Borrowing it
Nothing to install: this file belongs to bobmatnyc/mcp-browser. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/bobmatnyc/mcp-browser/main/.claude/agents/clerk-ops.mdgit clone --depth 1 https://github.com/bobmatnyc/mcp-browserWrote 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/bobmatnyc/mcp-browser/clerk-ops)<a href="https://agentmods.dev/agents/bobmatnyc/mcp-browser/clerk-ops"><img src="https://agentmods.dev/badge/agents/bobmatnyc/mcp-browser/clerk-ops/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/bobmatnyc/mcp-browser/clerk-ops"><img src="https://agentmods.dev/badge/agents/bobmatnyc/mcp-browser/clerk-ops.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 | $0.00116 | $0.06071 |
| Opus 5.5 | $0.00046 | $0.02428 |
| Sonnet 5.5 | $0.00023 | $0.01214 |
| Haiku 4.5 | $0.00012 | $0.00607 |
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 2mo 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>` 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.
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_andsk_test_for development,pk_live_andsk_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)(.*)',
],
}
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.
- 2mo ago First seen · 914 lines · 116 tokens per session scan A 873519917873
clerk-ops is an agent published in the GitHub repository bobmatnyc/mcp-browser (2 stars, last pushed 10mo ago), licensed MIT. It adds 116 tokens to every session and 6,071 once invoked, about $0.0005 per session on Opus 5.5. 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.
clerk-ops compared with agents from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| clerk-opsbobmatnyc/mcp-browser | Agent | 2 | 10mo ago | MIT | A | 116 | Claude Code |
| security-validatorihatesea69/kiro-kit | Agent | 19 | 2mo ago | MIT | A | 46 | Claude Code |
| cloud-architectDokhacgiakhoa/Agent-Skills-4-Vibe-Coding-CLI | Agent | 512 | 4mo ago | none | A | 64 | Claude Code |
| God Agent Notus — Vercel Platform AgentHolley-Studio/thesmos-governance | Agent | 2 | 11d ago | none | A | 46 | Claude Code |
| playwright-test-generatormicrosoft/playwright | Agent | 99k | yesterday | Apache-2.0 | A | 151 | Claude Code |
| .NET-Notebook-Migration-Agentmicrosoft/ai-agents-for-beginners | Agent | 79k | 4d ago | MIT | A | 33 | Claude Code |
| code-revieweranthropics/claude-cookbooks | Agent | 54k | 2d ago | MIT | A | 52 | Claude Code |