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-routing)<a href="https://agentmods.dev/rules/lucamezzalira/mfe-skills/mfe-boundary-routing"><img src="https://agentmods.dev/badge/rules/lucamezzalira/mfe-skills/mfe-boundary-routing/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-routing"><img src="https://agentmods.dev/badge/rules/lucamezzalira/mfe-skills/mfe-boundary-routing.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 | $0.00029 | $0.01337 |
| Opus 5 | $0.00015 | $0.00668 |
| Sonnet 5 | $0.00006 | $0.00267 |
| Haiku 4.5 | $0.00003 | $0.00134 |
Grade A, and why
mfe-boundary-routing 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 11d 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 — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.
URL routing ownership — shell vs micro-frontend
Version: 1.1 | Skill: reviewing-mfe-boundaries | Source: Building Micro-Frontends (O'Reilly)
Principle
Split routing responsibility by URL depth, not by who implements the router API:
| URL depth | Owner | Example |
|---|---|---|
| First segment (top-level path) | Shell | /, /catalog, /checkout |
| Second segment onward | Micro-frontend | /catalog/product/sku-123, /checkout/shipping |
The shell answers only: which MFE loads for this top-level area?
The MFE answers: what happens inside that area?
Navigation style is flexible. Use <a href>, React Router <Link>, navigate(), Angular Router, or full page loads — as long as changing the first segment loads the correct remote and deeper segments stay inside the owning MFE.
Shell: dynamic first-level routes (main goal)
The shell should load only first-level URLs from a runtime manifest (routes.json or equivalent) plus remote URLs (remotes.json). That way:
- Adding or removing an MFE updates configuration — not shell application code
- No shell redeploy is required when an existing MFE adds internal pages (
/catalog/product/:id,/catalog/sale) — those routes are owned and deployed by the MFE team
[
{ "path": "/", "scope": "home_mfe", "module": "./HomeApp", "navLabel": "Home" },
{ "path": "/catalog/*", "scope": "catalog_mfe", "module": "./CatalogApp", "navLabel": "Catalog" }
]
The shell maps each entry to one remote mount (wildcard /* hands all deeper paths to that MFE). Nav labels can also come from the manifest.
Do not in the shell:
- Register domain sub-routes (
/catalog/product/:id,/checkout/shipping) - Hard-code per-MFE routes in
App.tsxwhen a manifest could list them instead
Micro-frontend: hardcoded internal routes (expected)
Inside an MFE, routes are usually hardcoded in code — that is normal and preferred. The catalog team ships new pages without touching the shell because the shell only mounts /catalog/*.
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.
- 11d ago First seen · 126 lines · 1,337 tokens per session scan A c2c14d13e818
mfe-boundary-routing is a cursor rule published in the GitHub repository lucamezzalira/mfe-skills (51 stars, last pushed 16d ago), licensed MIT. It adds 29 tokens to every session and 1,337 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.