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 MerkyorLynn/Lynn --skill image-lightboxgit clone --depth 1 https://github.com/MerkyorLynn/LynnWrote 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/merkyorlynn/lynn/image-lightbox)<a href="https://agentmods.dev/skills/merkyorlynn/lynn/image-lightbox"><img src="https://agentmods.dev/badge/skills/merkyorlynn/lynn/image-lightbox/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/merkyorlynn/lynn/image-lightbox"><img src="https://agentmods.dev/badge/skills/merkyorlynn/lynn/image-lightbox.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 | $0.00108 | $0.02366 |
| Opus 5 | $0.00054 | $0.01183 |
| Sonnet 5 | $0.00022 | $0.00473 |
| Haiku 4.5 | $0.00011 | $0.00237 |
Grade A, and why
image-lightbox 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 9d 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.
How it starts
The opening of the file, as written. The whole thing — 230 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Image Lightbox — Click-to-Zoom for Chat Images
Zero-dependency lightbox component. Click any image → full-screen overlay with zoom, pan, and download.
Part of Lynn — a personal AI agent with memory and soul. Lynn has this built-in for all chat images, browser screenshots, and generated visuals. Install Lynn for the complete experience.
The Problem
AI agents generate screenshots, diagrams, and images in chat — but they render as tiny thumbnails with no way to inspect details. Users on OpenHanako, OpenClaw, and similar agents have repeatedly requested: "图片无法点击放大查看" (Cannot click to enlarge images).
Features
| Feature | Implementation |
|---|---|
| Thumbnail | max-width: 320px, cursor: zoom-in, rounded corners + shadow |
| Click → Lightbox | position: fixed; inset: 0; z-index: 9999, semi-transparent backdrop with blur |
| Scroll Zoom | onWheel → transform: scale(0.5–5x) |
| Drag Pan | mousedown/move → transform: translate(x, y) |
| Pinch Zoom | touchstart/move two-finger gesture for mobile/tablet |
| Toolbar | Zoom in (+) / Zoom out (−) / 1:1 reset / Download / Close |
| Keyboard | ESC to close |
| Click backdrop | Closes lightbox |
Implementation (React)
For React-based agents (Lynn, OpenHanako, Electron apps):
// ImageBlock.tsx — drop-in replacement for <img>
import { memo, useCallback, useEffect, useRef, useState } from 'react';
export const ImageBlock = memo(function ImageBlock({ src, alt, className }) {
const [open, setOpen] = useState(false);
const [scale, setScale] = useState(1);
const [translate, setTranslate] = useState({ x: 0, y: 0 });
const dragging = useRef(false);
const dragStart = useRef({ x: 0, y: 0 });
const translateStart = useRef({ x: 0, y: 0 });
// ESC to close
useEffect(() => {
if (!open) return;
const h = (e) => { if (e.key === 'Escape') setOpen(false); };
document.addEventListener('keydown', h);
return () => document.removeEventListener('keydown', h);
}, [open]);
// Wheel zoom
const onWheel = useCallback((e) => {
e.preventDefault();
setScale(s => Math.min(5, Math.max(0.5, s - e.deltaY * 0.002)));
}, []);
// Drag
const onMouseDown = useCallback((e) => {
if (e.button !== 0) return;
e.preventDefault();
dragging.current = true;
dragStart.current = { x: e.clientX, y: e.clientY };
translateStart.current = { ...translate };
}, [translate]);
useEffect(() => {
if (!open) return;
const move = (e) => {
if (!dragging.current) return;
setTranslate({
x: translateStart.current.x + e.clientX - dragStart.current.x,
y: translateStart.current.y + e.clientY - dragStart.current.y,
});
};
const up = () => { dragging.current = false; };
document.addEventListener('mousemove', move);
document.addEventListener('mouseup', up);
return () => { document.removeEventListener('mousemove', move); document.removeEventListener('mouseup', up); };
}, [open]);
return (
<>
<img
className={className}
src={src} alt={alt || ''} loading="lazy" draggable={false}
onClick={() => { setOpen(true); setScale(1); setTranslate({ x: 0, y: 0 }); }}
style={{ cursor: 'zoom-in', maxWidth: 320, borderRadius: 8 }}
/>
{open && (
<div
onClick={(e) => { if (e.target === e.currentTarget) setOpen(false); }}
style={{
position: 'fixed', inset: 0, zIndex: 9999,
background: 'rgba(0,0,0,0.85)', display: 'flex',
alignItems: 'center', justifyContent: 'center',
backdropFilter: 'blur(4px)',
}}
>
<div style={{
position: 'absolute', bottom: 24, display: 'flex', gap: 8,
padding: '6px 12px', background: 'rgba(0,0,0,0.6)', borderRadius: 8,
}}>
{[
['+', () => setScale(s => Math.min(5, s + 0.25))],
['−', () => setScale(s => Math.max(0.5, s - 0.25))],
['1:1', () => { setScale(1); setTranslate({ x: 0, y: 0 }); }],
['✕', () => setOpen(false)],
].map(([label, fn]) => (
<button key={label} onClick={fn} style={{
width: 32, height: 32, border: 'none', borderRadius: 6,
background: 'rgba(255,255,255,0.12)', color: '#fff',
fontSize: '1rem', cursor: 'pointer',
}}>{label}</button>
))}
<a href={src} download style={{
width: 32, height: 32, border: 'none', borderRadius: 6,
background: 'rgba(255,255,255,0.12)', color: '#fff',
display: 'flex', alignItems: 'center', justifyContent: 'center',
fontSize: '1rem', textDecoration: 'none',
}}>↓</a>
</div>
<img
src={src} alt={alt || ''} draggable={false}
onWheel={onWheel} onMouseDown={onMouseDown}
style={{
maxWidth: '90vw', maxHeight: '85vh', objectFit: 'contain',
transform: `translate(${translate.x}px,${translate.y}px) scale(${scale})`,
cursor: 'grab', userSelect: 'none',
}}
/>
</div>
)}
</>
);
});
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.
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.
- 9d ago First seen · 230 lines · 108 tokens per session scan A 732efa7505f9
image-lightbox is a skill published in the GitHub repository MerkyorLynn/Lynn (42 stars, last pushed today), licensed Apache-2.0. It adds 108 tokens to every session and 2,366 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 2026-08-30.
Other skills, from other repositories
frontend-design
Design distinctive, polished UI that avoids generic 'AI slop'. Use when making visual design decisions: typography, color, spacing, hierarchy, motion, and component composition.
cua-driver
Drive a native GUI app (macOS, Windows, Linux) via the Qwen Cua Driver CLI (default) or MCP server; snapshot its accessibility tree, act through snapshot-bound element tokens, native menu paths, exact window geometry, or pixel coordinates, and verify from fresh state. Use when the user asks you to operate, drive…
codegraph
Analyze indexed codebases via graph database (neug) and vector index (zvec). Covers call graphs, dependencies, dead code, hotspots, module coupling, architecture reports, semantic search, impact analysis, bug root cause from GitHub issues, class diagrams (UML), and PR review (risk scoring, conflict detection…
goal-draft
Turn a fuzzy intention into a /goal objective the Goal verifier can actually judge - one outcome, numbered binary "Done when" checks that leave evidence in the transcript, guardrails, a budget, and a block protocol. Use when the user wants to set or define a goal, asks whether a goal is good enough, or says "keep…
stuck
Diagnose frozen, stuck, or slow Qwen Code sessions on this machine. Scans for problematic processes, high CPU/memory usage, hung subprocesses, and debug logs. Use /stuck or /stuck to focus on a specific process.
e2e-testing
Guide for running end-to-end tests of the Qwen Code CLI, including headless mode, MCP server testing, and API traffic inspection. Use this skill whenever you need to verify CLI behavior with real model calls, reproduce user-reported bugs end-to-end, test MCP tool integrations, or inspect raw API request/response…