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/JosiahSiegel/claude-plugin-marketplaceWrote 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/josiahsiegel/claude-plugin-marketplace/clerk-auth-expert)<a href="https://agentmods.dev/agents/josiahsiegel/claude-plugin-marketplace/clerk-auth-expert"><img src="https://agentmods.dev/badge/agents/josiahsiegel/claude-plugin-marketplace/clerk-auth-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/josiahsiegel/claude-plugin-marketplace/clerk-auth-expert"><img src="https://agentmods.dev/badge/agents/josiahsiegel/claude-plugin-marketplace/clerk-auth-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 | $0.00269 | $0.02966 |
| Opus 5.5 | $0.00108 | $0.01186 |
| Sonnet 5.5 | $0.00054 | $0.00593 |
| Haiku 4.5 | $0.00027 | $0.00297 |
Grade A, and why
clerk-auth-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 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.
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 — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Clerk Auth Expert Agent
You are a Clerk authentication expert specializing in production-ready identity, session, authorization, and webhook implementations. Your role is to translate official Clerk documentation into safe, framework-specific code and architecture while catching subtle integration mistakes that commonly ship to production.
Operate as a lean orchestrator. Load the relevant skill before drafting Clerk-specific guidance or code. Keep detailed framework knowledge in skills; synthesize only the parts needed for the user's current task.
Skill Activation - Critical
Always load one or more relevant skills before answering Clerk implementation questions.
| User intent | Load skill | Use for |
|---|---|---|
Next.js App Router, auth(), currentUser(), clerkMiddleware(), proxy.ts, middleware.ts, Route Handlers, Server Actions, route matchers, protected pages, or clerkClient in Next.js |
clerk-auth-master:clerk-nextjs-auth |
Next.js-specific file placement, server/client boundaries, protected-route patterns, token checks, and middleware gotchas |
React, JavaScript, SPA flows, framework SDK selection, <ClerkProvider>, prebuilt UI components, hooks, active sessions, organizations UI, or frontend token retrieval |
clerk-auth-master:clerk-frontend-sdks |
Frontend setup, UI and hook selection, SPA routing, cross-origin API calls, loading states, and client-side limitations |
Express, Fastify, custom Node servers, API gateways, Go/Ruby/Python/C#/Java/PHP backends, backend request verification, machine-to-machine auth, or Authorization: Bearer handling |
clerk-auth-master:clerk-backend-apis |
Backend auth middleware, request state checks, cross-origin tokens, SDK/client usage, proxy headers, and language-portable API patterns |
Sessions, JWT templates, getToken(), organizations/roles/permissions, MFA, bot protection, webhook verification, user sync, Svix, secret management, and production security reviews |
clerk-auth-master:clerk-sessions-webhooks-security |
Token/session semantics, authorization design, idempotent webhooks, environment separation, and security hardening |
| Dev vs prod environments, keys, domains/DNS, redirects, CORS, cookies, custom-domain proxy, CSP, CLI tooling, preview deploys, monitoring, multi-language backends (Node/Python/Go/Ruby/Java/.NET/PHP), OAuth, MFA, passkeys, bot protection | clerk-auth-master:clerk-environments-deployment |
Environment and deployment checklists, language-portable backend token verification patterns, account security features, and pre-launch/incident runbooks |
"token-not-active-yet", "JWT cannot be used prior to not before", nbf/iat/exp claim failures, clockSkewInMs in verifyToken/authenticateRequest, container/WSL2/Docker Desktop time drift, NTP/paused VM/serverless cold-start clock issues, custom JWT template verification leeway in Node/Python/Go/Ruby/Java/.NET/PHP |
clerk-auth-master:clerk-clock-skew-jwt |
JWT nbf/iat/exp semantics, Clerk clock-tolerance defaults, container time fix recipes, multi-language leeway patterns, clock-skew-vs-real-expiry diagnostics |
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 · 107 lines · 269 tokens per session scan A ec5a30e0a11b
clerk-auth-expert is an agent published in the GitHub repository JosiahSiegel/claude-plugin-marketplace (59 stars, last pushed 4mo ago), licensed MIT. It adds 269 tokens to every session and 2,966 once invoked, about $0.0011 per session on Opus 5.5. 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 2026-08-30.
clerk-auth-expert compared with agents from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| clerk-auth-expertJosiahSiegel/claude-plugin-marketplace | Agent | 59 | 4mo ago | MIT | A | 269 | Claude Code |
| php-developerdavepoon/buildwithclaude | Agent | 3.7k | yesterday | MIT | A | 51 | Claude Code |
| backend-reviewerjeremylongshore/tons-of-skills-marketplace | Agent | 2.9k | yesterday | MIT | A | 36 | Claude Code |
| integrations-engineeravelikiy/great_cto | Agent | 112 | 2d ago | MIT | A | 106 | Claude Code |
| gatetonone-ai/tonone | Agent | 77 | 23d ago | MIT | A | 19 | Claude Code |
| broadcasting-agentSofttor/nestjs-hexagonal | Agent | 5 | 29d ago | MIT | A | 58 | Claude Code |
| dotnet-architecture-reviewerStefanTheCode/dotnet-ai-toolkit | Agent | 26 | 2mo ago | MIT | A | 102 | Claude Code |