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 medy-gribkov/arcana --skill oauth-authgit clone --depth 1 https://github.com/medy-gribkov/arcanaWrote 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/medy-gribkov/arcana/oauth-auth)<a href="https://agentmods.dev/skills/medy-gribkov/arcana/oauth-auth"><img src="https://agentmods.dev/badge/skills/medy-gribkov/arcana/oauth-auth/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/medy-gribkov/arcana/oauth-auth"><img src="https://agentmods.dev/badge/skills/medy-gribkov/arcana/oauth-auth.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 | $0.00026 | $0.03394 |
| Opus 5 | $0.00013 | $0.01697 |
| Sonnet 5 | $0.00005 | $0.00679 |
| Haiku 4.5 | $0.00003 | $0.00339 |
Grade B, and why
oauth-auth scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Sends data to an external URLmediumData exfiltration
A POST to an outside endpoint may be telemetry or may be exfiltration; either way the mod talks to somewhere, and you should know where.
const response = await fetch('https://provider.com/oauth/token', { method: 'POST', How it starts
The opening of the file, as written. The whole thing — 521 lines — stays where its author put it; the contents beside it link to each section on GitHub.
OAuth and Authentication
Implement secure OAuth2 flows, JWT validation, session management, and authentication patterns.
OAuth2 Authorization Code Flow with PKCE
BAD: No PKCE, state stored in localStorage
// Client initiates OAuth without PKCE
const authUrl = `https://provider.com/oauth/authorize?client_id=${clientId}&redirect_uri=${redirectUri}&response_type=code`;
localStorage.setItem('oauth_state', Math.random().toString());
window.location.href = authUrl;
GOOD: PKCE with httpOnly cookie state
import crypto from 'crypto';
// Generate PKCE challenge
function generatePKCE() {
const verifier = crypto.randomBytes(32).toString('base64url');
const challenge = crypto
.createHash('sha256')
.update(verifier)
.digest('base64url');
return { verifier, challenge };
}
// Initiate OAuth with PKCE
export async function initiateOAuth(res: Response) {
const { verifier, challenge } = generatePKCE();
const state = crypto.randomBytes(32).toString('base64url');
// Store verifier and state in httpOnly cookie
res.setHeader('Set-Cookie', [
`pkce_verifier=${verifier}; HttpOnly; Secure; SameSite=Lax; Max-Age=600`,
`oauth_state=${state}; HttpOnly; Secure; SameSite=Lax; Max-Age=600`
]);
const params = new URLSearchParams({
client_id: process.env.OAUTH_CLIENT_ID!,
redirect_uri: process.env.OAUTH_REDIRECT_URI!,
response_type: 'code',
scope: 'openid profile email',
state,
code_challenge: challenge,
code_challenge_method: 'S256'
});
return `https://provider.com/oauth/authorize?${params}`;
}
Token Exchange and Validation
BAD: No validation, symmetric JWT with weak secret
// Exchange code without validating state
const response = await fetch('https://provider.com/oauth/token', {
method: 'POST',
body: JSON.stringify({ code, client_id: clientId, client_secret: secret })
});
const { access_token } = await response.json();
// Weak symmetric JWT
import jwt from 'jsonwebtoken';
const token = jwt.sign({ userId }, 'weak-secret', { expiresIn: '1h' });
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.
- 10d ago First seen · 521 lines · 26 tokens per session scan B 7b1bfac00328
oauth-auth is a skill published in the GitHub repository medy-gribkov/arcana (1 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 26 tokens to every session and 3,394 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it B with 1 finding (sends data to an external url). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
api-designer
Design RESTful and RPC APIs — OpenAPI specs, request/response schemas, error codes, versioning, and documentation.
claude-api
Build apps with the Anthropic Claude API — chat completions, tool use, streaming, vision, and multi-turn conversations.
discord-bot
Create Discord bots — slash commands, embeds, voice, roles, threads, and Discord.js/Pycord implementations.
github-integration
Integrate with GitHub — Actions, Apps, webhooks, Octokit, and repository automation workflows.
graphql-builder
Design and implement GraphQL schemas — types, queries, mutations, subscriptions, resolvers, and federation.
mcp-builder
Scaffold and implement Model Context Protocol servers — tools, resources, prompts, and sampling handlers.