mfe-architecture

mfe-architecture is a cursor rule for Cursor from lucamezzalira/mfe-skills. It costs 126 tokens per session (804 once invoked), scanned A, original, MIT.

A guide to micro-frontends, an approach where separate teams own and deploy different business areas of one web application.

In plain words
What is it for?
Use it to evaluate micro-frontends, divide a frontend into independently owned areas, choose how those areas are composed and routed, or review whether the boundaries make sense.
Why use it?
It helps decide whether splitting a frontend is appropriate and keeps the split aligned with team ownership and business responsibilities. It also provides shared terms and a way to compare architectural choices.

Cursor rule for Cursor

Written for Cursor: installed under .cursor/.

Good fit Use it to evaluate micro-frontends, divide a frontend into independently owned areas, choose how those areas are composed and routed, or review whether the boundaries make sense.

Compare 6 cursor rules from other repositories ↓
Install with agentmods
npx agentmods add rules/lucamezzalira/mfe-skills/mfe-architecture
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/lucamezzalira/mfe-skills

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.

agentmods badge for mfe-architecture

README.md
[![agentmods](https://agentmods.dev/badge/rules/lucamezzalira/mfe-skills/mfe-architecture/github.svg)](https://agentmods.dev/rules/lucamezzalira/mfe-skills/mfe-architecture)
Your own site
<a href="https://agentmods.dev/rules/lucamezzalira/mfe-skills/mfe-architecture"><img src="https://agentmods.dev/badge/rules/lucamezzalira/mfe-skills/mfe-architecture/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.

agentmods 80×15 button for mfe-architecture

Your own site · 80×15
<a href="https://agentmods.dev/rules/lucamezzalira/mfe-skills/mfe-architecture"><img src="https://agentmods.dev/badge/rules/lucamezzalira/mfe-skills/mfe-architecture.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 126 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 804 The whole file, excluding the scripts and references it only reads on demand.
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00126 $0.00804
Opus 5 $0.00063 $0.00402
Sonnet 5 $0.00025 $0.00161
Haiku 4.5 $0.00013 $0.00080

Measured 12d ago against content hash 3e62da3d65ae, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

mfe-architecture 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.

.cursor/rules/mfe-architecture.mdc · 53 lines

How it starts

The opening of the file, as written. The whole thing — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Micro-frontend core concepts

Canonical vocabulary, principles, and decisions framework for micro-frontend architecture, as defined in Building Micro-Frontends (O'Reilly) and the Micro-Frontend Canvas (buildingmicrofrontends.com).

Task routing

Identify the task type first, then load the appropriate reference file. Do not load all files at once.

Task Load First action
Should we use MFEs? references/boundary-design.md Apply the organisational readiness gate before any implementation advice
Defining or reviewing boundaries references/boundary-design.md Ask about team ownership before discussing technology
Reviewing boundary validity or architecture for principle violations references/rules.md → or load reviewing-mfe-boundaries skill for code-level detail Run the boundary health check for validity; scan against the eight rules for violations
Choosing composition, routing, or communication references/decisions-framework.md Confirm split strategy (vertical vs horizontal) before composition; shell owns first URL segment, MFE owns sub-routes
Micro-Frontend Canvas facilitation Install micro-frontend-canvas skill (see references/canvas-pointer.md) Confirm domain is identified; do not facilitate Canvas from this skill
Generating or reviewing MFE code Load reviewing-mfe-boundaries skill This skill handles code-level boundary enforcement

If the user's terminology differs from the canonical definitions in the reference files, map it once to the canonical term, then continue using theirs.

Do not revert to generic frontend advice once this skill is active. Micro-frontend principles apply at the boundary between independently deployed units — not within a single unit.

When not to activate

Stand down if the question is purely about component composition, state management within a single deployed unit, or build tooling with no independent-deployment or team-scaling angle.


Examples

Read the full file on GitHub · 53 lines

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.

  1. 12d ago First seen · 53 lines · 126 tokens per session scan A 3e62da3d65ae

Subscribe to this mod's changes

mfe-architecture is a cursor rule published in the GitHub repository lucamezzalira/mfe-skills (51 stars, last pushed 17d ago), licensed MIT. It adds 126 tokens to every session and 804 once invoked, about $0.0006 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.