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 skills add bam-bam-2/solo-skills --skill measured-ui-calloutsgit clone --depth 1 https://github.com/bam-bam-2/solo-skillsWrote 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/bam-bam-2/solo-skills/measured-ui-callouts)<a href="https://agentmods.dev/skills/bam-bam-2/solo-skills/measured-ui-callouts"><img src="https://agentmods.dev/badge/skills/bam-bam-2/solo-skills/measured-ui-callouts/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.
<a href="https://agentmods.dev/skills/bam-bam-2/solo-skills/measured-ui-callouts"><img src="https://agentmods.dev/badge/skills/bam-bam-2/solo-skills/measured-ui-callouts.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00055 | $0.00553 |
| Opus 5 | $0.00028 | $0.00277 |
| Sonnet 5 | $0.00011 | $0.00111 |
| Haiku 4.5 | $0.00006 | $0.00055 |
Grade A, and why
measured-ui-callouts 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 13d 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
측정 기반 실물 화면 콜아웃
실제 화면을 장식용 이미지로 재제작하지 말고, 원본 화면을 증거 자료로 유지한다.
작업 순서
- 원본 화면에서 강조 대상과 개인정보 영역을 먼저 구분한다.
- 실제 DOM 화면이면 대상 요소의
getBoundingClientRect()를 측정한다. 눈대중 좌표를 사용하지 않는다. - DOM이 없는 캡처 이미지면 원본 픽셀에서 셀 경계와 텍스트 영역을 측정한 뒤, 렌더링 배율·이동값으로 변환한다.
- 개인정보는 원래 셀 경계를 유지한 채 해당 영역만 모자이크 또는 블러 처리한다. 회색 박스로 넓게 덮어 원본 구조를 가리지 않는다.
- 강조 박스는 설명하는 대상 하나만 감싼다. 주변 빈 영역, 다른 행, 버튼을 함께 감싸지 않는다.
- 제목·설명·브랜드 라벨과 실제 화면 카드 사이에 충분한 여백을 둔다. 카드가 제목 글자의 하단을 덮지 않도록 제목의 실제 bounding box보다 아래에 배치한다.
- 최종 캔버스 전체를 캡처하고 제목, 카드, 하단 설명, 콜아웃이 모두 캔버스 안에 들어오는지 확인한다. 부분
clip으로 잘린 결과를 완성본으로 쓰지 않는다. - GIF는 첫 프레임만 보지 않는다. 모든 대표 프레임에서 강조 위치, 개인정보 가림, 제목 잘림 여부를 확인한다.
필수 검수
- 원본 화면의 작업 내용은 변경하지 않았는가
- 실명, 주소, 전화번호, 특허고객번호, 전체 출원번호, 접수번호, 결제·인증 정보가 남지 않았는가
- 강조 박스가 실제 설명 대상과 정확히 일치하는가
- 제목과 설명이 상단 카드에 가려지거나 캔버스 밖으로 잘리지 않았는가
- 정적 이미지와 GIF의 캔버스 비율·표시 크기가 일관적인가
- 공개 발행 전 브라우저에서 실제 표시 크기로 다시 확인했는가
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.
- 13d ago First seen · 29 lines · 55 tokens per session scan A 54d8d6e4c006
measured-ui-callouts is a skill published in the GitHub repository bam-bam-2/solo-skills (363 stars, last pushed 9d ago), licensed MIT. It adds 55 tokens to every session and 553 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
magpie-issue-triage
For each open issue in the configured candidate pool, read the issue body and comments and classify the candidate disposition. On user confirmation, posts a triage-proposal comment that invites the project team to react. Read-only on tracker state — no workflow transitions, closures, or label changes. Six classes in…
appdrag-automation
Automate Appdrag tasks via Rube MCP (Composio). Always search tools first for current schemas.
frontend-perfection
Audit and polish frontend (static HTML/CSS/JS or built SPA) to measurable perfection: real-Chrome Lighthouse >=13 runs (mobile+desktop, no Playwright internals), SEO meta layer, WCAG contrast by computed luminance, heading order, a11y checks (axe-core subset), back-to-top navigation, design tokens (zero raw hex)…
frontend-a11y
Deep accessibility (a11y) audit of a webpage or static HTML/CSS, mapped to the full Front-End-Checklist Accessibility category (95 rules) — far beyond the 12 basic rules in frontend-perfection. Runs offline static checks (Python stdlib, no browser/network) for structure, ARIA validity, headings, landmarks, tables…
frontend-performance
Audit web performance depth beyond Lighthouse. Use when the user asks for a performance audit, Core Web Vitals (CWV) review, bundle-size analysis, or to optimize loading — including slow LCP/FCP/INP/CLS, a heavy JS/CSS bundle, or missing HTTP/2, text compression, browser caching, HSTS, resource hints, service worker…
frontend-testing
Scaffold and advise on frontend testing for production readiness, mapped to the Front-End-Checklist Testing category (13 rules). Defines a testing pyramid (unit, integration, E2E, visual, a11y, cross-browser, real-device, perf-budget, mutation, error-monitoring, coverage, mocking, contract) and emits copy-pasteable…