imagine-icon

imagine-icon is a skill for Claude Code from Mineru98/imagine. It costs 122 tokens per session (1,987 once invoked), scanned A, original, MIT.

An app and website icon set generator. It creates a 1024×1024 master icon, then exports the sizes and layouts needed for iOS, Android adaptive icons, favicons, progressive web apps, and Apple touch icons.

In plain words
What is it for?
It helps prepare launcher icons, favicons, PWA icons, and complete mobile icon sets. It can create one or four visual variations and export platform-specific files.
Why use it?
It removes the repetitive work of resizing one icon for many platforms. It also checks safe margins and transparency and reports warnings about the exported files.

Skill for Claude Code

Written for Claude Code: argument-hint in frontmatter. Also seen: mentions Codex.

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is ./images/icons/<app-slug>/.

Part of the imagine plugin — 8 skills, 10 agents shipped together

Good fit It helps prepare launcher icons, favicons, PWA icons, and complete mobile icon sets. It can create one or four visual variations and export platform-specific files.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/Mineru98/imagine
agentmods
npx agentmods add skills/mineru98/imagine/imagine-icon

Made for: Claude Code.

Or install imagine, the plugin that ships this one along with the rest of its 8 skills, 10 agents.

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 imagine-icon

README.md
[![agentmods](https://agentmods.dev/badge/skills/mineru98/imagine/imagine-icon/github.svg)](https://agentmods.dev/skills/mineru98/imagine/imagine-icon)
Your own site
<a href="https://agentmods.dev/skills/mineru98/imagine/imagine-icon"><img src="https://agentmods.dev/badge/skills/mineru98/imagine/imagine-icon/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 imagine-icon

Your own site · 80×15
<a href="https://agentmods.dev/skills/mineru98/imagine/imagine-icon"><img src="https://agentmods.dev/badge/skills/mineru98/imagine/imagine-icon.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 122 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,987 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 $0.00122 $0.01987
Opus 5 $0.00061 $0.00993
Sonnet 5 $0.00024 $0.00397
Haiku 4.5 $0.00012 $0.00199

Measured 10d ago against content hash aff8d583d8c9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

imagine-icon 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 10d 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/imagine-icon/SKILL.md · 115 lines

How it starts

The opening of the file, as written. The whole thing — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.

imagine-icon

한 번의 호출로 iOS / Android adaptive / Web(favicon+PWA) 아이콘 세트를 산출한다. 마스터 생성은 AI, 리사이즈·레이아웃은 결정적 후처리다.

트리거

  • imagine-icon "<컨셉>" / imagine-icon export <master.png> (명시 호출)
  • "앱 아이콘 만들어줘"
  • "favicon 만들어줘"
  • "런처 아이콘", "launcher icon"
  • "PWA 아이콘"
  • "아이콘 세트 뽑아줘"

파이프라인

  1. 마스터 생성 (AI): generate_size: 1024x1024 PNG로 Codex 이미지 모델 호출.
  2. 프롬프트 구성: config.prompt_template의 고정 문구 + 사용자 컨셉 키워드만 조합. 제목·앱 이름을 프롬프트에 넣지 않는다. 4가지 variation_directions(minimal / 3d-glossy / flat-illustration / abstract-geometric) 중 --variation 지정이 없으면 기본 1장만 생성(--n 4로 4종 배치 생성 가능).
  3. 세이프존 검증 (결정적): 마스터 PNG의 중앙 60% 박스 밖에 핵심 콘텐츠가 얼마나 있는지 픽셀 비율로 계산. quality_checks.safe_zone_overflow_max_ratio 초과 시 사용자에게 경고.
  4. Alpha 검증: Android foreground는 배경 투명이어야 함 → PNG alpha 채널 검사, 전면 알파 0 픽셀이 없으면 "투명 배경 요청이 반영되지 않았을 수 있다" 경고.
  5. 사이즈 익스포트: scripts/lib/icon-exporter.jsexportSizes(masterPath, targets, outputDir, options) 호출. sharp 있으면 Lanczos3, 없으면 pngjs 박스 평균 폴백(작은 사이즈 품질 저하 경고).
  6. 리포트 작성: _report.md에 각 파일 경로·resize 엔진·경고 요약.

출력 규약

./images/icons/<app-slug>/
├── master.png                     (1024×1024)
├── ios/
│   └── AppIcon-1024.png
├── android/
│   ├── ic_launcher_foreground.png   (512 canvas, 432 foreground, transparent)
│   └── ic_launcher_background.png   (512 solid color)
├── web/
│   ├── favicon-16.png
│   ├── favicon-32.png
│   ├── favicon-48.png
│   ├── apple-touch-icon-180.png
│   ├── pwa-192.png
│   └── pwa-512.png
├── manifest.webmanifest            (PWA, 선택)
└── _report.md
  • <app-slug>는 사용자 컨셉에서 slugify. --out-dir 지정 시 그대로 사용(조용히 변경 금지).
  • 루트 ./images/ 직하 쓰기 금지.

마스터 프롬프트 규약

다음 문구를 그대로 프롬프트에 포함한다 (config.prompt_template):

app icon, single focal motif, centered composition, 15% padding safe zone,
bold silhouette recognizable at small size, solid background or simple gradient,
no text
  • 앱 이름·브랜드 문구는 프롬프트에 넣지 않는다. 아이콘에 글자가 새겨지는 것을 원천 차단.
  • Negative prompt 강제: text, letters, typography, multiple objects, cluttered detail, photorealistic, watermark, logo text.
  • --variation으로 방향성 지정:
    • minimal: minimal flat vector style, limited palette (≤3 colors), geometric primitives only
    • 3d-glossy: soft 3D rendering, subtle glossy highlight, studio lighting, rounded volumes
    • flat-illustration: flat illustration, solid shapes, decorative but legible at 16px
    • abstract-geometric: abstract geometric composition, bold shapes, strong silhouette

Read the full file on GitHub · 115 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 10d ago First seen · 115 lines · 122 tokens per session scan A aff8d583d8c9

Subscribe to this mod's changes

imagine-icon is a skill published in the GitHub repository Mineru98/imagine (5 stars, last pushed 12d ago), licensed MIT. It adds 122 tokens to every session and 1,987 once invoked, about $0.0006 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 2026-08-31.

Related

Other skills, from other repositories

html-ppt-zhangzara-retro-zine

A neighborhood zine on the disappearing corner shops — portraits, voices, and what a block loses when they close. Built as a decision-grade story deck for community, local readers.

nexu-io/open-design · 49 tokens

html-ppt-zhangzara-studio

A photography studio's portfolio-and-rate deck — the signature work, the process, and the packages that win the brief. Built as a decision-grade design craft deck for prospective clients.

nexu-io/open-design · 47 tokens

motion-frames

A single-frame motion-design composition with looping CSS animations — rotating type ring, animated globe, ticking timer, parallax labels. Renders as a hero video poster you can hand straight to HyperFrames or any keyframe-based exporter. Use when the brief asks for "motion design", "animated hero", "loop", "video…

nexu-io/open-design · 91 tokens

webgl-halftone-drift

A self-contained WebGL2 hero: a flowing field screened through a rotated halftone dot grid into a duotone print aesthetic; move the cursor to bend the drift.

nexu-io/open-design · 44 tokens

webgl-holographic-foil

A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.

nexu-io/open-design · 41 tokens

motion-graphics

A short, design-led motion graphic where motion is the message — kinetic typography, stat count-up, chart/data-viz hit, logo sting / brand lockup, lower-third / callout / social overlay, animated map (highlight regions, connect places, zoom to a location), animated tweet / news-article / headline, webpage / UI…

heygen-com/hyperframes · 139 tokens