vercel

vercel is a skill for Claude Code, Codex from andresquirogadev/skillsense. It costs 0 tokens per session (507 once invoked), scanned A, original, MIT.

A set of conventions for deploying applications on Vercel, a hosting platform that builds and serves web projects. It covers GitHub deployments, environment variables, and choosing between Edge and Node.js server functions.

In plain words
What is it for?
Use it when configuring Vercel deployments, preview and production environments, environment variables, or server-side routes that need database access or file handling.
Why use it?
It reduces common deployment mistakes, such as putting secrets in source code, overriding settings Vercel can detect, or choosing the wrong server runtime.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it when configuring Vercel deployments, preview and production environments, environment variables, or server-side routes that need database access or file handling.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/andresquirogadev/skillsense/vercel
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 andresquirogadev/skillsense --skill vercel
Clone the repo
git clone --depth 1 https://github.com/andresquirogadev/skillsense

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.

agentmods badge for vercel

README.md
[![agentmods](https://agentmods.dev/badge/skills/andresquirogadev/skillsense/vercel/github.svg)](https://agentmods.dev/skills/andresquirogadev/skillsense/vercel)
Your own site
<a href="https://agentmods.dev/skills/andresquirogadev/skillsense/vercel"><img src="https://agentmods.dev/badge/skills/andresquirogadev/skillsense/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.

agentmods 80×15 button for vercel

Your own site · 80×15
<a href="https://agentmods.dev/skills/andresquirogadev/skillsense/vercel"><img src="https://agentmods.dev/badge/skills/andresquirogadev/skillsense/vercel.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 507 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00000 $0.00507
Opus 5 $0.00000 $0.00253
Sonnet 5 $0.00000 $0.00101
Haiku 4.5 $0.00000 $0.00051

Measured 9d ago against content hash 92fc6c3fdccb, 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 9d 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.

packages/catalog/skills/vercel/SKILL.md · 44 lines

How it starts

The opening of the file, as written. The whole thing — 44 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Vercel Skill

You are deploying to Vercel. Apply these conventions.

Deployment

  • Connect the GitHub repo to Vercel — every push to main deploys to production; every PR creates a preview deployment.
  • Use vercel.json only for rewrites, redirects, headers, and cron jobs — avoid overriding build settings that Vercel auto-detects.
  • Set environment variables in the Vercel dashboard per environment (Production / Preview / Development); use Vercel CLI (vercel env pull) to sync to .env.local.

Edge vs Serverless Functions

  • Choose the runtime per route with export const runtime = 'edge' or 'nodejs'.
  • Edge runtime: ultra-low latency, globally distributed, but limited Node.js APIs (no fs, limited crypto).
  • Node.js runtime: full Node.js APIs, longer cold start — use for DB connections, file I/O.
  • Connect to databases from the Edge with connection-pooled drivers (@neondatabase/serverless, Supabase edge client).

Environment Variables

  • Access env vars with process.env.VAR_NAME — Vercel injects them at build time (public vars) and at runtime (secret vars).
  • Use NEXT_PUBLIC_ prefix for client-side accessible variables in Next.js.
  • Never commit .env files; use .env.local for local development (gitignored).

Image Optimization

  • Vercel's Image Optimization runs next/image optimizations automatically — set domains or remotePatterns in next.config.ts for external image hosts.
  • Cache optimized images at the CDN edge by setting an aggressive Cache-Control header on image routes.

Cron Jobs

// vercel.json
{
  "crons": [{ "path": "/api/cron/cleanup", "schedule": "0 2 * * *" }]
}
  • Protect cron routes by verifying Authorization: Bearer ${CRON_SECRET} header.

Performance

  • Use Vercel's Analytics (@vercel/analytics) and Speed Insights (@vercel/speed-insights) for Core Web Vitals monitoring.
  • Enable ISR (Incremental Static Regeneration) on Next.js pages with revalidate to cache at the CDN.
  • Use Vercel KV (Redis), Vercel Postgres, or Vercel Blob for serverless-compatible storage.

Read the full file on GitHub · 44 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.

  1. 9d ago First seen · 44 lines · 0 tokens per session scan A 92fc6c3fdccb

Subscribe to this mod's changes

vercel is a skill published in the GitHub repository andresquirogadev/skillsense (2 stars, last pushed 5mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 507 tokens. 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.

Related

Other skills, from other repositories

rework-rate

Measure and interpret PR rework rate — the emerging 5th DORA metric.

bradygaster/squad · 20 tokens

awesome-azd-template-submit

Submit an azd template to the awesome-azd gallery. Use when asked to submit, add, or contribute a template to awesome-azd. Requires only a GitHub repository URL — all metadata (title, description, languages, frameworks, Azure services, IaC) is auto-detected by the submission pipeline.

Azure/awesome-azd · 72 tokens

My Skill

Content here.

bradygaster/squad · 2 tokens

ralphctl-code-review-and-quality

Multi-phase code-quality skill — primary frame for the evaluator role in Execute, the architecture axis in Plan, and correctness/readability in Refine. Multi-axis code review with severity vocabulary. Use when you are the evaluator assessing a generator's output, and when reviewing any change before signalling…

lukas-grigis/ralphctl · 76 tokens

ralphctl-test-driven-development

Execute-phase skill — write the failing test before the code that makes it pass; for bug fixes, this is the reproduction test itself. Use for any logic change, bug fix, or behavioural modification; for the full root-cause triage pipeline around an unexpected failure, see ralphctl-debugging-and-error-recovery.

lukas-grigis/ralphctl · 72 tokens

ralphctl-idea-refinement

Ideation skill — refine a raw, unshaped idea into a sharp, buildable concept through divergent expansion (variation lenses like inversion, simplification, audience shift) followed by convergent stress-testing (user value, feasibility, differentiation), ending in a one-pager with explicit assumptions and a "Not Doing"…

lukas-grigis/ralphctl · 121 tokens