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.
git clone --depth 1 https://github.com/lucamezzalira/mfe-skillsWrote 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/rules/lucamezzalira/mfe-skills/mfe-boundary-remediation)<a href="https://agentmods.dev/rules/lucamezzalira/mfe-skills/mfe-boundary-remediation"><img src="https://agentmods.dev/badge/rules/lucamezzalira/mfe-skills/mfe-boundary-remediation/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/rules/lucamezzalira/mfe-skills/mfe-boundary-remediation"><img src="https://agentmods.dev/badge/rules/lucamezzalira/mfe-skills/mfe-boundary-remediation.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 | $0.00023 | $0.03839 |
| Opus 5 | $0.00012 | $0.01920 |
| Sonnet 5 | $0.00005 | $0.00768 |
| Haiku 4.5 | $0.00002 | $0.00384 |
Grade A, and why
mfe-boundary-remediation 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 12d 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 — 466 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Remediation patterns
Version: 1.2 | Skill: reviewing-mfe-boundaries | Source: Building Micro-Frontends (O'Reilly)
Each section maps to one of the eight boundary rules.
Rule 1 — Reframing a component as a micro-frontend (or vice versa)
If a unit named or behaving as a UI component is being integrated as a micro-frontend, the fix is to decide which it actually is:
If it is truly a shared UI primitive (button, form field, layout wrapper): move it to an npm design system package. Remove the runtime integration overhead. It should be a versioned package dependency, not a deployed micro-frontend.
If it is truly a business capability masquerading as a component: rename it to reflect the domain, assign a single team to own it, and ensure it fetches its own data rather than receiving domain objects as props.
If the boundary is ambiguous: run the boundary health check from understanding-mfe-architecture/references/rules.md. If it fails two or more tests, it is in the wrong category.
Rule 2 — Reducing an oversized API surface
Before — container owns context:
<CheckoutMicrofrontend
user={user}
cart={cart}
shippingOptions={shippingOptions}
paymentMethods={paymentMethods}
discountCodes={discountCodes}
/>
After — step 1: identify which props are domain data the micro-frontend should fetch itself.
In this example: shippingOptions, paymentMethods, and discountCodes are checkout domain data. The checkout micro-frontend should retrieve them from its own backend (BFF or API layer), not receive them from the container.
After — step 2: reduce to the minimum context identifiers:
// The checkout MFE fetches its own shipping options, payment methods, discounts
<CheckoutMicrofrontend userId={userId} cartId={cartId} />
After — step 3: inside the checkout micro-frontend, fetch domain data directly:
// Inside checkout-mfe — fetches its own data
function CheckoutApp({ userId, cartId }) {
const cart = useCartData(cartId) // own API call
const shippingOptions = useShipping() // own API call
const paymentMethods = usePaymentMethods() // own API call
}
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.
- 12d ago First seen · 466 lines · 3,839 tokens per session scan A b94f0cb9ce13
mfe-boundary-remediation is a cursor rule published in the GitHub repository lucamezzalira/mfe-skills (51 stars, last pushed 17d ago), licensed MIT. It adds 23 tokens to every session and 3,839 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 2026-08-30.
Other cursor rules, from other repositories
pages
Source: docs/agents/pages.md Regenerate: npm run agents:sync -w packages/openbridge-webcomponents -->.
shadcn-tailwind-guide
A guide to building new components with shadcn/ui and Tailwind CSS, a utility-based system for styling interfaces.
css-render-blocking-diagnosis
Cursor rule "css-render-blocking-diagnosis" from adobecom/da-express-milo, covering css render-blocking diagnosis & resolution, critical learning from 98 pagespeed achievement, primary diagnostic protocol, step 1: css blocking symptom recognition and step 2: css loading sequence audit.
frontend-architecture
Vite + React SPA architecture - directory layout, providers, bundle splitting. Tailwind styling in tailwind.mdc.
web-pages-e2e-test-maintenance
Keep web pages end-to-end coverage current.
tanstack-react-router_routing
TanStack Router: Routing.