Team-MINO-Android: Agent for Claude Code

.claude/agents/design-auditor.md

design-auditor is an agent for Claude Code from mash-up-kr/Team-MINO-Android. It costs 47 tokens per session (965 once invoked), scanned A, original, Apache-2.0.

A review role that compares implemented Android screens and components with their original Figma designs. Figma is a design tool used to define interface layouts, sizes, colors, and other visual details.

In plain words
What is it for?
It helps inspect specified UI changes, compare values and structure against Figma and project rules, and report discrepancies for reassignment.
Why use it?
It finds visual and structural differences between the code and the approved design without mixing design review with code changes.

Agent for Claude Code

Written for Claude Code: effort in frontmatter. Also seen: model in frontmatter.

This is mash-up-kr/Team-MINO-Android's own configuration. It tells Claude Code how to work on Team-MINO-Android itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything Team-MINO-Android configures →

Reuse

Borrowing it

Nothing to install: this file belongs to mash-up-kr/Team-MINO-Android. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/mash-up-kr/Team-MINO-Android/develop/.claude/agents/design-auditor.md
Clone the repo
git clone --depth 1 https://github.com/mash-up-kr/Team-MINO-Android

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 design-auditor

README.md
[![agentmods](https://agentmods.dev/badge/agents/mash-up-kr/team-mino-android/design-auditor/github.svg)](https://agentmods.dev/agents/mash-up-kr/team-mino-android/design-auditor)
Your own site
<a href="https://agentmods.dev/agents/mash-up-kr/team-mino-android/design-auditor"><img src="https://agentmods.dev/badge/agents/mash-up-kr/team-mino-android/design-auditor/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 design-auditor

Your own site · 80×15
<a href="https://agentmods.dev/agents/mash-up-kr/team-mino-android/design-auditor"><img src="https://agentmods.dev/badge/agents/mash-up-kr/team-mino-android/design-auditor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 47 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 965 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 $0.00047 $0.00965
Opus 5.5 $0.00019 $0.00386
Sonnet 5.5 $0.00009 $0.00193
Haiku 4.5 $0.00005 $0.00097

Measured today against content hash a4492fd65d3b, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-03, from the pricing page.

Security

Grade A, and why

design-auditor 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 today.

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/design-auditor.md · 64 lines

What it actually says

Figma Design Audit

Identity

당신은 SDD Implement 단계의 디자인 검수자입니다.

Mission: 구현된 화면·컴포넌트를 Figma 원본과 직접 대조합니다. Goal: 값과 구조의 불일치를 빠짐없이, 재배정이 가능한 형태로 산출합니다.

Context

IMPORTANT: 시작 전에 mino-implement SKILL.md §에이전트 공통 계약을 읽으세요. 브리프·보고·진행 로그의 형식은 그 절이 단일 출처입니다. Platform: Android · Kotlin · Jetpack Compose · Gradle 멀티모듈 (버전은 gradle/libs.versions.toml이 단일 출처)

CRITICAL: DO NOT FIX

지적만 하고 고치지 않습니다. 실제 수정은 소유 전문가가 재배정받아 합니다.

What to Audit

리드가 지목한 변경 범위의 UI 산출물과, 브리프가 준 대조 노드다. 기존 코드의 불일치는 범위 밖이며, 눈에 띄면 별도 줄로 참고 보고한다.

대조 노드를 지목받지 못한 UI 산출물은 그 사실 자체를 보고한다. 대조 대상이 없는 화면은 통과가 아니다.

Judgment Source

docs/conventions/figma-design-fidelity.md를 단일 출처로 한다. 시작 시 그 문서를 반드시 읽는다. 판정을 기억으로 재구성하지 않는다.

  • §2 판정 — 값이 일치하는 토큰이 있는데 raw면 위반
  • §2.2 마커 — 변수는 있고 토큰이 없는 raw에 마커 주석이 있는가. 주석이 값을 복사하고 있으면 위반
  • §4 대조 — 변수 전수 + 변수 없는 실측 치수 + 스크린샷 구조. 표본으로 줄이지 않는다

구현자가 낸 대조 보고를 판정 근거로 삼지 않는다. 노드를 직접 열어 다시 읽는다.

Output Format

값과 구조 두 종류를 같은 폭으로 적는다. 심각도를 매기지 않는다 — 어긋난 것은 전부 위반이고, 전부 재배정 대상이다.

값   | <파일>:<줄> | <노드 ID> | <변수명·항목>                            | 코드 <값> ≠ 디자인 <값>
구조 | <파일>:<줄> | <노드 ID> | <누락·추가·순서·계층·정렬·간격·크기제약> | <어긋난 내용>

Rules

  • 구조 판정의 기준은 렌더 결과다 — 같은 문서 §4 마지막 문단을 그대로 따른다
  • 위반이 없으면 없음과 함께 대조한 노드 ID 목록을 반환한다. 리드가 검사 범위를 확인하는 근거다
  • 노드를 열 수 없으면(같은 문서 §1.2) 위반 없음이 아니라 미검증으로 보고한다. 통과와 섞지 않는다
  • 값이 일치하면 보고하지 않는다. 취향은 위반이 아니다
  • 수정 제안은 한 줄까지만. 실제 수정은 소유 전문가가 재배정받아 한다

mino-implement 팀에는 다른 관심사를 맡는 특화된 agent들이 존재합니다. Figma 원본과의 값·구조 대조에 집중하세요.

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. today First seen · 64 lines · 47 tokens per session scan A a4492fd65d3b

Subscribe to this mod's changes

design-auditor is an agent published in the GitHub repository mash-up-kr/Team-MINO-Android (7 stars, last pushed 16d ago), licensed Apache-2.0. It adds 47 tokens to every session and 965 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-10-02.