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 instructions/asmyshlyaev177/react-horizontal-scrolling-menu/agents-mdgit 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/instructions/asmyshlyaev177/react-horizontal-scrolling-menu/agents-md)<a href="https://agentmods.dev/instructions/asmyshlyaev177/react-horizontal-scrolling-menu/agents-md"><img src="https://agentmods.dev/badge/instructions/asmyshlyaev177/react-horizontal-scrolling-menu/agents-md.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 | $0.04109 | $0.04109 |
| Opus 5 | $0.02055 | $0.02055 |
| Sonnet 5 | $0.00822 | $0.00822 |
| Haiku 4.5 | $0.00411 | $0.00411 |
Grade A, and why
react-horizontal-scrolling-menu AGENTS.md 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 5d 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 — 292 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS — react-horizontal-scrolling-menu
A horizontal scrolling menu for React, built on native browser scrolling with per-item visibility tracking (IntersectionObserver). Published to npm; ~347k downloads/month; one stable public API across React 16.8–19.
If you are here to use the library rather than change it, read
skills/ instead — those files are written for you, and are more specific
than this one. npx @tanstack/intent@latest install wires them into your
agent; skills/menu-setup/SKILL.md is the entry point.
Layout
src/ # the library
stories/ # Storybook stories; *.source.tsx files are the
# canonical examples, rendered on the website and
# mirrored to /examples/<slug>.md
skills/ # AI agent skills, published with the package
# (package.json `files`), one dir per SKILL.md
website/ # the landing + docs site: TanStack Start, SSR,
# prerendered onto Cloudflare Workers. A workspace
# member, with two Playwright suites: website/e2e
# (HTTP-level smoke) and website/tests (a11y)
e2e/ # Playwright, against the built library
types/ # public type surface
Commands
pnpm test # unit + lint + e2e (wireit orchestrates)
pnpm test:unit
pnpm test:e2e
pnpm build # rollup build of the library
pnpm storybook # the examples, live
# website/ is its own workspace
cd website && pnpm dev # vite dev
cd website && pnpm build # build + prerender every route
cd website && pnpm typecheck
cd website && pnpm test # build, then the smoke suite (website/e2e)
cd website && pnpm test:a11y # build, then axe + rendered contrast (website/tests)
cd website && pnpm preview # build, then serve the Worker locally
cd website && pnpm deploy # wrangler deploy
Package management
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.
- 5d ago First seen · 292 lines · 4,109 tokens per session scan A c8a25c880615
react-horizontal-scrolling-menu AGENTS.md is an instructions file published in the GitHub repository asmyshlyaev177/react-horizontal-scrolling-menu (788 stars, last pushed yesterday), licensed MIT. It adds 4,109 tokens to every session, about $0.0205 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 instructions, from other repositories
heroes-react AGENTS.md
AGENTS.md instructions for johnpapa/heroes-react, covering heroes react — agent guide, repository structure, tech stack, build & run and install dependencies.
heroes-react copilot-instructions.md
Copilot instructions for johnpapa/heroes-react, covering copilot instructions — heroes-react, project type, javascript conventions, react patterns and redux conventions.
react CLAUDE.md
Claude Code instructions for react/react, covering react, monorepo overview and current active work.
react-svg AGENTS.md
AGENTS.md instructions for tanem/react-svg, covering agents.md, writing, architecture, build & test and releases.
ai CLAUDE.md
Claude Code instructions for vercel/ai, a project described as: The AI Toolkit for TypeScript. From the creators of Next.js, the AI SDK is a free open-source library for building AI-powered applications and agents.
KarmaCircle AGENTS.md
AGENTS.md instructions for karmacircleCommunity/KarmaCircle, covering agentic workflow, git / branching, the apps/web ↔ apps/api boundary, repo-specific guardrails and when you're not sure which duplicate a request means.