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.
npx skills add JosiahSiegel/claude-plugin-marketplace --skill clerk-backend-apisgit 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/skills/josiahsiegel/claude-plugin-marketplace/clerk-backend-apis)<a href="https://agentmods.dev/skills/josiahsiegel/claude-plugin-marketplace/clerk-backend-apis"><img src="https://agentmods.dev/badge/skills/josiahsiegel/claude-plugin-marketplace/clerk-backend-apis/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/skills/josiahsiegel/claude-plugin-marketplace/clerk-backend-apis"><img src="https://agentmods.dev/badge/skills/josiahsiegel/claude-plugin-marketplace/clerk-backend-apis.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 | $0.00151 | $0.02463 |
| Opus 5.5 | $0.00060 | $0.00985 |
| Sonnet 5.5 | $0.00030 | $0.00493 |
| Haiku 4.5 | $0.00015 | $0.00246 |
Grade A, and why
clerk-backend-apis 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.
8. Test with curl or an HTTP client, not only the browser UI. How it starts
The opening of the file, as written. The whole thing — 210 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Clerk Backend APIs
Overview
Use this skill for Clerk authentication in backend services, API servers, workers, and server-to-server integrations. The key responsibilities are authenticating incoming requests, enforcing authorization on server resources, safely using the Backend API, and making cross-origin token behavior explicit.
Prefer official Clerk SDKs and middleware when available. When the target runtime lacks a first-class Clerk framework SDK, use Clerk-documented token verification and Backend API patterns rather than ad hoc JWT parsing.
Backend Integration Model
The server flow is language-independent:
- Receive request.
- Preserve auth-relevant headers and cookies through all proxies.
- Authenticate Clerk input using an official SDK/helper where available.
- Derive identity, session, organization, and token type from verified request state.
- Authorize the requested resource and action.
- Parse/validate application input.
- Perform data access or side effects.
- Return explicit
401unauthenticated or403/concealment unauthorized responses for APIs, unless using Clerk defaults intentionally.
Avoid handwritten JWT parsing unless Clerk's official docs for the target language require a lower-level path. Clerk token semantics evolve, and framework SDKs handle edge cases better than custom code.
Express Pattern
Register Clerk middleware before routes that need auth state. Use getAuth(req) in route handlers when custom JSON responses are preferred. Use requireAuth() when automatic route protection behavior fits the app.
Minimal shape:
import express from 'express'
import { clerkMiddleware, getAuth, requireAuth } from '@clerk/express'
const app = express()
app.use(clerkMiddleware())
app.get('/api/me', (req, res) => {
const { isAuthenticated, userId, orgId } = getAuth(req)
if (!isAuthenticated) return res.status(401).json({ error: 'Unauthorized' })
return res.json({ userId, orgId })
})
app.get('/api/protected', requireAuth(), (req, res) => {
res.json({ ok: true })
})
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 · 210 lines · 151 tokens per session scan A df9d4705fc24
clerk-backend-apis is a skill published in the GitHub repository JosiahSiegel/claude-plugin-marketplace (59 stars, last pushed 4mo ago), licensed MIT. It adds 151 tokens to every session and 2,463 once invoked, about $0.0006 per session on Opus 5.5. 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.
clerk-backend-apis compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| clerk-backend-apisJosiahSiegel/claude-plugin-marketplace | Skill | 59 | 4mo ago | MIT | A | 151 | Claude Code |
| mem0-oss-to-platformmem0ai/mem0 | Skill | 68k | 2d ago | Apache-2.0 | A | 217 | Claude Code, Codex |
| azure-mgmt-botservice-dotnetmicrosoft/skills | Skill | 3.2k | yesterday | MIT | A | 78 | Claude Code |
| fastapi-router-pymicrosoft/skills | Skill | 3.2k | yesterday | MIT | A | 46 | Claude Code |
| dev-runtimelangwatch/langwatch | Skill | 5.0k | yesterday | Apache-2.0 | A | 172 | Claude Code |
| api-designericrisco/rsc-harness | Skill | 503 | 2d ago | MIT | A | 105 | Claude Code, Codex |
| migrate-segw-to-raparc-mcp/arc-1 | Skill | 252 | yesterday | MIT | A | 106 | Claude Code |