A project rule for fixing bugs in the Muy design system, a shared set of interface components and styles. It requires both the local fix and a change proposed to the upstream Muy repository.

Use it when changing Muy components, tests, or local workarounds. It guides developers to open a GitHub issue and pull request for the root cause.

It prevents a workaround in one project from hiding the underlying design-system bug. Links between the local and upstream changes make the fix easier to track.

muy — Cursor rule for Cursor by multei/web

Install

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.

Clone the repo

git clone --depth 1 https://github.com/multei/web

Made for: Cursor.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/rules/multei/web/muy/github.svg)](https://agentmods.dev/rules/multei/web/muy)

Your own site

<a href="https://agentmods.dev/rules/multei/web/muy"><img src="https://agentmods.dev/badge/rules/multei/web/muy/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.

Your own site · 80×15

<a href="https://agentmods.dev/rules/multei/web/muy"><img src="https://agentmods.dev/badge/rules/multei/web/muy.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 195 This file is loaded in full into every session.

When invoked 195 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00195	$0.00195
Opus 5.5	$0.00078	$0.00078
Sonnet 5.5	$0.00039	$0.00039
Haiku 4.5	$0.00019	$0.00019

Measured yesterday against content hash 569f1a85b8dd, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

muy 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 yesterday.

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.

.cursor/rules/muy.mdc · 16 lines

What it actually says

Upstream fixes for `muy`

We have access to muy/muy. Whenever a bug or limitation in muy requires a local workaround or fix in this repo:

Still ship the consumer fix here if needed (tests, temporary local implementation, etc.).
Also open an issue and PR on https://github.com/muy/muy that fixes the root cause in the design system.
Link the consumer issue/PR to the upstream PR (and vice versa).
Prefer aligning with existing muy patterns (e.g. clsx for optional class names, same folder/test layout under packages/muy/lib/).

Do not leave muy bugs fixed only in multei/web without an upstream PR.

Changes

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.

yesterday First seen · 16 lines · 195 tokens per session scan A 569f1a85b8dd

Subscribe to this mod's changes

muy is a cursor rule published in the GitHub repository multei/web (4 stars, last pushed today), licensed MIT. It adds 195 tokens to every session, about $0.0008 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 2026-11-07.

CSS and styling Frontend Git and workflow gatsby gatsby-site netlify

muy next to 6 cursor rules from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
muymultei/web	Cursor rule	4	today	MIT	A	195	Cursor
shadcn-tailwind-guidedtyq/magic	Cursor rule	5.1k	14d ago	none	A	13	Cursor
css-render-blocking-diagnosisadobecom/da-express-milo	Cursor rule	6	yesterday	Apache-2.0	A	1,102	Cursor
irisils15/pantheon-legacy	Cursor rule	12	7d ago	MIT	A	43	Cursor
rebase-only-merged-agentsbriangmilnes/APAS-VERUS	Cursor rule	10	1mo ago	MIT	A	297	Cursor
release-checklistyoreai/relay	Cursor rule	2	3mo ago	Apache-2.0	A	215	Cursor
7-day-nextjs-web-design-cursormattcsnyder/7-day-mobile-and-web-design-skill	Cursor rule	2	5mo ago	none	A	16	Cursor