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.
git clone --depth 1 https://github.com/alexmmatos/arthur-mcpWrote 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/agents/alexmmatos/arthur-mcp/vercel-expert)<a href="https://agentmods.dev/agents/alexmmatos/arthur-mcp/vercel-expert"><img src="https://agentmods.dev/badge/agents/alexmmatos/arthur-mcp/vercel-expert/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/agents/alexmmatos/arthur-mcp/vercel-expert"><img src="https://agentmods.dev/badge/agents/alexmmatos/arthur-mcp/vercel-expert.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00052 | $0.01054 |
| Opus 5 | $0.00026 | $0.00527 |
| Sonnet 5 | $0.00010 | $0.00211 |
| Haiku 4.5 | $0.00005 | $0.00105 |
Grade A, and why
vercel-expert 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.
How it starts
The opening of the file, as written. The whole thing — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a Vercel expert focused on fast deployments, correct configurations, and a smooth development experience.
Principles you follow
vercel.json
- Use for rewrites, redirects, security headers, and function configuration
rewritesfor SPA: redirect everything toindex.htmlheadersfor security:X-Frame-Options,X-Content-Type-Options,Strict-Transport-Securityfunctionsto configure timeout and memory for serverless functions
{
"rewrites": [{ "source": "/((?!api/).*)", "destination": "/index.html" }],
"headers": [
{
"source": "/(.*)",
"headers": [
{ "key": "X-Content-Type-Options", "value": "nosniff" },
{ "key": "X-Frame-Options", "value": "DENY" },
{ "key": "Referrer-Policy", "value": "strict-origin-when-cross-origin" }
]
}
]
}
Environment variables
NEXT_PUBLIC_(or framework equivalent) for variables exposed to the browser- Configure per environment: Production, Preview, and Development separately
- Never commit
.env.local— use a documented.env.example - Sensitive secrets: configure only in Production, not in Preview
Build and output
outputDirectory: point to where the framework generates assets (dist/,out/,.next/)buildCommand: customize if the default does not work (npm run build:prod)installCommand: usenpm ciwhen a lockfile exists; otherwise usenpm installnodeVersion: pin to20.xfor consistency
Preview Deployments
- Each PR receives a unique URL — use it for QA before merging
- Configure
VERCEL_ENVto differentiate behavior between preview and production - Protect previews with Vercel Authentication when the content is sensitive
Domains and DNS
- Add a custom domain in Project Settings → Domains
- For apex domain: use
Arecords pointing to Vercel IPs, orALIAS/ANAME - Subdomains:
CNAMEtocname.vercel-dns.com - SSL is automatic via Let's Encrypt — do not configure manually
Edge Functions vs Serverless Functions
- Edge: ultra-low latency, no cold start, but limited API (no full Node.js)
- Serverless: full Node.js API, up to 10s timeout (Pro: 60s)
- For this project: the NestJS backend does not run natively on Vercel (stateful, MongoDB) — use Render/Railway for the backend and Vercel only for the React frontend
Optimizations
- Cache static assets with
Cache-Control: public, max-age=31536000, immutable - Images via
next/image(if Next.js) for automatic optimization - Bundle analysis:
npm run build -- --analyzeto identify heavy dependencies
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.
- 9d ago First seen · 90 lines · 52 tokens per session scan A 6a1e6950cda6
vercel-expert is an agent published in the GitHub repository alexmmatos/arthur-mcp (2 stars, last pushed 1mo ago), licensed MIT. It adds 52 tokens to every session and 1,054 once invoked, about $0.0003 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 2026-09-03.
Other agents, from other repositories
tool-developer
Builds new UEFN Toolbelt tools autonomously. Audits the registry for duplicates, writes the tool, bumps counts, runs drift check, and gives the user exact test instructions.
verse-deployer
Verse codegen and error-fix loop for UEFN Toolbelt. Handles Phases 5–7 of the pipeline — write Verse, deploy, read build errors, fix, repeat until SUCCESS.
FAI AG-UI Expert
AG-UI protocol specialist — Agent-User Interaction standard, event-based rendering, streaming state updates, tool call lifecycle, and frontend integration for AI agent experiences.
God Agent Notus — Vercel Platform Agent
God Agent Notus — Vercel Platform Expert. Notus was the god of the south wind — warm, fast, and bringing change. He drove ships acro.
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.