What is stack-vercel?

A Vercel knowledge guide for building and deploying web applications with Vercel's frontend hosting platform, including Next.js and server-side functions.

Use it when working with Next.js, Vercel Functions, deployments, caching, scheduled jobs, queues, or Vercel storage services.

It gives the existing team roles a shared place to find Vercel-specific guidance and current reference material.

stack-vercel — Skill for Claude Code by e-t-y-b/etyb-skills

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.

Any agent

npx skills add e-t-y-b/etyb-skills --skill vercel

Clone the repo

git clone --depth 1 https://github.com/e-t-y-b/etyb-skills

Made for: Claude Code.

Or install etyb, the plugin that ships this one along with the rest of its 14 skills, 5 agents, 4 hooks.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/e-t-y-b/etyb-skills/vercel/github.svg)](https://agentmods.dev/skills/e-t-y-b/etyb-skills/vercel)

Your own site

<a href="https://agentmods.dev/skills/e-t-y-b/etyb-skills/vercel"><img src="https://agentmods.dev/badge/skills/e-t-y-b/etyb-skills/vercel/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/e-t-y-b/etyb-skills/vercel"><img src="https://agentmods.dev/badge/skills/e-t-y-b/etyb-skills/vercel.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 251 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 4,289 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.

Model	Per session	Once invoked
Fable 5.1	$0.00251	$0.04289
Opus 5.5	$0.00100	$0.01716
Sonnet 5.5	$0.00050	$0.00858
Haiku 4.5	$0.00025	$0.00429

Measured 1mo ago against content hash d95589a50134, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

stack-vercel 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.

stacks/vercel/SKILL.md · 143 lines

How it starts

The opening of the file, as written. The whole thing — 143 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Vercel Stack — Team Briefing

This is a knowledge overlay, not a new specialist. The existing ETYB team does the work — backend-architect writes the backend code, devops-engineer wires the deploys, security-engineer enforces the boundary. This pack tells each role where the current Vercel knowledge lives.

Where the full briefing lives

The full Stack briefing lives in this same folder. Per-product and per-role pages are siblings of this SKILL.md. Every page carries last_verified_on stamps and authoritative-source URLs in its frontmatter; see skills/etyb/core/knowledge-currency.md for the drift-check protocol that uses them.

Stack briefing: stacks/vercel/index.md
Per-product pages: stacks/vercel/<product>.md — one per entry in products_covered above
Per-role views: stacks/vercel/<role>.md — one per role in applies_to_roles above

When ETYB is installed locally these are read directly from disk. For third-party agents without the install, the same content is reachable as raw markdown at https://raw.githubusercontent.com/e-t-y-b/etyb-skills/main/stacks/vercel/<page>.md.

When delegate_to_skills (frontmatter above) lists a first-party vendor MCP/skill that's installed in the user's environment, ETYB defers to it first. The in-repo Stack content is the curated fallback.

What changed in 2025-2026 that older training data misses

Critical context — an LLM with a 2024 cutoff will get these wrong:

Next.js 16 shipped (late 2025) with Cache Components as the recommended caching model. The 'use cache' directive at file, function, or component scope, paired with cacheLife() and cacheTag(), is the new default — replacing ad-hoc fetch(..., { next: { revalidate } }), unstable_cache, and export const revalidate = N for most cases. Old patterns still work in 15.x, but new builds should adopt Cache Components.
Partial Prerendering (PPR) is GA and the default rendering model for new App Router projects in Next.js 16. A single route can ship a static shell with streamed Suspense holes — this is neither SSG, SSR, nor ISR in the classical sense. Mental models built before PPR will fight the framework.
Fluid Compute went GA in 2025 and changed Vercel Functions billing/concurrency math fundamentally. Functions now multiplex in-process concurrency, bill on active CPU rather than wall-clock GB-seconds, and dynamically scale CPU within a single instance. "Cold start vs warm" reasoning from the pre-Fluid era is wrong.
Vercel Postgres is Neon under the hood. Old @vercel/postgres SDK calls still work but the Marketplace direction is for users to provision Neon (or another Marketplace Postgres) directly. New projects should use @neondatabase/serverless rather than reaching for @vercel/postgres.
Vercel KV is a Marketplace integration, typically powered by Upstash. New code should treat Marketplace as the primary path.
Vercel Sandbox GA'd in 2025 — microVM-isolated execution for running untrusted code (AI-generated code, agent tool outputs, user-submitted scripts). If a request involves "let an LLM run code" or "execute user-submitted code," Sandbox is the answer, not a homegrown VM2/subprocess.
Vercel Workflow ships durable functions (long-running, multi-step, replay-safe) for background jobs and AI agent orchestration. Don't reach for Temporal/Inngest on Vercel before checking whether Workflow fits.
Vercel Queues ships first-party producer/consumer queues with visibility timeouts and DLQs.
Vercel AI SDK v5+ is a major rewrite. The streaming UI primitives (streamUI, experimental_StreamingReactResponse) from v3 are deprecated. Current canon: streamText, generateText, generateObject, streamObject, tool() definitions, useChat() v2, plus AI Elements — a shadcn-layered component library specifically for AI UIs.
AI Gateway routes across providers (Anthropic, OpenAI, Google, Mistral, xAI, Groq, Fireworks, Bedrock, etc.) with observability, caching, rate limiting, and fallback. Use @ai-sdk/gateway + gateway('anthropic/claude-sonnet-4.7') etc.
Turbopack is the production build path for Next.js 16+ (stable for dev since Next.js 15, stable for build is rolling out). Webpack is still supported but no longer the default story.
after() (formerly unstable_after) is GA: schedule work after the response is sent without blocking the user.
taintObjectReference / taintUniqueValue are the canonical guard against accidentally serializing server-only objects/secrets into a Client Component.

Read the full file on GitHub · 143 lines

Files

What ships with it

37 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.

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.

1mo ago First seen · 143 lines · 251 tokens per session scan A d95589a50134

Subscribe to this mod's changes

stack-vercel is a skill published in the GitHub repository e-t-y-b/etyb-skills (11 stars, last pushed 3mo ago), licensed MIT. It adds 251 tokens to every session and 4,289 once invoked, about $0.0010 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 2026-08-31.

Claude Code Cloud DevOps and cloud Frontend agentskills ai-agent architecture

architecture-diagram

Dark-themed SVG architecture/cloud/infra diagrams as HTML.

mateaix/mateclaw · 15 tokens

routine

Manage CocoRoutine Snowflake task scheduling. Usage: $routine list, $routine schedule --cadence , $routine disable , $routine delete .

Snowflake-Labs/cocoplus · 44 tokens

aws-architecture-diagram

AWS architecture diagrams — generate visual network topology diagrams from live AWS infrastructure. Use when drawing AWS network diagrams, visualizing VPCs, mapping Transit Gateway topology, or generating architecture documentation.

automateyournetwork/netclaw · 43 tokens

capacity-and-cost-engineering

Model technical capacity, unit cost, and budget constraints connected to demand, performance, and reliability decisions. Use when projecting capacity from growth forecasts, sizing for peak events, designing cost-aware scaling policies, defining budget thresholds or quota/rate-limit enforcement, running or planning…

magnus919/agent-skills · 168 tokens

vllm

Operate, configure, benchmark, and troubleshoot vLLM inference servers: Docker and Kubernetes deployment, quantization-aware model configuration (tensor parallelism, KV cache), OpenAI-compatible API serving, throughput and latency benchmarking, continuous batching tuning, GPU operation, and upgrade/rollback. Use when…

magnus919/agent-skills · 196 tokens

traefik

Deploy, configure, and troubleshoot Traefik v3 reverse proxy — covers all providers, routing, TLS/ACME, middlewares, and production patterns with YAML examples. Load when setting up or debugging a Traefik instance. Do not use this skill for unrelated requests; route to the nearest named specialist.

magnus919/agent-skills · 67 tokens