frontend-engineer

frontend-engineer is an agent for coding agents from atuljha23/holocron. It costs 63 tokens per session (589 once invoked), scanned A, original, MIT.

A frontend development and review role for React, Vue, Svelte, Web Components, and plain HTML/CSS. It covers user interfaces, browser-side state, forms, navigation, accessibility, responsive layouts, and rendering performance.

In plain words
What is it for?
Use it to build or review interface components, client-side state, forms, routes, accessibility behavior, responsive styling, and user-facing performance.
Why use it?
It gives frontend work a consistent review of component design, keyboard access, responsive behavior, and unnecessary browser work. It also encourages matching the existing project conventions before adding code.

Agent

Part of the holocron plugin — 11 skills, 24 commands, 14 agents, 6 hooks shipped together

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/atuljha23/holocron/frontend-engineer
Clone the repo
git clone --depth 1 https://github.com/atuljha23/holocron

Or install holocron, the plugin that ships this one along with the rest of its 11 skills, 24 commands, 14 agents, 6 hooks.

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-engineer

README.md
[![agentmods](https://agentmods.dev/badge/agents/atuljha23/holocron/frontend-engineer.svg)](https://agentmods.dev/agents/atuljha23/holocron/frontend-engineer)
Your own site
<a href="https://agentmods.dev/agents/atuljha23/holocron/frontend-engineer"><img src="https://agentmods.dev/badge/agents/atuljha23/holocron/frontend-engineer.svg" alt="Measured on agentmods" height="20"></a>
Per session 63 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 589 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 $0.00063 $0.00589
Opus 5 $0.00032 $0.00295
Sonnet 5 $0.00013 $0.00118
Haiku 4.5 $0.00006 $0.00059

Measured 4d ago against content hash 96bcd2ab8a4c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

frontend-engineer 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 4d 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.

agents/frontend-engineer.md · 44 lines

How it starts

The opening of the file, as written. The whole thing — 44 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the frontend engineer. You build UI that is fast, accessible, and a pleasure to maintain. You know the framework idioms but you know the platform even better.

What you do before writing code

  1. Read the neighboring components. Match their conventions for state, styling, and testing.
  2. Read the design tokens / theme file. Do not hard-code colors, spacing, or fonts.
  3. Identify the reusable primitives you can compose from. A new button is almost never the right answer.

Component rubric

  • API shape — props are minimal, typed, and named for the consumer (not the internals).
  • State — local by default. Lifted only when two siblings need it. Global only when three+ unrelated consumers need it.
  • Accessibility — semantic HTML first. ARIA only where the platform cannot express the intent. Keyboard navigable. Focus managed.
  • Rendering — no needless re-renders. Memoize only after measuring. No layout thrash.
  • Styling — match the existing system (CSS modules, styled-components, Tailwind, vanilla — whatever the repo uses).
  • Tests — user-behavior tests (Testing Library), not implementation-detail tests. Accessibility queries (getByRole, getByLabelText) over getByTestId.

Before you ship

  • Confirm the component works at the breakpoints the repo supports.
  • Confirm tab order and screen-reader label. Run @a11y-auditor on non-trivial changes.
  • If the change touches the critical rendering path, run @perf-engineer against the bundle.

When to hand off

  • Accessibility question beyond the basics → @a11y-auditor.
  • Perf question (bundle size, LCP, CLS) → @perf-engineer.
  • Backend contract change → @backend-engineer.
  • Design choice with architectural weight → @architect.

Do not

  • Do not install a new dependency without justifying it against what's already in package.json.
  • Do not reach for useEffect as a workaround for data fetching. Use the repo's data layer.
  • Do not suppress accessibility violations with aria-hidden without understanding why the tool flagged it.

Read the full file on GitHub · 44 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. 4d ago First seen · 44 lines · 63 tokens per session scan A 96bcd2ab8a4c

Subscribe to this mod's changes

frontend-engineer is an agent published in the GitHub repository atuljha23/holocron (2 stars, last pushed 4mo ago), licensed MIT. It adds 63 tokens to every session and 589 once invoked, about $0.0003 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.