convex-workos

convex-workos is a skill for Claude Code from PolarCoding85/convex-agent-skillz. It costs 46 tokens per session (1,855 once invoked), scanned A, original, MIT.

Integration instructions for using WorkOS AuthKit, an authentication service for user sign-in and account management, with Convex, a backend platform. It shows the required Convex authentication settings, environment variables, and client setup patterns.

In plain words
What is it for?
Setting up AuthKit with Convex, configuring React or Next.js clients, adding the two required token providers, handling user provisioning, and troubleshooting WorkOS-specific authentication problems.
Why use it?
It helps avoid configuration errors caused by WorkOS using two different types of JSON Web Token issuer, or token source. It also clarifies which credentials and redirect settings belong in each application environment.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

Good fit Setting up AuthKit with Convex, configuring React or Next.js clients, adding the two required token providers, handling user provisioning, and troubleshooting WorkOS-specific authentication problems.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/polarcoding85/convex-agent-skillz/convex-workos-skill
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.

Any agent
npx skills add PolarCoding85/convex-agent-skillz --skill convex-workos-skill
Clone the repo
git clone --depth 1 https://github.com/PolarCoding85/convex-agent-skillz

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 convex-workos

README.md
[![agentmods](https://agentmods.dev/badge/skills/polarcoding85/convex-agent-skillz/convex-workos-skill.svg)](https://agentmods.dev/skills/polarcoding85/convex-agent-skillz/convex-workos-skill)
Your own site
<a href="https://agentmods.dev/skills/polarcoding85/convex-agent-skillz/convex-workos-skill"><img src="https://agentmods.dev/badge/skills/polarcoding85/convex-agent-skillz/convex-workos-skill.svg" alt="Measured on agentmods" height="20"></a>
Per session 46 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,855 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found 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 5.1 $0.00046 $0.01855
Opus 5 $0.00023 $0.00928
Sonnet 5 $0.00009 $0.00371
Haiku 4.5 $0.00005 $0.00186

Measured 8d ago against content hash 9646a4a5d966, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

convex-workos 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 8d 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.

.claude/skills/convex-workos-skill/SKILL.md · 266 lines

How it starts

The opening of the file, as written. The whole thing — 266 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Convex + WorkOS AuthKit

Provider-specific patterns for integrating WorkOS AuthKit with Convex.

Required Configuration

1. auth.config.ts

// convex/auth.config.ts
const clientId = process.env.WORKOS_CLIENT_ID;

export default {
  providers: [
    {
      type: 'customJwt',
      issuer: 'https://api.workos.com/',
      algorithm: 'RS256',
      applicationID: clientId,
      jwks: `https://api.workos.com/sso/jwks/${clientId}`
    },
    {
      type: 'customJwt',
      issuer: `https://api.workos.com/user_management/${clientId}`,
      algorithm: 'RS256',
      jwks: `https://api.workos.com/sso/jwks/${clientId}`
    }
  ]
};

Note: WorkOS requires TWO provider entries for different JWT issuers.

2. Environment Variables

# .env.local (Vite/React)
VITE_WORKOS_CLIENT_ID=client_01...
VITE_WORKOS_REDIRECT_URI=http://localhost:5173/callback

# .env.local (Next.js)
WORKOS_CLIENT_ID=client_01...
WORKOS_API_KEY=sk_test_...
WORKOS_COOKIE_PASSWORD=your_32_char_minimum_password_here
NEXT_PUBLIC_WORKOS_REDIRECT_URI=http://localhost:3000/callback

# Convex Dashboard Environment Variables
WORKOS_CLIENT_ID=client_01...

Client Setup

React (Vite)

// src/main.tsx
import { AuthKitProvider, useAuth } from "@workos-inc/authkit-react";
import { ConvexProviderWithAuthKit } from "@convex-dev/workos";
import { ConvexReactClient } from "convex/react";

const convex = new ConvexReactClient(import.meta.env.VITE_CONVEX_URL);

ReactDOM.createRoot(document.getElementById("root")!).render(
  <AuthKitProvider
    clientId={import.meta.env.VITE_WORKOS_CLIENT_ID}
    redirectUri={import.meta.env.VITE_WORKOS_REDIRECT_URI}
  >
    <ConvexProviderWithAuthKit client={convex} useAuth={useAuth}>
      <App />
    </ConvexProviderWithAuthKit>
  </AuthKitProvider>
);

Install: npm install @workos-inc/authkit-react @convex-dev/workos

Next.js App Router

// components/ConvexClientProvider.tsx
'use client';

import { ReactNode, useCallback, useRef } from 'react';
import { ConvexReactClient, ConvexProviderWithAuth } from 'convex/react';
import { AuthKitProvider, useAuth, useAccessToken } from '@workos-inc/authkit-nextjs/components';

const convex = new ConvexReactClient(process.env.NEXT_PUBLIC_CONVEX_URL!);

export function ConvexClientProvider({ children }: { children: ReactNode }) {
  return (
    <AuthKitProvider>
      <ConvexProviderWithAuth client={convex} useAuth={useAuthFromAuthKit}>
        {children}
      </ConvexProviderWithAuth>
    </AuthKitProvider>
  );
}

function useAuthFromAuthKit() {
  const { user, loading: isLoading } = useAuth();
  const { accessToken, loading: tokenLoading, error: tokenError } = useAccessToken();

  const loading = (isLoading ?? false) || (tokenLoading ?? false);
  const authenticated = !!user && !!accessToken && !loading;

  const stableAccessToken = useRef<string | null>(null);
  if (accessToken && !tokenError) {
    stableAccessToken.current = accessToken;
  }

  const fetchAccessToken = useCallback(async () => {
    if (stableAccessToken.current && !tokenError) {
      return stableAccessToken.current;
    }
    return null;
  }, [tokenError]);

  return {
    isLoading: loading,
    isAuthenticated: authenticated,
    fetchAccessToken,
  };
}

Read the full file on GitHub · 266 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 8d ago First seen · 266 lines · 46 tokens per session scan A 9646a4a5d966

Subscribe to this mod's changes

convex-workos is a skill published in the GitHub repository PolarCoding85/convex-agent-skillz (17 stars, last pushed 6mo ago), licensed MIT. It adds 46 tokens to every session and 1,855 once invoked, about $0.0002 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 2026-08-30.

Related

Other skills, from other repositories

mcp-server

Configure, launch, validate, and troubleshoot CCAM's comprehensive MCP server for Claude Code, Codex, and other MCP hosts. Use when installing dependencies, building the server, selecting stdio, HTTP, or REPL transport, setting mutation/destructive policy, supplying dashboard authentication, or checking complete tool…

hoangsonww/Claude-Code-Agent-Monitor · 66 tokens

endpoint-probe

Probes each major Agent Monitor API route — /api/stats, /api/analytics, /api/sessions, /api/pricing/cost, /api/workflows/runs, /api/cc-config/overview — and reports each one's HTTP status, latency, and response shape, flagging which are reachable. Use to verify a dashboard install is wired up correctly.

hoangsonww/Claude-Code-Agent-Monitor · 80 tokens

fusecore

Use when creating modules, understanding FuseCore structure, or implementing features in a FuseCore modular-monolith Laravel project.

fusengine/agents · 27 tokens

laravel-architecture

Use when structuring a Laravel project, creating services/repositories/actions, implementing dependency injection, or organizing code layers.

fusengine/agents · 28 tokens

laravel-api

Use when creating API endpoints, transforming responses with API Resources, or handling API authentication, rate limiting, or versioning.

fusengine/agents · 28 tokens

laravel-attributes

Use when migrating Eloquent models, Jobs, Console commands, Controllers, API Resources, Validation, Factories or Seeders to Laravel 13 PHP attributes.

fusengine/agents · 36 tokens