A coding-agent skill for operating Vercel from the terminal. Vercel is a platform for deploying web applications, and the Vercel CLI is its command-line tool.

Use it to deploy a local project, view deployment logs, configure environment variables, promote a preview, roll back a release, or link the project to Vercel.

It helps automate deployment and day-to-day operations from the current project directory, including builds, previews, production releases, and rollbacks.

vercel — Skill for Claude Code and Codex by helbertparanhos

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 helbertparanhos/vercel-mcp-pro --skill skill

Clone the repo

git clone --depth 1 https://github.com/helbertparanhos/vercel-mcp-pro

Made for: Claude Code, Codex.

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/helbertparanhos/vercel-mcp-pro/skill/github.svg)](https://agentmods.dev/skills/helbertparanhos/vercel-mcp-pro/skill)

Your own site

<a href="https://agentmods.dev/skills/helbertparanhos/vercel-mcp-pro/skill"><img src="https://agentmods.dev/badge/skills/helbertparanhos/vercel-mcp-pro/skill/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/helbertparanhos/vercel-mcp-pro/skill"><img src="https://agentmods.dev/badge/skills/helbertparanhos/vercel-mcp-pro/skill.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 133 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,314 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	$0.00133	$0.01314
Opus 5	$0.00067	$0.00657
Sonnet 5	$0.00027	$0.00263
Haiku 4.5	$0.00013	$0.00131

Measured 8d ago against content hash 8cc5a8db282b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

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 8d 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.

skill/SKILL.md · 97 lines

How it starts

The opening of the file, as written. The whole thing — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/vercel — Deploy e operação via Vercel CLI

Esta skill dirige a Vercel CLI para o ciclo de deploy no terminal. Ela é o par operacional do MCP vercel-mcp-pro:

CLI (esta skill) → melhor para fazer o deploy a partir do código local (git push → deploy, build, preview/prod), porque envia os arquivos do diretório atual.
MCP vercel-mcp-pro → melhor para tudo o resto via API em qualquer client: listar/inspecionar deployments, ler logs estruturados, CRUD de env/domínios/DNS/aliases/certs/webhooks/edge-config, promover, rollback, checks.

Quando a tarefa for deploy do projeto atual, prefira o CLI. Quando for consulta/gestão de recursos, prefira as tools do MCP. Diga ao usuário qual caminho está usando.

Pré-requisitos (verifique antes de agir)

CLI instalado: vercel --version. Se faltar: npm i -g vercel.
Autenticação por token (não-interativa, ideal para automação):
- Use a env var VERCEL_TOKEN (a mesma do MCP) e passe --token $VERCEL_TOKEN nos comandos, OU rode vercel login se o usuário preferir o fluxo interativo.
- Para equipes: adicione --scope <team-slug> (ou configure em .vercel/project.json via vercel link).
Projeto linkado: se não houver .vercel/project.json, rode vercel link (ou vercel pull) antes de deployar.

Nunca imprima o valor de VERCEL_TOKEN. Referencie sempre como $VERCEL_TOKEN.

Fluxos

1. Deploy de preview

vercel --token $VERCEL_TOKEN --yes

Retorna a URL de preview. --yes aceita os defaults sem prompt.

2. Deploy de produção

vercel --prod --token $VERCEL_TOKEN --yes

Confirme com o usuário antes de ir para produção (ação outward-facing).

3. Ver logs

Deploy/runtime de um deployment:

vercel logs <deployment-url-ou-id> --token $VERCEL_TOKEN

Para logs históricos/estruturados e diagnóstico de build com erro, prefira o MCP: get_build_logs / get_runtime_logs / get_deployment_events.

4. Variáveis de ambiente

vercel env add <NOME> <production|preview|development> --token $VERCEL_TOKEN
vercel env ls --token $VERCEL_TOKEN
vercel env rm <NOME> <ambiente> --token $VERCEL_TOKEN

Para CRUD em lote/programático, prefira o MCP (bulk_create_env_vars, update_env_var).

Read the full file on GitHub · 97 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.

8d ago First seen · 97 lines · 133 tokens per session scan A 8cc5a8db282b

Subscribe to this mod's changes

vercel is a skill published in the GitHub repository helbertparanhos/vercel-mcp-pro (0 stars, last pushed 6d ago), licensed MIT. It adds 133 tokens to every session and 1,314 once invoked, about $0.0007 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 2026-08-31.

Claude Code Cloud DevOps and cloud automation claude cursor deployment

ep

Workflow de deploy e gestão do Easypanel via MCP. Use sempre que o usuário pedir para fazer deploy, gerenciar projetos/serviços, configurar GitHub auto-deploy, checar logs, alterar env vars ou verificar status no Easypanel. Triggers: /ep, 'fazer deploy', 'deployar', 'redeployar', 'subir no easypanel', 'checar logs do…

helbertparanhos/easypanel-mcp-server · 142 tokens

securing-helm-chart-deployments

Secure Helm chart deployments by validating chart integrity, scanning templates for misconfigurations, and enforcing security contexts in Kubernetes releases.

xalgorix/xalgorix · 34 tokens

hosted-agents

Build background agents in sandboxed environments. Use for hosted coding agents, sandboxed VMs, Modal sandboxes, and remote coding environments.

aboalrejal-ai/skills · 33 tokens

devops-specialist

DevOps agent specializing in deployment, monitoring, and infrastructure automation.

glincker/claude-code-marketplace · 17 tokens

agent-guardrails

Stop AI agents from secretly bypassing your rules. Mechanical enforcement with git hooks, secret detection, deployment verification, and import registries. Born from real production incidents: server crashes, token leaks, code rewrites. Works with Claude Code, Clawdbot, Cursor. Install once, enforce forever.

diegosouzapw/awesome-omni-skill · 66 tokens

huggingface-llm-trainer

Train or fine-tune language and vision models using TRL (Transformer Reinforcement Learning) or Unsloth with Hugging Face Jobs infrastructure. Covers SFT, DPO, GRPO and reward modeling training methods, plus GGUF conversion for local deployment. Includes guidance on the TRL Jobs package, UV scripts with PEP 723…

aboalrejal-ai/skills · 133 tokens