistency |
Stale var(--xxx, #fff) references |
.tsx and .module.css |
The fallback hex is what actually renders if the token name was never defined — a silent breakage. Cleanup pass renames to the real semantic token and drops the fallback. |
Recharts hex props (fill="#…" / stroke="#…") |
.tsx only |
Should come from packages/ui-shared/src/theme/chartColors.ts so the chart flips with mode |
Raw Tailwind palette utilities (bg-white, text-gray-500, border-slate-200, dark:bg-zinc-900, etc.) |
.tsx, cva()/cn() strings |
Tailwind utilities that resolve to raw palette hex bypass the semantic shadcn tokens — must use bg-background / text-foreground / bg-card / bg-[var(--color-…)] instead |
| Hardcoded English in JSX | .tsx |
Delegated to i18n-gap-check skill |
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 First seen · 297 lines · 265 tokens per session scan A 4d66c66261bb
frontend-arch-review is a skill published in the GitHub repository AlphaBitCore/nexus-gateway (23 stars, last pushed 3d ago), licensed Apache-2.0. It adds 265 tokens to every session and 4,099 once invoked, about $0.0013 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 2026-08-30.
Other skills, from other repositories
generic-static-code-reviewer
Review static site code for bugs, security issues, performance problems, accessibility gaps, and CLAUDE.md compliance. Enforces pure HTML/CSS/JS standards, minimal page weight, mobile-first design. Use when completing features, before commits, or reviewing changes.
audit-expert
Expert-level security auditing, compliance, code review, and vulnerability assessment. Use when the user mentions compliance, security review, code review, vulnerability assessment, SOC 2, or GDPR, or when the task involves Audit Types, Audit Frameworks, Audit Process, or Authentication Review.
accessibility-audit
Fast, high-signal accessibility triage for pages, components, or PRs targeting WCAG 2.2 AA compliance.
design-systems
Principal-level design system practice — design tokens, multi-platform theming, component API design, accessibility built-in, versioning + governance, contribution model, documentation, and the discipline that turns "one team's component library" into a load-bearing capability for every product surface — including…
interaction-design
Principal-level interaction design — affordances, signifiers, feedback, mappings, constraints, error prevention, recovery, gesture + input model design, microcopy, motion as functional language, and the discipline that turns flows into experiences users complete without thinking and don't have to recover from.
wcag-accessibility
WCAG 2.2 AA + AAA accessibility patterns for every user-facing surface — semantic HTML, ARIA 1.2, keyboard navigation, screen reader support, color contrast, motion preferences, and the 9 new SCs introduced in WCAG 2.2. Also lazy-loads a11y.md content migrated from rules/common/ on 2026-06-02.