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.
npx agentmods add skills/global-mindee/way/visual-verdictnpx skills add Global-mindee/WAY --skill visual-verdictgit clone --depth 1 https://github.com/Global-mindee/WAYWrote 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.
[](https://agentmods.dev/skills/global-mindee/way/visual-verdict)<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>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.
| Model | Per session | Once 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 |
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.
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 이상generated_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 0~100verdict: 짧은 상태값 (pass/revise/fail)category_match: 생성 스크린샷이 의도한 UI 카테고리/스타일에 부합하면truedifferences[]: 구체적인 시각 불일치 (레이아웃·간격·타이포그래피·색상·위계)suggestions[]: differences에 직결된 실행 가능한 다음 수정안reasoning: 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:
- visual-verdict를 권위 있는 결정 기준으로 유지한다.
- 픽셀 단위 diff 도구(pixelmatch 오버레이 등)를 보조 디버그 수단으로만 사용해 hotspot을 국소화한다.
- 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."
}
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.
- 6d ago First seen · 81 lines · 69 tokens per session scan A 289e3866e24e
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.
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…
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…
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…
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…
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…
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…