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 PolarCoding85/convex-agent-skillz --skill convex-workos-skillgit clone --depth 1 https://github.com/PolarCoding85/convex-agent-skillzWrote 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/polarcoding85/convex-agent-skillz/convex-workos-skill)<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>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 | $0.00046 | $0.01855 |
| Opus 5 | $0.00023 | $0.00928 |
| Sonnet 5 | $0.00009 | $0.00371 |
| Haiku 4.5 | $0.00005 | $0.00186 |
Grade A, and why
convex-workos scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 266 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Convex + WorkOS AuthKit
Provider-specific patterns for integrating WorkOS AuthKit with Convex.
Required Configuration
1. auth.config.ts
// convex/auth.config.ts
const clientId = process.env.WORKOS_CLIENT_ID;
export default {
providers: [
{
type: 'customJwt',
issuer: 'https://api.workos.com/',
algorithm: 'RS256',
applicationID: clientId,
jwks: `https://api.workos.com/sso/jwks/${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,
};
}
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.
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.
- 8d ago First seen · 266 lines · 46 tokens per session scan A 9646a4a5d966
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.
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…
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.
fusecore
Use when creating modules, understanding FuseCore structure, or implementing features in a FuseCore modular-monolith Laravel project.
laravel-architecture
Use when structuring a Laravel project, creating services/repositories/actions, implementing dependency injection, or organizing code layers.
laravel-api
Use when creating API endpoints, transforming responses with API Resources, or handling API authentication, rate limiting, or versioning.
laravel-attributes
Use when migrating Eloquent models, Jobs, Console commands, Controllers, API Resources, Validation, Factories or Seeders to Laravel 13 PHP attributes.