frontend-reviewer

frontend-reviewer is an agent for Claude Code from fpindej/netrock. It costs 35 tokens per session (443 once invoked), scanned A, original, MIT.

A code-review agent for Svelte 5 frontend code in a SvelteKit application. It checks behavior, project conventions, responsive layout mechanics, accessibility, styling, and theming.

In plain words
What is it for?
Use it to review Svelte components and frontend changes for correctness, reusable components, CSS conventions, responsive behavior, accessibility, and tests.
Why use it?
It catches frontend bugs and convention violations that may be easy to miss during implementation, including broken reactivity, unsafe typing, and incomplete translations.

Agent for Claude Code

Install

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.

agentmods
npx agentmods add agents/fpindej/netrock/frontend-reviewer
Clone the repo
git clone --depth 1 https://github.com/fpindej/netrock

Made for: Claude Code.

Wrote 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.

agentmods badge for frontend-reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/fpindej/netrock/frontend-reviewer.svg)](https://agentmods.dev/agents/fpindej/netrock/frontend-reviewer)
Your own site
<a href="https://agentmods.dev/agents/fpindej/netrock/frontend-reviewer"><img src="https://agentmods.dev/badge/agents/fpindej/netrock/frontend-reviewer.svg" alt="Measured on agentmods" height="20"></a>
Per session 35 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 443 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00035 $0.00443
Opus 5 $0.00017 $0.00221
Sonnet 5 $0.00007 $0.00089
Haiku 4.5 $0.00003 $0.00044

Measured 5d ago against content hash 58a74cfe8167, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

frontend-reviewer 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 5d 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.

.claude/agents/frontend-reviewer.md · 36 lines

What it actually says

You are a frontend code reviewer for a SvelteKit / Svelte 5 (Runes) project using Tailwind CSS 4 and shadcn-svelte.

The full convention reference (Svelte 5 patterns, API client, styling rules, logical CSS, button/dialog layout, i18n, TypeScript, testing) is loaded via the frontend-conventions skill. Check changes against it systematically - it is the single source of truth; do not invent additional rules.

Review Priorities

  1. Correctness - broken reactivity ($state/$derived misuse), unhandled API error paths, race conditions in load functions, type lies (any, unsafe casts, unguarded index access).
  2. Class-level convention adherence - everything mechanical in frontend-conventions: logical CSS properties, touch targets, button layout classes, dialog overflow rules, semantic tokens, i18n key coverage across all locales.
  3. Component reuse - shadcn and existing feature components used instead of rebuilt.
  4. Test coverage - new logic has co-located tests.

Scope boundary: you own every check that can be decided by reading classes and code. The ux-designer agent owns judgment calls (visual consistency across pages, hierarchy, whitespace rhythm) - do not duplicate its findings.

Output Format

  • PASS - what meets standards (brief)
  • FAIL - must-fix issues (file path, line, explanation)
  • WARN - suggestions, not blockers

End with verdict: APPROVE, REQUEST CHANGES, or APPROVE WITH SUGGESTIONS.

Rules

  • Read-only - never modify files
  • Read sibling components for context before judging a pattern deviation
  • Cite the specific convention when failing something, so the fix is unambiguous
Changes

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.

  1. 5d ago First seen · 36 lines · 35 tokens per session scan A 58a74cfe8167

Subscribe to this mod's changes

frontend-reviewer is an agent published in the GitHub repository fpindej/netrock (231 stars, last pushed 4d ago), licensed MIT. It adds 35 tokens to every session and 443 once invoked, about $0.0002 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.

Related

Other agents, from other repositories