frontend-reviewer

frontend-reviewer is an agent for Claude Code from fjpulidop/specrails-core. It costs 152 tokens per session (1,560 once invoked), scanned A, original, MIT.

A frontend code-audit agent that scans changed user-interface files for bundle-size increases, accessibility problems, and rendering-performance issues. Accessibility means making the interface usable by people with disabilities.

In plain words
What is it for?
Use it when frontend files change to produce findings against WCAG 2.1 AA accessibility guidance, bundle-size risks, and rendering performance.
Why use it?
It can catch interface problems that ordinary correctness tests may miss, including issues affecting page speed and users who rely on assistive technology.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter; mentions CLAUDE.md.

Part of the specrails plugin — 28 skills, 14 agents shipped together

Good fit Use it when frontend files change to produce findings against WCAG 2.1 AA accessibility guidance, bundle-size risks, and rendering performance.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/fjpulidop/specrails-core/frontend-reviewer
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.

Clone the repo
git clone --depth 1 https://github.com/fjpulidop/specrails-core

Made for: Claude Code.

Or install specrails, the plugin that ships this one along with the rest of its 28 skills, 14 agents.

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/fjpulidop/specrails-core/frontend-reviewer/github.svg)](https://agentmods.dev/agents/fjpulidop/specrails-core/frontend-reviewer)
Your own site
<a href="https://agentmods.dev/agents/fjpulidop/specrails-core/frontend-reviewer"><img src="https://agentmods.dev/badge/agents/fjpulidop/specrails-core/frontend-reviewer/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.

agentmods 80×15 button for frontend-reviewer

Your own site · 80×15
<a href="https://agentmods.dev/agents/fjpulidop/specrails-core/frontend-reviewer"><img src="https://agentmods.dev/badge/agents/fjpulidop/specrails-core/frontend-reviewer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 152 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,560 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00152 $0.01560
Opus 5 $0.00076 $0.00780
Sonnet 5 $0.00030 $0.00312
Haiku 4.5 $0.00015 $0.00156

Measured 8d ago against content hash 6f17df6f0aba, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, 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 8d 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.

specrails-plugin/agents/frontend-reviewer.md · 123 lines

How it starts

The opening of the file, as written. The whole thing — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a frontend code auditor specializing in the frontend stack used in this project (read from CLAUDE.md). You scan frontend files for bundle size regressions, accessibility violations, and render performance problems. You produce a structured findings report — you never fix code, never suggest code changes, and never ask for clarification.

Your Mission

  • Scan every file in FRONTEND_FILES_LIST for the issues defined below
  • Produce a structured report with a finding table per check category
  • Set FRONTEND_REVIEW_STATUS as the final line of your output

What You Receive

The orchestrator injects two inputs into your invocation prompt:

  • FRONTEND_FILES_LIST: the list of frontend files created or modified during this implementation run. Scan every file in this list.
  • PIPELINE_CONTEXT: a brief description of what was implemented — feature names and change names. Use this for context when assessing findings.

Bundle Size

Look for signals of bundle size regression in the modified files.

Pattern What to look for Severity
Dynamic imports without chunk naming New import() calls that lack a /* webpackChunkName: "..." */ hint Medium
Large static assets without compression Images or fonts added without evidence of compression or lazy loading Medium
Heavy library synchronous imports New synchronous imports of moment.js, full lodash (without tree-shaking path like lodash/get), or similarly large libraries in components in the critical rendering path High
Unused CSS classes A class defined in a modified CSS/SCSS file that is not referenced in any modified component file in this changeset Medium

Severity: High if a known heavy library (moment.js, full lodash, etc.) is added synchronously. Medium for all other bundle signals.

Accessibility

Scan all .html, .htm, .jsx, .tsx, .vue, and .svelte files for WCAG 2.1 AA violations.

Rule What to look for File types Severity
Missing alt text <img> tags without an alt attribute .html, .htm, .jsx, .tsx, .vue, .svelte High
Missing form labels <input> elements without an associated <label> element or aria-label attribute .html, .htm, .jsx, .tsx, .vue, .svelte High
Non-semantic interactive elements <div> or <span> with an onClick handler but no role attribute and no tabIndex .jsx, .tsx, .vue, .svelte High
Missing ARIA roles Custom interactive patterns (sliders, dropdowns, modals) without appropriate ARIA attributes .html, .htm, .jsx, .tsx, .vue, .svelte Medium
Low contrast (static) Hard-coded color pairs where the contrast ratio is estimably below 4.5:1 — flag for manual review, not auto-detectable with certainty .css, .scss, .sass, .less Medium
Missing landmark regions Pages or top-level components that lack <main>, <nav>, <header>, or equivalent ARIA landmark roles .html, .htm, .jsx, .tsx, .vue, .svelte Medium
Missing page title <title> absent or empty in modified HTML files or page-level components .html, .htm, .jsx, .tsx Medium

Read the full file on GitHub · 123 lines

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. 8d ago First seen · 123 lines · 152 tokens per session scan A 6f17df6f0aba

Subscribe to this mod's changes

frontend-reviewer is an agent published in the GitHub repository fjpulidop/specrails-core (9 stars, last pushed yesterday), licensed MIT. It adds 152 tokens to every session and 1,560 once invoked, about $0.0008 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 2026-08-31.

Related

Other agents, from other repositories

vue-reviewer

Expert Vue.js code reviewer specializing in Composition API correctness, reactivity pitfalls, component architecture, template security, and Vue-specific performance. Use for any change touching .vue, .ts/.js files with Vue imports, or Vue ecosystem code (Pinia, Vue Router, Nuxt). MUST BE USED for Vue projects.

affaan-m/ECC · 68 tokens

ui-interaction-reviewer

Interactive-component review — buttons, modals, drawers, forms, focus states, loading patterns, UX writing, empty states. Checks the invisible details that compound into "feels right": :active states, spatial-consistency entry/exit, modal vs popover transform-origin, inline form errors, focus-visible, optimistic UI…

RaNDoM6913/claude-code-superkit · 208 tokens

ui-motion-reviewer

Motion-specific review — runs the 4-question Animation Decision Framework (should it animate? purpose? easing? duration?), catches ease-in on UI, transition:all, scale(0) entry, bounce/elastic defaults, animations on keyboard-triggered actions, prefers-reduced-motion gaps, and poorly-chosen spring vs duration…

RaNDoM6913/claude-code-superkit · 189 tokens

ui-typography-reviewer

Typography-specific deep review — font selection, modular scale, line-height, line-length, pairing, tracking, OpenType features, web-font loading. Dispatch when a font-family, font-weight, or type-scale token changed; when a Google Fonts or font-loading import was added or changed; when the user asks about fonts…

RaNDoM6913/claude-code-superkit · 129 tokens

ts-reviewer

Review TypeScript/React code against SocialApp frontend patterns.

RaNDoM6913/claude-code-superkit · 15 tokens

ui-color-reviewer

Color-system review — OKLCH usage, tinted neutrals, contrast, palette construction, theme selection (dark/light), status colors, accessibility. Called by ui-reviewer when color changes need deep attention, or directly when the user asks specifically about palette / theme / contrast / accessibility. Dispatch when: a…

RaNDoM6913/claude-code-superkit · 154 tokens