vercel/microfrontends is a library for splitting a large web application into independently developed applications called microfrontends. It supports microfrontend setups using frameworks and tools including Next.js, SvelteKit, React Router, Vite, and React, including gradual migrations and local development.
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 vercel/microfrontends --skill vercel-microfrontendsgit clone --depth 1 https://github.com/vercel/microfrontendsWrote 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/vercel/microfrontends/vercel-microfrontends)<a href="https://agentmods.dev/skills/vercel/microfrontends/vercel-microfrontends"><img src="https://agentmods.dev/badge/skills/vercel/microfrontends/vercel-microfrontends/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/vercel/microfrontends/vercel-microfrontends"><img src="https://agentmods.dev/badge/skills/vercel/microfrontends/vercel-microfrontends.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket pass
- Snyk warn
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 | $0.00122 | $0.00795 |
| Opus 5.5 | $0.00049 | $0.00318 |
| Sonnet 5.5 | $0.00024 | $0.00159 |
| Haiku 4.5 | $0.00012 | $0.00080 |
Grade A, and why
vercel-microfrontends 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 1mo 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 — 39 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Vercel Microfrontends
Split a large application into independently deployable units that render as one cohesive app. Vercel handles routing on its global network using microfrontends.json.
Core concepts: default app (has microfrontends.json, serves unmatched requests) · child apps (have routing path patterns) · asset prefix (prevents static-asset collisions) · independent deployments.
Frameworks: Next.js (App Router + Pages Router), SvelteKit, React Router, Vite — all via @vercel/microfrontends.
CLI (vercel microfrontends / vercel mf):
create-group— create a new group; interactive by default, or fully non-interactive with--non-interactive(options:--name,--project(repeatable),--default-app,--default-route,--project-default-route(repeatable, format:<project>=<route>, required for each non-default project in non-interactive mode),--yesto skip confirmation prompt); note:--non-interactiveis blocked if adding the projects would exceed the free tier limit — the user must confirm billing changes interactivelyadd-to-group— add the current project to an existing group; requires interactive terminal (options:--group,--default-route)remove-from-group— remove the current project from its group; requires interactive terminal (option:--yesskips project-link prompt only)delete-group— delete a group and all its settings, irreversible; requires interactive terminal (option:--groupto pre-select group)pull— pull remotemicrofrontends.jsonfor local development (option:--dpl)microfrontends proxy— local dev proxy ·microfrontends port— print auto-assigned port
Finding Detailed Information
This skill includes detailed reference docs in the references/ directory. Do not read all references upfront. Instead, search or grep the relevant file when the user asks about a specific topic:
| Topic | Reference file |
|---|---|
Getting started, quickstart, framework setup, microfrontends.json schema, fields, naming, examples |
references/configuration.md |
| Path expressions, asset prefixes, flag-controlled routing, middleware | references/path-routing.md |
| Local proxy setup, polyrepo config, Turborepo, ports, deployment protection | references/local-development.md |
Inspecting groups (inspect-group), adding/removing projects, fallback environments, navigation, observability |
references/managing-microfrontends.md |
Testing utilities (validateMiddlewareConfig, validateRouting, etc.), debug headers, common issues |
references/troubleshooting.md |
| Deployment protection, Vercel Firewall, WAF rules for microfrontends | references/security.md |
What ships with it
8 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.
- 1mo ago First seen · 39 lines · 122 tokens per session scan A b32ded2caabe
vercel-microfrontends is a skill published in the GitHub repository vercel/microfrontends (45 stars, last pushed 4d ago), licensed MIT. It adds 122 tokens to every session and 795 once invoked, about $0.0005 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 skills, from other repositories
adapter-aws-lambda
Deploy tRPC on AWS Lambda with awsLambdaRequestHandler() from @trpc/server/adapters/aws-lambda for API Gateway v1 (REST, APIGatewayProxyEvent) and v2 (HTTP, APIGatewayProxyEventV2), and Lambda Function URLs. Enable response streaming with awsLambdaStreamingRequestHandler() wrapped in awslambda.streamifyResponse().…
adapter-fetch
Deploy tRPC on WinterCG-compliant edge runtimes with fetchRequestHandler() from @trpc/server/adapters/fetch. Supports Cloudflare Workers, Deno Deploy, Vercel Edge Runtime, Astro, Remix, SolidStart. FetchCreateContextFnOptions provides req (Request) and resHeaders (Headers) for context creation. The endpoint option…
verify
Build/launch/drive recipe for verifying apps/docs changes at runtime (demos, docs pages, llms.txt).
deploy-release
Prepare and verify a staged or production deployment with rollback and smoke checks.
mobile-web-app
Add router-agnostic, native app-like page transitions to mobile web apps with SSGOI. Explore live drill, sheet, slide, and zoom demos at https://ssgoi.dev. Use when building or improving a mobile web app's routed page structure, layouts, or transitions, or when a project uses SSGOI or an @ssgoi package.
system-design-building-blocks
Select infrastructure components by the constraint each removes: load balancers, caches and invalidation, queues and pub/sub, CDN, API gateway, rate limiting, consistent hashing. Use when choosing cache, queue, replica, or edge layers; defer engine tuning to the database category.