visual-verdict

visual-verdict is a skill for Claude Code, Codex from Global-mindee/WAY. It costs 69 tokens per session (950 once invoked), scanned A, original, MIT.

A strict comparison method for judging a generated user-interface screenshot against one or more reference images. It returns a score, a pass or revision decision, identified differences, and suggested changes.

In plain words
What is it for?
Use it to review screenshots during repeated UI design or implementation revisions, continuing changes until the stated visual threshold is reached.
Why use it?
It gives a consistent way to decide whether layout, spacing, typography, colors, and component styling match the intended design.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

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 skills/global-mindee/way/visual-verdict
Any agent
npx skills add Global-mindee/WAY --skill visual-verdict
Clone the repo
git clone --depth 1 https://github.com/Global-mindee/WAY

Made for: Claude Code, Codex.

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 visual-verdict

README.md
[![agentmods](https://agentmods.dev/badge/skills/global-mindee/way/visual-verdict.svg)](https://agentmods.dev/skills/global-mindee/way/visual-verdict)
Your own site
<a href="https://agentmods.dev/skills/global-mindee/way/visual-verdict"><img src="https://agentmods.dev/badge/skills/global-mindee/way/visual-verdict.svg" alt="Measured on agentmods" height="20"></a>
Per session 69 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 950 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 5.1 $0.00069 $0.00950
Opus 5 $0.00034 $0.00475
Sonnet 5 $0.00014 $0.00190
Haiku 4.5 $0.00007 $0.00095

Measured 6d ago against content hash 289e3866e24e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

visual-verdict 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 6d 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.

skills/01_dx-and-quality/visual-verdict/SKILL.md · 81 lines

What it actually says

visual-verdict (비주얼 판정)

생성된 UI 스크린샷을 하나 이상의 기준 이미지와 대조해, 다음 수정 반복을 구동할 수 있는 엄격한 JSON 판정을 반환한다.

언제 사용하나

  • 과제에 시각 충실도 요건(레이아웃·간격·타이포그래피·컴포넌트 스타일)이 있을 때
  • 생성된 스크린샷과 기준 이미지가 1장 이상 있을 때
  • 수정을 계속하기 전에 결정론적 통과/실패 가이드가 필요할 때

이 스킬은 메모리 html-deliverable-render-verify(HTML 산출물 렌더링 검수 의무) 절차의 판정 표준으로 연결된다 — 정적 검사만으로 불충분한 HTML 산출물의 시각 검수 결과를 정량화한다.

입력

  • reference_images[] — 기준 이미지 경로 1개 이상
  • generated_screenshot — 현재 산출 이미지
  • 선택: category_hint — 의도한 UI 카테고리/스타일 (예: dashboard, report, landing)

출력 계약

JSON만 반환한다. 다음 정확한 형태를 따른다.

{
  "score": 0,
  "verdict": "revise",
  "category_match": false,
  "differences": ["..."],
  "suggestions": ["..."],
  "reasoning": "짧은 설명"
}

규칙:

  • score: 정수 0~100
  • verdict: 짧은 상태값 (pass / revise / fail)
  • category_match: 생성 스크린샷이 의도한 UI 카테고리/스타일에 부합하면 true
  • differences[]: 구체적인 시각 불일치 (레이아웃·간격·타이포그래피·색상·위계)
  • suggestions[]: differences에 직결된 실행 가능한 다음 수정안
  • reasoning: 1~2문장 요약

임계와 루프

  • 통과 목표 임계는 90 이상.
  • score < 90이면 수정을 계속하고, 다음 시각 검수 패스 전에 visual-verdict를 재실행한다.
  • 다음 스크린샷이 임계를 넘기 전까지 시각 과제를 완료로 취급하지 않는다.

디버그 시각화

불일치 진단이 어려울 때:

  1. visual-verdict를 권위 있는 결정 기준으로 유지한다.
  2. 픽셀 단위 diff 도구(pixelmatch 오버레이 등)를 보조 디버그 수단으로만 사용해 hotspot을 국소화한다.
  3. 픽셀 diff hotspot을 구체적인 differences[]·suggestions[] 갱신으로 변환한다.

주의: 캡처는 16,384px 텍스처 한계가 있으므로 동적 scale 후 픽셀 열람으로 측정한다(HTML 렌더링 검수 교훈). 보고서형 산출물은 등장 애니메이션을 금지한다.

예시

{
  "score": 87,
  "verdict": "revise",
  "category_match": true,
  "differences": [
    "상단 내비게이션 간격이 기준보다 좁음",
    "주요 버튼이 더 작은 폰트 굵기를 사용함"
  ],
  "suggestions": [
    "내비 항목 좌우 패딩을 4px 늘릴 것",
    "주요 버튼 font-weight를 600으로 설정할 것"
  ],
  "reasoning": "핵심 레이아웃은 일치하나 스타일 세부가 아직 어긋남."
}
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. 6d ago First seen · 81 lines · 69 tokens per session scan A 289e3866e24e

Subscribe to this mod's changes

visual-verdict is a skill published in the GitHub repository Global-mindee/WAY (11 stars, last pushed 1mo ago), licensed MIT. It adds 69 tokens to every session and 950 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 2026-08-30.

Related

Other skills, from other repositories

Art

Static visual content across 20+ formats — diagrams, mermaid, infographics, D3 dashboards, comics, icons, wallpaper — via Nano Banana Pro (default), Nano Banana, and Flux. USE WHEN art, illustration, diagram, flowchart, infographic, header image, blog social thumbnail, visualize, generate image, mermaid, architecture…

danielmiessler/LifeOS · 124 tokens

CreateCLI

Generates production-ready TypeScript CLIs via a 3-tier template system (manual arg parsing, Commander.js, oclif), each shipping full implementation, docs, package.json, strict config, JSON output, and exit-code compliance. USE WHEN create CLI, build CLI, command-line tool, wrap API, add command, upgrade tier…

danielmiessler/LifeOS · 88 tokens

Daemon

Manage the public daemon profile — a digital representation of what you're working on. DaemonAggregator reads LifeOS sources (TELOS, KNOWLEDGE, PROJECTS, MEMORY/WORK, identity) → daemon-data.json. SecurityFilter strips names/paths/credentials via deterministic patterns (NOT LLM). Workflows: UpdateDaemon, ReadDaemon…

danielmiessler/LifeOS · 109 tokens

Telos

Dual-context skill: Personal TELOS reads and updates goals, beliefs, narratives, strategies, and more with timestamped backups; Project TELOS analyzes .md/.csv directories for dependency chains, bottlenecks, and alignment, generating reports, narrative points, or dashboards. USE WHEN Telos, life goals, projects…

danielmiessler/LifeOS · 104 tokens

SystemsThinking

Structural analysis of complex systems — Iceberg model, Causal Loop feedback diagrams, archetype matching, Meadows leverage points, and concept maps — grounded in the premise that behavior is generated by structure. USE WHEN systems thinking, causal loop, feedback loops, archetypes, leverage points, iceberg model, fix…

danielmiessler/LifeOS · 90 tokens

BiasCheck

Three-layer bias analysis on any URL, file, or text — auto-fetches the content and any cited study, then audits data-level biases, source conflicts of interest, and journalism-added distortions, separating what the data supports from what's editorialized. USE WHEN bias analysis, analyze bias, bias check, check this…

danielmiessler/LifeOS · 109 tokens