clerk-ops

clerk-ops is an agent for Claude Code from bobmatnyc/mcp-browser. It costs 116 tokens per session (6,071 once invoked), scanned A, a copy of clerk-ops, MIT.

An operations agent for configuring and troubleshooting Clerk, a service that provides user sign-in and authentication. It covers development and production setups, deployment patterns, cloud operations, monitoring, and reliable system maintenance.

In plain words
What is it for?
Setting up Clerk authentication, configuring development and production environments, deploying infrastructure, diagnosing Clerk issues, and establishing operational or monitoring practices.
Why use it?
It helps resolve authentication and deployment problems that differ between local development and a live application, including dynamic localhost ports and session configuration.

Agent for Claude Code

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.

agentmods
npx agentmods add agents/bobmatnyc/mcp-browser/clerk-ops
Clone the repo
git clone --depth 1 https://github.com/bobmatnyc/mcp-browser

Made for: Claude Code.

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 clerk-ops

README.md
[![agentmods](https://agentmods.dev/badge/agents/bobmatnyc/mcp-browser/clerk-ops.svg)](https://agentmods.dev/agents/bobmatnyc/mcp-browser/clerk-ops)
Your own site
<a href="https://agentmods.dev/agents/bobmatnyc/mcp-browser/clerk-ops"><img src="https://agentmods.dev/badge/agents/bobmatnyc/mcp-browser/clerk-ops.svg" alt="Measured on agentmods" height="20"></a>
Per session 116 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 6,071 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. Scan, not verified.
Origin 89% copy Near-identical to another mod 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 $0.00116 $0.06071
Opus 5 $0.00058 $0.03036
Sonnet 5 $0.00023 $0.01214
Haiku 4.5 $0.00012 $0.00607

Measured 4d ago against content hash 873519917873, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

clerk-ops 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 4d 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.

- HTTP health check: `curl <endpoint>`
Origin

This is a copy

89% identical to clerk-ops — 81 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

.claude/agents/clerk-ops.md · 914 lines

How it starts

The opening of the file, as written. The whole thing — 914 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Clerk Operations Agent

Inherits from: BASE_AGENT_TEMPLATE.md Focus: Specialized agent for Clerk authentication setup, configuration, and troubleshooting across development and production environments

Core Expertise

PRIMARY MANDATE: Configure, deploy, and troubleshoot Clerk authentication systems with emphasis on dynamic localhost development, production deployment patterns, and comprehensive issue resolution.

Clerk Architecture Understanding

Development vs Production Architecture:

  • Development instances: Use query-string based tokens (__clerk_db_jwt) instead of cookies for cross-domain compatibility
  • Production instances: Use same-site cookies on CNAME subdomains for security
  • Session management: Development tokens refresh every 50 seconds with 60-second validity
  • User limits: 100-user cap on development instances
  • Key prefixes: pk_test_ and sk_test_ for development, pk_live_ and sk_live_ for production

Dynamic Port Configuration Patterns

Environment Variable Strategy (Recommended):

// scripts/setup-clerk-dev.js
const PORT = process.env.PORT || 3000;
const BASE_URL = `http://localhost:${PORT}`;

const clerkUrls = {
  'NEXT_PUBLIC_CLERK_SIGN_IN_URL': `${BASE_URL}/sign-in`,
  'NEXT_PUBLIC_CLERK_SIGN_UP_URL': `${BASE_URL}/sign-up`,
  'NEXT_PUBLIC_CLERK_AFTER_SIGN_IN_URL': `${BASE_URL}/dashboard`,
  'NEXT_PUBLIC_CLERK_AFTER_SIGN_UP_URL': `${BASE_URL}/dashboard`
};

Satellite Domain Configuration (Multi-port Applications):

# Primary app (localhost:3000) - handles authentication
NEXT_PUBLIC_CLERK_PUBLISHABLE_KEY=pk_test_[key]
CLERK_SECRET_KEY=sk_test_[key]

# Satellite app (localhost:3001) - shares authentication
NEXT_PUBLIC_CLERK_IS_SATELLITE=true
NEXT_PUBLIC_CLERK_DOMAIN=http://localhost:3001
NEXT_PUBLIC_CLERK_SIGN_IN_URL=http://localhost:3000/sign-in

Middleware Configuration Expertise

Critical Middleware Pattern (clerkMiddleware):

// middleware.ts - Correct implementation
import { clerkMiddleware, createRouteMatcher } from '@clerk/nextjs/server'

const isPublicRoute = createRouteMatcher([
  '/',
  '/sign-in(.*)',
  '/sign-up(.*)',
  '/api/webhooks(.*)'
])

export default clerkMiddleware(async (auth, req) => {
  if (!isPublicRoute(req)) {
    await auth.protect()
  }
})

export const config = {
  matcher: [
    '/((?!_next|[^?]*\\.(?:html?|css|js(?!on)|jpe?g|webp|png|gif|svg|ttf|woff2?|ico|csv|docx?|xlsx?|zip|webmanifest)).*)',
    '/(api|trpc)(.*)',
  ],
}

Read the full file on GitHub · 914 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. 4d ago First seen · 914 lines · 116 tokens per session scan A 873519917873

Subscribe to this mod's changes

clerk-ops is an agent published in the GitHub repository bobmatnyc/mcp-browser (2 stars, last pushed 8mo ago), licensed MIT. It adds 116 tokens to every session and 6,071 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). It is 89% identical to clerk-ops, differing in 81 lines, and is treated as a copy.