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-rules-core)<a href="https://agentmods.dev/rules/lucamezzalira/mfe-skills/mfe-boundary-rules-core"><img src="https://agentmods.dev/badge/rules/lucamezzalira/mfe-skills/mfe-boundary-rules-core/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-rules-core"><img src="https://agentmods.dev/badge/rules/lucamezzalira/mfe-skills/mfe-boundary-rules-core.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 | $0.00024 | $0.05038 |
| Opus 5 | $0.00012 | $0.02519 |
| Sonnet 5 | $0.00005 | $0.01008 |
| Haiku 4.5 | $0.00002 | $0.00504 |
Grade A, and why
mfe-boundary-rules-core 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 — 552 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MFE boundary rules
Version: 1.3 | Skill: reviewing-mfe-boundaries | Source: Building Micro-Frontends (O'Reilly). Canvas facilitation: separate micro-frontend-canvas skill.
Principle-level definitions, violation signals, and canonical code patterns for all eight boundary rules. Tool-agnostic — applies regardless of composition mechanism, framework, or toolchain.
For framework-specific code patterns (Module Federation v2, Angular/Native Federation, Single SPA): load references/rules-toolchain.md.
Each rule entry contains: the canonical definition, violation signals, and code-checkable patterns.
Rule 1 — Represents a business subdomain, not a component
A micro-frontend is the technical representation of a business subdomain. It is not a reusable UI component.
The distinction: a component addresses a technical challenge through abstraction and reusability, and its API is frequently coupled with its container. A micro-frontend completely owns a business domain; it is context-aware, not designed for reuse across domains.
How to identify a domain: base boundaries on user journey steps (checkout, search, profile, authentication) or clear business capabilities — not on technical frameworks, component types, or UI layout regions.
The rule of thumb: if you can reuse it everywhere, it is probably a component. If it represents a domain and can live on its own, it is a micro-frontend.
Violation signals:
- A micro-frontend named after a UI element (header, sidebar, card) rather than a business capability
- A micro-frontend that is reused across multiple unrelated domains
- Boundaries drawn along technical layers (data layer, presentation layer) rather than domain lines
Code-checkable patterns:
// ✗ Named after a UI element — not a domain
<HeaderMicrofrontend />
<SidebarMicrofrontend />
<CardMicrofrontend />
// ✓ Named after a business capability
<CheckoutMicrofrontend />
<CatalogMicrofrontend />
<AuthenticationMicrofrontend />
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 · 552 lines · 5,038 tokens per session scan A 57c6dd178def
mfe-boundary-rules-core is a cursor rule published in the GitHub repository lucamezzalira/mfe-skills (51 stars, last pushed 16d ago), licensed MIT. It adds 24 tokens to every session and 5,038 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
ponytail
Ponytail, lazy senior dev mode. Always pick the simplest solution that works.
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.
dev-standard
Apache Superset development standards and guidelines for Cursor IDE.
cli-error-handling
CLI command error handling patterns.
prefer-direct-imports-over-module-mocks
Prefer extracting a testable core over vi.mock / vi.resetModules when unit tests need to reach production logic entangled with config, env, or singletons.
control-plane-descriptors
Control plane descriptor and instance implementation patterns.