oauth-authentication

oauth-authentication is a skill for Claude Code, Codex from hoangatg/ai-agent-toolkit. It costs 36 tokens per session (913 once invoked), scanned A, original, MIT.

A guide to identifying users and controlling what they can access. It covers sessions, OAuth 2.0, JWTs, single sign-on, roles, permissions, and passkeys.

In plain words
What is it for?
Use it to implement user login, third-party sign-in, machine access, role-based permissions, or session management.
Why use it?
It helps avoid insecure or unsuitable choices when adding login and access control to an application.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to implement user login, third-party sign-in, machine access, role-based permissions, or session management.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/hoangatg/ai-agent-toolkit/oauth-authentication
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 hoangatg/ai-agent-toolkit --skill oauth-authentication
Clone the repo
git clone --depth 1 https://github.com/hoangatg/ai-agent-toolkit

Made for: Claude Code, Codex.

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 oauth-authentication

README.md
[![agentmods](https://agentmods.dev/badge/skills/hoangatg/ai-agent-toolkit/oauth-authentication/github.svg)](https://agentmods.dev/skills/hoangatg/ai-agent-toolkit/oauth-authentication)
Your own site
<a href="https://agentmods.dev/skills/hoangatg/ai-agent-toolkit/oauth-authentication"><img src="https://agentmods.dev/badge/skills/hoangatg/ai-agent-toolkit/oauth-authentication/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.

agentmods 80×15 button for oauth-authentication

Your own site · 80×15
<a href="https://agentmods.dev/skills/hoangatg/ai-agent-toolkit/oauth-authentication"><img src="https://agentmods.dev/badge/skills/hoangatg/ai-agent-toolkit/oauth-authentication.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 36 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 913 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 $0.00036 $0.00913
Opus 5 $0.00018 $0.00456
Sonnet 5 $0.00007 $0.00183
Haiku 4.5 $0.00004 $0.00091

Measured 7d ago against content hash f50b1e567f7a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

oauth-authentication 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 7d 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.

.agent/skills/oauth-authentication/SKILL.md · 120 lines

How it starts

The opening of the file, as written. The whole thing — 120 lines — stays where its author put it; the contents beside it link to each section on GitHub.

OAuth & Authentication

Know who they are. Control what they can do. Do it securely.


1. Authentication Methods

Method Best For Complexity
Session + Cookie Server-rendered apps (Next.js, Rails) Low
JWT (stateless) SPAs, mobile apps, microservices Medium
OAuth 2.0 Third-party login (Google, GitHub) Medium
Passkeys/WebAuthn Passwordless, highest security High
Magic Link Email-based, no password Low

2. OAuth 2.0 Flows

Flow Use Case Security
Authorization Code + PKCE Web apps, mobile apps ✅ Most secure
Client Credentials Machine-to-machine ✅ Server only
Device Code TVs, CLI tools
Implicit Deprecated ❌ Don't use
Password Grant Deprecated ❌ Don't use

Rule: Always use Authorization Code + PKCE for user-facing apps.


3. JWT Best Practices

Token Design

Aspect Recommendation
Access token Short-lived (15 min)
Refresh token Long-lived (7-30 days), rotated
Algorithm RS256 (asymmetric) for distributed
Claims Minimal: sub, iat, exp, roles
Storage HttpOnly cookie (web), secure storage (mobile)

Token Security

❌ Don't ✅ Do
Store in localStorage HttpOnly, Secure, SameSite cookies
Long-lived access tokens Short access + refresh rotation
Send in URL params Send in Authorization header
Encode sensitive data Minimal claims, lookup DB for details

4. Authorization Patterns

Pattern Best For
RBAC (Role-Based) Simple: admin, editor, viewer
ABAC (Attribute-Based) Complex: department + level + resource
ReBAC (Relationship-Based) Social: "friends of friends" (Zanzibar)
ACL File/resource-level permissions

5. Auth Providers

Read the full file on GitHub · 120 lines

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. 7d ago First seen · 120 lines · 36 tokens per session scan A f50b1e567f7a

Subscribe to this mod's changes

oauth-authentication is a skill published in the GitHub repository hoangatg/ai-agent-toolkit (1 stars, last pushed 5mo ago), licensed MIT. It adds 36 tokens to every session and 913 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 2026-09-03.