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.
npx skills add lucamezzalira/mfe-skills --skill reviewing-mfe-boundariesgit 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/skills/lucamezzalira/mfe-skills/reviewing-mfe-boundaries)<a href="https://agentmods.dev/skills/lucamezzalira/mfe-skills/reviewing-mfe-boundaries"><img src="https://agentmods.dev/badge/skills/lucamezzalira/mfe-skills/reviewing-mfe-boundaries/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/skills/lucamezzalira/mfe-skills/reviewing-mfe-boundaries"><img src="https://agentmods.dev/badge/skills/lucamezzalira/mfe-skills/reviewing-mfe-boundaries.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00192 | $0.03270 |
| Opus 5 | $0.00096 | $0.01635 |
| Sonnet 5 | $0.00038 | $0.00654 |
| Haiku 4.5 | $0.00019 | $0.00327 |
Grade A, and why
reviewing-mfe-boundaries 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 — 266 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MFE boundary health
Reviews and generates micro-frontend code against the eight boundary rules from Building Micro-Frontends (O'Reilly). All rules are tool-agnostic. Full rule definitions, violation signals, and code-checkable patterns are in references/rules-core.md — load it when you need the detail for a specific rule.
On every activation, apply this summary table directly — no file load needed:
| Rule | What to check in code | Severity |
|---|---|---|
| 1 — Business subdomain | Name reflects a business capability, not a UI element | High |
| 2 — Minimal API surface | Fewer than 5 props; no full domain objects passed | Critical |
| 3 — Hide implementation details | No direct imports from another MFE's internals | Critical |
| 4 — Events not shared state | No shared store; shell handles shell:* only; domain events peer-to-peer or URL |
Critical |
| 5 — Independent deployment | No versioned URLs in shell config; no build-time MFE imports; no CI pipeline coupling | High |
| 6 — Isolate failure | Every remote mount has a fallback in the shell | High |
| 7 — Coarse-grained | Nesting depth > 1 (MFE inside MFE); more than 3 MFEs per view | High |
| 8 — Single-team ownership | One team in CODEOWNERS; no cross-team sign-off on internals | High |
For full rule definitions and violation signals: load references/rules-core.md.
For framework-specific patterns (MF v2, Angular/Native Federation, Single SPA): load references/rules-toolchain.md.
For URL routing ownership (shell first segment, MFE deeper paths): load references/routing-ownership.md.
For fix patterns and step-by-step remediation: load references/remediation.md when the user asks how to fix a violation or requests a migration plan.
Cold start: new project
If no boundaries exist yet, ask about the highest-priority unknown first — one question per turn. Do not generate implementation code until each check is resolved.
Check 1 — Team ownership Ask: "Which team will own this micro-frontend end-to-end — design, development, deployment, and operations?" If unresolved: do not generate implementation code. Ask the user to install the micro-frontend-canvas skill and complete a canvas iteration (see https://github.com/lucamezzalira/mfe-canvas).
What ships with it
4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 266 lines · 192 tokens per session scan A eb58cf6d7e32
reviewing-mfe-boundaries is a skill published in the GitHub repository lucamezzalira/mfe-skills (51 stars, last pushed 17d ago), licensed MIT. It adds 192 tokens to every session and 3,270 once invoked, about $0.0010 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 skills, from other repositories
qt-qml-review
Invoke when the user asks to review, check, audit, or look over Qt6 QML code -- or suggest before committing. Runs deterministic linting (47+ rules) then six parallel deep- analysis agents covering bindings, layout, loaders, delegates, states, and performance. Optionally invokes system qmllint for type-level checks.…
verify-behavior
Verify or reproduce visible product behavior by driving the real UI with pi-computer-use's checked tools, requiring verified expect postconditions and durable state evidence for meaningful UI flows. Use when triage needs visual reproduction, implementation needs behavioral proof, review needs interactive confirmation…
recipe-front-review
Reviews completed frontend implementation for governing-source compliance, scope economy, repository quality, and security, then applies user-approved React corrections.
qa-frontend
Internal PostHog developer frontend/browser QA skill. Use only when a PostHog developer explicitly asks to run frontend QA, browser-test a PR, verify a UI flow against the local PostHog stack, use qa-frontend, or QA current frontend changes with browser/runtime evidence. Do not use for generic code review, PR review…
frontend-architecture
Frontend component architecture review — dispatch the component-architecture-review agent over the frontend component files to catch reusable components that should be extracted, duplicated UI patterns, prop drilling, component-granularity problems, and inconsistent component APIs as a frontend evolves. Use when the…
review-persistence-security-resources
Normative reviewer for persistence, settings, secrets, logging hygiene, resources, caches, cross-platform behavior and long-lived state in the explyt/spring-plugin IntelliJ plugin. Use when reviewing changes that touch PersistentStateComponent, settings UI, credentials, caches, service fields, logging, file paths…