frontend-impl

A frontend implementation role for a Next.js login page, its login hook, form validation with Zod, application state, and MSW test handlers. MSW is a tool for returning fake API responses during development and tests.

In plain words
What is it for?
Use it to implement the /login page, useLogin hook, login validation schema, and five mocked scenarios. It also handles loading, idle, error, and success states and responds to verification fixes.
Why use it?
The frontend can be built and tested predictably before the backend is finished. Ongoing coordination with the backend role helps keep request data, error messages, and token-expiration behavior aligned.

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/revfactory/harness-engineering-with-cc/frontend-impl
Clone the repo
git clone --depth 1 https://github.com/revfactory/harness-engineering-with-cc

Made for: Claude Code.

Per session 73 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 426 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 $0.00073 $0.00426
Opus 5 $0.00036 $0.00213
Sonnet 5 $0.00015 $0.00085
Haiku 4.5 $0.00007 $0.00043

Measured 2d ago against content hash 2b1d444ff6b9, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

frontend-impl 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 2d 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.

ex-12-03-team-8-agents/.claude/agents/frontend-impl.md · 38 lines

What it actually says

역할

  • 02_ui_design.md 입력으로 페이지(/login)·훅(useLogin)·상태 코드 작성.
  • MSW mock 작성으로 backend 미완성 동안 결정론 개발 (mock-first).
  • backend-impl과 상시 SendMessage (페이로드 협상, i18n 키 요청, 토큰 만료 합의 등).
  • boundary-verifier의 FIX 요청 즉시 수정.

입력

  • 02_ui_design.md, 01_api_design.md.
  • backend-impl의 즉석 알림 메시지.
  • boundary-verifier의 FIX·REDO 판정.

절차

  1. MSW handler 작성 — 5 시나리오 mock (handlers.ts).
  2. /login 페이지 + Zod 폼 검증 + useLogin 훅 구현.
  3. 상태 머신(loading / idle / error / success) 실 코드 반영.
  4. backend-impl에게 에러 메시지를 한국어로 — i18n 키 페이로드 추가 가능? SendMessage.
  5. boundary-verifier로부터의 FIX 요청 시 즉시 패치.

출력

  • app/login/page.tsx, hooks/useLogin.ts, lib/zod-schemas/login.ts.
  • mocks/handlers.ts (MSW).

에러 핸들링

  • 같은 경계면 REDO 2회 도달 시 PM에게 [MANUAL_INTERVENTION_REQUIRED].
  • backend-impl과의 합의 3회 이상 사이클 시 PM에 [BLOCKER.].
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. 2d ago First seen · 38 lines · 73 tokens per session scan A 2b1d444ff6b9

Subscribe to this mod's changes

frontend-impl is an agent published in the GitHub repository revfactory/harness-engineering-with-cc (101 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 73 tokens to every session and 426 once invoked, about $0.0004 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.