vercel-reviewer

vercel-reviewer is an agent for Claude Code from TheBeardedBearSAS/claude-craft. It costs 50 tokens per session (7,588 once invoked), scanned A, original, MIT.

A code-review agent for applications deployed on Vercel, a platform for hosting websites and server-side code.

In plain words
What is it for?
It is for reviewing Vercel configuration, serverless functions, incremental caching, scheduled jobs, storage, analytics, and environment variables. It does not review framework-specific Next.js code.
Why use it?
It helps find deployment settings that can break releases, expose secrets, leave scheduled endpoints unprotected, or cause caching conflicts.

Agent for Claude Code

Written for Claude Code: effort in frontmatter. Also seen: model in frontmatter; names the NotebookEdit tool.

Part of the claude-craft plugin — 56 skills, 94 commands, 47 agents, 5 hooks shipped together

Good fit It is for reviewing Vercel configuration, serverless functions, incremental caching, scheduled jobs, storage, analytics, and environment variables. It does not review framework-specific Next.js code.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/thebeardedbearsas/claude-craft/vercel-reviewer
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.

Clone the repo
git clone --depth 1 https://github.com/TheBeardedBearSAS/claude-craft

Made for: Claude Code.

Or install claude-craft, the plugin that ships this one along with the rest of its 56 skills, 94 commands, 47 agents, 5 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.

agentmods badge for vercel-reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/thebeardedbearsas/claude-craft/vercel-reviewer/github.svg)](https://agentmods.dev/agents/thebeardedbearsas/claude-craft/vercel-reviewer)
Your own site
<a href="https://agentmods.dev/agents/thebeardedbearsas/claude-craft/vercel-reviewer"><img src="https://agentmods.dev/badge/agents/thebeardedbearsas/claude-craft/vercel-reviewer/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-reviewer

Your own site · 80×15
<a href="https://agentmods.dev/agents/thebeardedbearsas/claude-craft/vercel-reviewer"><img src="https://agentmods.dev/badge/agents/thebeardedbearsas/claude-craft/vercel-reviewer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 50 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 7,588 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00050 $0.07588
Opus 5 $0.00025 $0.03794
Sonnet 5 $0.00010 $0.01518
Haiku 4.5 $0.00005 $0.00759

Measured 10d ago against content hash f7ee640d2fbd, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

vercel-reviewer scanned grade A with 1 finding 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 10d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

| **curl -I** / browser devtools Network tab | Inspecting `x-vercel-cache`, `Cache-Control` on deployed routes |
.claude/agents/vercel-reviewer.md · 822 lines

How it starts

The opening of the file, as written. The whole thing — 822 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Vercel Platform Reviewer Agent

Identity

I am a specialist in reviewing code for the Vercel deployment platform, framework-agnostic. My scope covers vercel.json configuration (rewrites, redirects, headers, regions, functions, crons), Serverless Functions on the Node.js runtime / Fluid Compute, ISR cache primitives (stale-while-revalidate at the platform level), Cron Jobs, Vercel Storage (Blob native; Postgres/KV via Marketplace only), Analytics/Speed Insights, and environment-variable/Preview-Deployment handling. I do not cover Next.js itself — its routing, rendering, or data-fetching conventions (revalidatePath, revalidateTag, App Router, etc.) are out of scope; those belong to the framework's own stack (/react:*, /vuejs:*, /angular:*), which documents its own integration with Vercel's build output in its tooling.md. I do not run a generic audit — I detect what breaks the deploy config, exposes a secret, leaves a Cron endpoint unguarded, or silently conflicts cache ownership between vercel.json and the framework.

Scoring System (100 points)

Category Points Focus
vercel.json & Architecture 30 Schema correctness, rewrites/redirects/headers, regions, functions block, project-shape fit
Functions & Runtime Choice 20 Node.js/Fluid Compute vs legacy Edge runtime, handler signature quality, cold-start awareness
Security & Env Handling 25 Secrets/env vars, cron auth guard, CORS/CSP headers, Marketplace credential scoping
ISR/Caching & Tests 25 Cache-header correctness (x-vercel-cache), revalidation strategy, handler test coverage

1. vercel.json & Architecture (30 points)

Decision tree: vercel.json placement and schema validity

Is a vercel.json present at the project root?
  NO  --> Is the project trivial (single static site, zero rewrites/headers/functions/crons)?
          YES --> OK (Vercel's zero-config detection is sufficient)
          NO  --> MAJOR: rewrites/headers/functions/crons cannot be expressed without vercel.json
  YES --> Does it reference "$schema": "https://openapi.vercel.sh/vercel.json" (or an
          equivalent SchemaStore entry)?
          NO  --> Is the config non-trivial (more than one top-level key beyond "version")?
                  YES --> CRITICAL: no schema validation on a config surface that fails
                          silently at deploy time (typo'd glob, wrong nesting, unknown key)
                  NO  --> MINOR
          YES --> Does "version" equal 2 (current config version)?
                  NO  --> MAJOR: deprecated or invalid version key
                  YES --> OK

Read the full file on GitHub · 822 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. 10d ago First seen · 822 lines · 50 tokens per session scan A f7ee640d2fbd

Subscribe to this mod's changes

vercel-reviewer is an agent published in the GitHub repository TheBeardedBearSAS/claude-craft (105 stars, last pushed 7d ago), licensed MIT. It adds 50 tokens to every session and 7,588 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other agents, from other repositories

cloud-architect

Multi-cloud architecture, cost optimization, serverless vs containers, disaster recovery, and infrastructure design specialist. Use for high-level architecture decisions, cloud migration planning, or cost optimization. Trigger phrases: cloud, AWS, GCP, Azure, serverless, containers, Kubernetes, infrastructure, cost…

travisjneuman/.claude · 69 tokens

deep-code-reviewer

Thorough 6-aspect code review covering correctness, security, performance, maintainability, testing, and documentation. Use for comprehensive PR reviews or code quality audits.

travisjneuman/.claude · 38 tokens

serverless-specialist

AWS Lambda, Cloudflare Workers, Vercel Edge Functions, and serverless architecture specialist. Use when building serverless functions, optimizing cold starts, or designing event-driven serverless systems. Trigger phrases: serverless, Lambda, Edge Functions, Workers, Vercel, Cloudflare Workers, cold start, function as…

travisjneuman/.claude · 72 tokens

parity-check

Audit code migrations for missing functionality. Compares source (legacy) against target (new) to find gaps in behavior, edge cases, i18n, and tests.

helderberto/agent-skills · 38 tokens

phase-verifier

Fresh-context acceptance verifier dispatched by /implementation:implement-dispatch at phase boundaries: checks a phase's binary acceptance criteria against the actual diff with the orchestrator's rationale withheld, and returns a per-criterion verdict grounded in direct evidence. Its tool cage bars Edit/Write and…

melodic-software/claude-code-plugins · 76 tokens

frontend-architect

Evaluate frontend architecture for deep modules, component design, and structural health. Use when planning features or auditing existing code.

helderberto/agent-skills · 27 tokens