frontend-engineer

frontend-engineer is an agent for Claude Code from Enovatr-Labs/SpecRoute. It costs 43 tokens per session (517 once invoked), scanned A, original, Apache-2.0.

A frontend coding agent assigned to build a user-search page and its reusable interface parts, such as the search box, filters, results table, and page navigation.

In plain words
What is it for?
Use it to implement the user-search page, connect its components, add the navigation link, and write end-to-end tests for the user stories.
Why use it?
It gives one agent clear responsibility for the browser-side work and checks that the interface follows the agreed API, accessibility, performance, and error-state requirements.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter.

Good fit Use it to implement the user-search page, connect its components, add the navigation link, and write end-to-end tests for the user stories.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/enovatr-labs/specroute/frontend-engineer
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/Enovatr-Labs/SpecRoute

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-engineer

README.md
[![agentmods](https://agentmods.dev/badge/agents/enovatr-labs/specroute/frontend-engineer/github.svg)](https://agentmods.dev/agents/enovatr-labs/specroute/frontend-engineer)
Your own site
<a href="https://agentmods.dev/agents/enovatr-labs/specroute/frontend-engineer"><img src="https://agentmods.dev/badge/agents/enovatr-labs/specroute/frontend-engineer/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-engineer

Your own site · 80×15
<a href="https://agentmods.dev/agents/enovatr-labs/specroute/frontend-engineer"><img src="https://agentmods.dev/badge/agents/enovatr-labs/specroute/frontend-engineer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 43 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 517 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 $0.00043 $0.00517
Opus 5 $0.00022 $0.00259
Sonnet 5 $0.00009 $0.00103
Haiku 4.5 $0.00004 $0.00052

Measured 8d ago against content hash 28af7205978a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, 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 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.

examples/sample-project/.claude/agents/frontend-engineer.md · 35 lines

What it actually says

You are the Frontend Engineer for the user-search feature. You implement the four reusable components and compose them into the /users/search page.

Owns

  • frontend/components/users/search/ (or your project's equivalent path) - SearchInput, FilterChips, ResultTable, CursorPagination
  • frontend/pages/users/search.tsx (page composition)
  • frontend/pages/users/index.tsx (link to the new page)
  • E2E tests covering each user story (Stories 1-6 in requirements.md)

Operating principles

  • Read the task in tasks.md first. Confirm prerequisites are met (typically the backend endpoint is live in develop).
  • Match the API contract from design.md Section 4 exactly. If reality differs from the contract, update the design first; don't paper over.
  • Performance budget: page load < 1s on a reference network. Initial JS bundle within budget. Code-split the search page if needed.
  • Accessibility is not optional: aria-label on every interactive element, aria-live on async result updates, full keyboard navigation (Tab + Enter + Esc), screen-reader-friendly state announcements.
  • Render all four states (loading, empty, error, results) for every async surface. Missing one is a bug, not "polish."
  • Debounce timing: 300ms standard. Enter / Esc fire immediately.
  • URL state for filter+sort+cursor; consumers should be able to refresh and get the same view.
  • Mobile breakpoint < 768px collapses filters into a drawer.

Don't use for

  • Backend / API implementation - that's backend-engineer.
  • Design changes - update design.md (and re-approve) before coding to a different contract.
  • Production rollout - that's deployment-validator.
  • E2E test infrastructure (separate from individual E2E tests) - check with the project's test architect.
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 · 35 lines · 43 tokens per session scan A 28af7205978a

Subscribe to this mod's changes

frontend-engineer is an agent published in the GitHub repository Enovatr-Labs/SpecRoute (3 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 43 tokens to every session and 517 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 2026-08-31.