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/kayforkind/reimagine-it/locknpx skills add Kayforkind/reimagine-it --skill lockgit clone --depth 1 https://github.com/Kayforkind/reimagine-itWrote 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/kayforkind/reimagine-it/lock)<a href="https://agentmods.dev/skills/kayforkind/reimagine-it/lock"><img src="https://agentmods.dev/badge/skills/kayforkind/reimagine-it/lock.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 | $0.00108 | $0.01021 |
| Opus 5 | $0.00054 | $0.00511 |
| Sonnet 5 | $0.00022 | $0.00204 |
| Haiku 4.5 | $0.00011 | $0.00102 |
Grade A, and why
reimagine-it-lock 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.
How it starts
The opening of the file, as written. The whole thing — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/reimagine-it lock
Parent: ../SKILL.md — the full Content-Derived Design engine. This sub-skill handles design DNA capture and reuse.
Captures a shipped design's full identity into a portable markdown pack so it can be reused on any source file:
/reimagine-it lock gold/domains/cinematic/after.html as house-cinema
/reimagine-it lock examples/end-users/horizon/auto.html as ops-console
What gets captured
| Category | What | Example |
|---|---|---|
| Palette | Ground, accent, support colors with hex values | #08141a ground, #3ae098 accent |
| Type stack | Display family, body family, fallbacks | Iowan Old Style, Georgia, serif |
| Motifs | Repeating visual patterns | Pulse wave, heartbeat ring |
| Motion | Animation budget, keyframe durations | alive-micro, 2–4 loops |
| 3D signature | 3D approach for the medium | matcap-hero, card-fan |
| Section structure | Page anatomy grid | Hero → Cards → Footer |
Token translation
Locks include a translation table so a webpage lock can inform another HTML token:
/reimagine-it webpage --ref house-cinema
/reimagine-it infographic --ref house-cinema
/reimagine-it dashboard --ref house-cinema
CLI (machine-readable)
The agent pack is markdown for the LLM. The CLI writes JSON the engine can apply without an agent:
npx reimagine-it lock -i house-style.html -o house.lock.json
npx reimagine-it -i my-page.html --ref house.lock.json -t landing -o on-brand.html
npx reimagine-it -i my-page.html --ref competitor.html --auto -o study.html
--ref accepts a .lock.json file or raw HTML (reverse-lock). Structure stays content-derived; only palette, type, and voice are pinned.
Procedure
- Read the target file (HTML with inline CSS).
- Extract palette: scan
:root { }block and allvar(--*)usage for hex values. - Extract type stack: scan
font-familydeclarations; capture display, body, fallbacks. - Extract motifs: scan SVG
<pattern>,<linearGradient>, keyframe@keyframesnames. - Extract motion: count
@keyframesblocks, note durations, checkprefers-reduced-motion. - Extract 3D: scan for
perspective,rotateX,rotateY,translateZ. - Extract section structure: scan semantic HTML (
<header>,<main>,<section>,<footer>). - Write the pack to
references/locks/<name>.md. - Report
LOCKED: <name> → references/locks/<name>.mdwith a summary of what was captured.
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.
- today Changed 15e32a026878
- yesterday Changed ea1a590d549f
- 6d ago First seen · 107 lines · 108 tokens per session scan A c1900046bf2a
reimagine-it-lock is a skill published in the GitHub repository Kayforkind/reimagine-it (77 stars, last pushed today), licensed MIT. It adds 108 tokens to every session and 1,021 once invoked, about $0.0005 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.
Other skills, from other repositories
ban-pattern
Register AI-generated-looking UI patterns as prohibited rules in the design system. Use when user says "AIっぽい", "AI臭い", "これ禁止", "このパターンやめたい", "ban this pattern", "add to prohibited", or points out a generic/cookie-cutter UI element.
design-review
HTMLファイルをmelta UIデザインシステムに照らしてレビューし、違反を検出・分類・修正提案する。トリガー: 「デザインレビュー」「DSチェック」「禁止パターンチェック」「design review」「check compliance」「DS準拠確認」。対象ファイルのパスを引数で受け取る。.
vibe-to-ui
Design systems, motion, mood boards, spatial layout, visual assets, Design Context profiles, and a global Inspiration Library from screenshots, website URLs, inspiration images, music, or fuzzy aesthetic intent. Classifies page archetype, explores 3 product-aware directions before locking tokens (unless exact…
anyviz
Use when 用户请求选择、创建、改进或统一数据可视化，并需按数据与意图选择图表、主题及 D3.js、ECharts、Mapbox、Three.js、Matplotlib、Plotly 或 ggplot2 技术栈。.
generate-figma-screen
Kod veya açıklamadan Figma'da tam ekran/sayfa oluşturur. Yayınlanmış design system bileşenlerini arayıp instance olarak yerleştirir; hardcode değer yerine DS token'larını kullanır. "Figma'da ekran oluştur", "kodu Figma'ya çevir", "landing page çiz", "ekran tasarla", "generate screen", "UI'ı Figma'ya aktar"…
fmcp-intent-router
F-MCP ile ilgili herhangi bir kullanıcı talebinin ilk giriş noktası. Kullanıcının niyetini analiz eder, hangi hedef SKILL'in çalıştırılacağına karar verir, o SKILL için gereken eksik input'ları tek turda toplar, özet+onay alır ve ondan sonra hedef SKILL'i çalıştırır. "figma", "ekran oluştur", "tasarım yap", "component…