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 asmyshlyaev177/react-horizontal-scrolling-menu --skill menu-setupgit clone --depth 1 https://github.com/asmyshlyaev177/react-horizontal-scrolling-menuWrote 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/asmyshlyaev177/react-horizontal-scrolling-menu/menu-setup)<a href="https://agentmods.dev/skills/asmyshlyaev177/react-horizontal-scrolling-menu/menu-setup"><img src="https://agentmods.dev/badge/skills/asmyshlyaev177/react-horizontal-scrolling-menu/menu-setup/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/asmyshlyaev177/react-horizontal-scrolling-menu/menu-setup"><img src="https://agentmods.dev/badge/skills/asmyshlyaev177/react-horizontal-scrolling-menu/menu-setup.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 4 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Agent Snooping · line 434 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
- medium Agent Snooping · line 420 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
- medium Agent Snooping · line 433 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
- medium Agent Snooping · line 438 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
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 | $0.00115 | $0.03282 |
| Opus 5.5 | $0.00046 | $0.01313 |
| Sonnet 5.5 | $0.00023 | $0.00656 |
| Haiku 4.5 | $0.00012 | $0.00328 |
Grade A, and why
menu-setup scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 443 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Menu Setup
Setup
npm install react-horizontal-scrolling-menu
import React from 'react';
import {
ScrollMenu,
VisibilityContext,
type publicApiType,
} from 'react-horizontal-scrolling-menu';
import 'react-horizontal-scrolling-menu/dist/styles.css';
const items = Array.from({ length: 10 }, (_, i) => `item-${i + 1}`);
export function App() {
return (
<ScrollMenu LeftArrow={LeftArrow} RightArrow={RightArrow}>
{items.map((id) => (
<Card itemId={id} key={id} title={id} />
))}
</ScrollMenu>
);
}
function LeftArrow() {
const api = React.useContext<publicApiType>(VisibilityContext);
const disabled = api.useLeftArrowVisible();
return (
<button disabled={disabled} onClick={() => api.scrollPrev()}>
←
</button>
);
}
function RightArrow() {
const api = React.useContext<publicApiType>(VisibilityContext);
const disabled = api.useRightArrowVisible();
return (
<button disabled={disabled} onClick={() => api.scrollNext()}>
→
</button>
);
}
function Card({ itemId, title }: { itemId: string; title: string }) {
const api = React.useContext<publicApiType>(VisibilityContext);
const visible = api.useIsVisible(itemId, true);
return (
<div style={{ width: '160px' }} data-visible={visible}>
{title}
</div>
);
}
Three contracts this relies on, none of which produce an error when violated:
- Every direct child of
ScrollMenuneeds a uniqueitemIdprop (the Reactkeyis the fallback). Ids areString()-coerced. styles.cssis a separate import — the JS bundle never injects CSS.- Item width comes from your CSS, in fixed units. The menu measures nothing.
The arrow hooks are the canonical edge detection: useLeftArrowVisible() /
useRightArrowVisible() return true when the first/last item is visible —
use the return value directly as the arrow's disabled state, as above.
Despite the "Visible" in the name, this is a disabled-latch: it only updates
while the menu itself is on screen, so arrows do not flicker when the page
scrolls vertically past the menu (src/createApi.ts:65-89).
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.
- 1mo ago Changed f7805e4becc2
- 1mo ago First seen · 443 lines · 115 tokens per session scan A 7fd19e752c0e
menu-setup is a skill published in the GitHub repository asmyshlyaev177/react-horizontal-scrolling-menu (789 stars, last pushed 19d ago), licensed MIT. It adds 115 tokens to every session and 3,282 once invoked, about $0.0005 per session on Opus 5.5. 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
build-with-simplepdf
Integrate SimplePDF into a web application for PDF viewing, editing, filling, signing, programmatic control, AI-agent interaction, human-in-the-loop form prefilling, submissions, webhooks, or customer-controlled storage. Use when a developer wants to add or improve PDF workflows in React, Next.js, JavaScript…
edit-pdf
Edit and fill PDF documents. Use when the user wants to fill a PDF form, add text/signatures/checkboxes/images to a PDF, or annotate a PDF. Accepts a PDF URL or file upload and returns a ready-to-use editor link. URL inputs are passed through directly. File uploads are stored temporarily (24 hours) then deleted.
fork-and-go
Guided walkthrough for forking and deploying your own SimplePDF Copilot: hosting choice, Pro-account confirmation, AI-provider wiring, demo customization, deploy, and the SimplePDF whitelist step. Use when a developer wants to fork, self-host, ship, or deploy SimplePDF Copilot.
compiler-orchestrator
Orchestrate the Rust compiler port end-to-end. Discovers the current frontier, fixes failing passes, ports new passes, reviews, and commits in a loop.
reskin
Author a NEW skin for the reskinnable-demo app. A skin is a self-contained domain plugin under src/skins/ / that implements the frozen Skin contract (src/shell/skin-contract.ts) to swap the app's entire experience — brand, theme, layout, pages, tools, data, and agent — as a live sales demo. Use when the user says "add…
setup-slack-channel
Use for the PROVIDER half of getting a locally running CopilotKit Channels agent to answer in Slack, when no Slack app exists yet — setting up a Channels bot in Slack for the first time, creating the Slack app and its tokens, attaching it to a managed Intelligence Channel, or when a Channel reports setuprequired, sits…