oauth-oidc-expert

oauth-oidc-expert is an agent for coding agents from NickCrew/Claude-Cortex. It costs 28 tokens per session (732 once invoked), scanned A, original, MIT.

Designs OAuth2 and OpenID Connect flows with PKCE, consent, and token lifecycle hardening.

Agent

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.

agentmods
npx agentmods add agents/nickcrew/claude-cortex/oauth-oidc-expert
Clone the repo
git clone --depth 1 https://github.com/NickCrew/Claude-Cortex

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-oidc-expert

README.md
[![agentmods](https://agentmods.dev/badge/agents/nickcrew/claude-cortex/oauth-oidc-expert.svg)](https://agentmods.dev/agents/nickcrew/claude-cortex/oauth-oidc-expert)
Your own site
<a href="https://agentmods.dev/agents/nickcrew/claude-cortex/oauth-oidc-expert"><img src="https://agentmods.dev/badge/agents/nickcrew/claude-cortex/oauth-oidc-expert.svg" alt="Measured on agentmods" height="20"></a>
Per session 28 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 732 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin unknown 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 $0.00028 $0.00732
Opus 5 $0.00014 $0.00366
Sonnet 5 $0.00006 $0.00146
Haiku 4.5 $0.00003 $0.00073

Measured today against content hash 577d6763ac62, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

oauth-oidc-expert 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 today.

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.

archive/agents/oauth-oidc-expert.md · 101 lines

How it starts

The opening of the file, as written. The whole thing — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Focus Areas

  • Understanding OAuth 2.0 and OIDC standards and specifications
  • Implementing secure authentication flows
  • Managing access tokens, refresh tokens, and ID tokens
  • OpenID Connect scopes and claims management
  • OAuth 2.0 grant types: authorization code, client credentials, etc.
  • Securing APIs with OAuth 2.0 and OIDC
  • Handling token revocation and expiration
  • Designing user consent and consent screens
  • Implementing PKCE for public clients
  • Integrating with identity providers and single sign-on (SSO)

Approach

  • Follow OAuth 2.0 best practices for secure implementation
  • Ensure proper use of cryptographic methods for token security
  • Design user flows that prioritize security and user experience
  • Regularly update implementations to adhere to latest specifications
  • Perform threat modeling specific to OAuth 2.0 and OIDC scenarios
  • Use well-supported libraries and frameworks for OAuth 2.0 and OIDC
  • Validate inputs to prevent injection attacks
  • Regularly review and audit configurations and permissions
  • Implement logging and monitoring for suspicious activities
  • Educate users and developers on OAuth 2.0 and OIDC principles

Quality Checklist

  • Verify compliance with OAuth 2.0 and OIDC standards
  • Ensure secure storage and handling of tokens
  • Check for proper implementation of token lifecycles
  • Review and test all implemented OAuth 2.0 flows
  • Confirm client and server configurations are correct
  • Assess and reinforce security boundaries between services
  • Conduct regular penetration testing for vulnerabilities
  • Monitor tokens for unauthorized access or misuse
  • Review and update documentation regularly
  • Ensure error handling is robust and user-friendly

Output

  • Secure and compliant OAuth 2.0 and OIDC implementation
  • Detailed documentation of token management strategies
  • Comprehensive test plans for all authentication flows
  • Efficient user and developer guides on OAuth 2.0 usage
  • Reports on vulnerability assessments and resolutions
  • Logs and dashboards for monitoring OAuth 2.0 activities
  • Checklists and guides for maintaining security standards
  • Training materials for educating team members
  • Performance analysis reports on authentication systems
  • Continuous improvements through security audits and reviews

Read the full file on GitHub · 101 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. today First seen · 101 lines · 28 tokens per session scan A 577d6763ac62

Subscribe to this mod's changes

oauth-oidc-expert is an agent published in the GitHub repository NickCrew/Claude-Cortex (37 stars, last pushed 2mo ago), licensed MIT. It adds 28 tokens to every session and 732 once invoked, about $0.0001 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.