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-architecture-rules-ref)<a href="https://agentmods.dev/rules/lucamezzalira/mfe-skills/mfe-architecture-rules-ref"><img src="https://agentmods.dev/badge/rules/lucamezzalira/mfe-skills/mfe-architecture-rules-ref/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-architecture-rules-ref"><img src="https://agentmods.dev/badge/rules/lucamezzalira/mfe-skills/mfe-architecture-rules-ref.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 | $0.00714 | $0.00714 |
| Opus 5.5 | $0.00286 | $0.00286 |
| Sonnet 5.5 | $0.00143 | $0.00143 |
| Haiku 4.5 | $0.00071 | $0.00071 |
Grade A, and why
mfe-architecture-rules-ref 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 2mo 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 — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MFE boundary rules — quick reference
Version: 1.2 | Skill: understanding-mfe-architecture | Full rules: load reviewing-mfe-boundaries skill
For full rule definitions, violation signals, and code-checkable patterns across all toolchains (React, Angular/Native Federation, Module Federation v1/v2, Single SPA), load reviewing-mfe-boundaries skill.
Boundary health check
Use this checklist when reviewing whether existing boundaries are well-formed. A well-formed boundary satisfies all seven:
- Is the API surface minimal — fewer than 5 props to the container?
- Is the micro-frontend context-aware — does it retrieve its own data given minimal input?
- Is it less extensible than a component — not designed for reuse across domains?
- Is it coarse-grained — not fine enough to require constant coordination with its container?
- Can it deploy without coordinating with other teams?
- Does it have a graceful fallback if it fails to load?
- Does a single team own it end-to-end?
If any answer is no, the boundary needs to be revisited before implementation begins.
Rule summary
| Rule | Core principle | Primary violation signal |
|---|---|---|
| 1 — Business subdomain | Represents a domain, not a UI element | Named after UI element; reused across domains |
| 2 — Minimal API surface | Fewer than 5 props; identifiers not objects | Domain objects passed as props; container fetches data for the MFE |
| 3 — Hide implementation details | API contract agreed upfront; internals hidden | Direct import from another MFE's package |
| 4 — Events not shared state | Event emitter or storage only; no shared state managers | Redux/Zustand/MobX shared across MFE boundaries |
| 5 — Independent deployment | No versioned URL pinning; no build-time coupling | Shell hard-codes versioned remote URL; CI needs: coupling |
| 6 — Isolate failure | Fallback in shell for every remote mount | No fallback at mount point in the shell |
| 7 — Coarse-grained | Max 3 MFEs per view; shell first segment via manifest; MFE hardcodes sub-routes | Shell owning /catalog/product/:id; shell hard-coded MFE routes; shell catalog:* handlers |
| 8 — Single-team ownership | One team owns full lifecycle | Multiple teams in CODEOWNERS for same MFE |
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.
- 2mo ago First seen · 51 lines · 714 tokens per session scan A e1dbbbae7a67
mfe-architecture-rules-ref is a cursor rule published in the GitHub repository lucamezzalira/mfe-skills (53 stars, last pushed 1mo ago), licensed MIT. It adds 714 tokens to every session, about $0.0029 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 2026-08-30.
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.
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.
config-validation-and-normalization
Config validation and normalization responsibilities (defineConfig normalizes, the orm section schema validates and resolves paths, the loader reports per-section diagnostics).
control-plane-descriptors
Control plane descriptor and instance implementation patterns.