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 KunanonJ/ai-skills-hub --skill aside-image-searchgit clone --depth 1 https://github.com/KunanonJ/ai-skills-hubWrote 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/kunanonj/ai-skills-hub/aside-image-search)<a href="https://agentmods.dev/skills/kunanonj/ai-skills-hub/aside-image-search"><img src="https://agentmods.dev/badge/skills/kunanonj/ai-skills-hub/aside-image-search/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/kunanonj/ai-skills-hub/aside-image-search"><img src="https://agentmods.dev/badge/skills/kunanonj/ai-skills-hub/aside-image-search.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00011 | $0.00607 |
| Opus 5 | $0.00005 | $0.00303 |
| Sonnet 5 | $0.00002 | $0.00121 |
| Haiku 4.5 | $0.00001 | $0.00061 |
Grade A, and why
aside-image-search 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 — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Image Search
Use the imageSearch global in the REPL tool. It fetches Google Images with the browser profile's cookies, parses result metadata from the returned HTML, and returns compact JSON. You do not need to manually inspect the DOM.
Quick Reference
const results = await imageSearch.search('max verstappen', { limit: 10 });
console.log(JSON.stringify(results, null, 2));
// → [{ title, sourceName, pageUrl, imageUrl, thumbnailUrl, width, height, dominantColor, licensable }]
Methods
imageSearch.search(query: string, opts?: ImageSearchOptions): Promise<ImageSearchResult[]>
Search Google Images. Returned imageUrl points to the discovered original image when Google exposes it. thumbnailUrl points to Google's thumbnail cache. License hints from Google are not legal guarantees; verify before reuse.
Browse the Google Images page directly if the helper fails.
Types
interface ImageSearchOptions {
limit?: number; // max search results. (default: 20)
safeSearch?: 'active' | 'off';
size?: 'large' | 'medium' | 'icon';
color?: 'black' | 'blue' | 'brown' | 'gray' | 'green' | 'orange' | 'pink' | 'purple' | 'red' | 'teal' | 'transparent' | 'white' | 'yellow';
type?: 'animated' | 'clipart' | 'lineart';
license?: 'creativeCommons' | 'commercial';
time?: 'day' | 'week' | 'month' | 'year';
}
interface ImageSearchResult {
/** Human-readable image/result title from Google or the source page. */
title: string;
/** Publisher or site name when Google exposes it. */
sourceName?: string;
/** Source page that contains the image. Open this to inspect context or attribution. */
pageUrl: string;
/** Best-effort original image URL. Prefer this when you need the actual image asset. */
imageUrl?: string;
/** Google thumbnail URL. Useful for quick preview when `imageUrl` is missing or huge. */
thumbnailUrl?: string;
/** Original image width in pixels when Google exposes it. */
width?: number;
/** Original image height in pixels when Google exposes it. */
height?: number;
/** Dominant CSS color from Google, useful for quick UI placeholders. Example: `rgb(192,198,224)`. */
dominantColor?: string;
/** Google marked the result as licensable or it came from a license-filtered search. Example: `true`. */
licensable?: boolean;
}
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 · 61 lines · 11 tokens per session scan A 6012f63e7b03
aside-image-search is a skill published in the GitHub repository KunanonJ/ai-skills-hub (5 stars, last pushed yesterday), licensed MIT. It adds 11 tokens to every session and 607 once invoked, about $0.0001 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 2026-09-03.
Other skills, from other repositories
issue-creation
Trigger: issue creation, bug reports, feature requests, or issue approval. Create and triage GitHub issues from repository evidence.
sdd-tasks
Break an SDD change into implementation tasks. Trigger: orchestrator launches task planning for a change.
work-unit-commits
Plan commits as reviewable work units. Trigger: implementation, commit splitting, chained PRs, or keeping tests and docs with code.
systemic-issue-triage
Trigger: new issue, bug report, triage, backlog, issue flood, community report, root cause, dead-end, blocked user. Attack issues by root class, never one-by-one; fixes must shrink the system, not grow it.
sdd-research
Trigger: SDD research, external evidence, source-backed research. Produce auditable evidence for a selected research lane.
skill-improver
Trigger: improve skills, audit skills, refactor skills, skill quality. Audit and upgrade existing LLM-first skills.