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 agentmods add skills/mturac/hermes-supercode-skills/auth-architectnpx skills add mturac/hermes-supercode-skills --skill auth-architectgit clone --depth 1 https://github.com/mturac/hermes-supercode-skillsWrote 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/mturac/hermes-supercode-skills/auth-architect)<a href="https://agentmods.dev/skills/mturac/hermes-supercode-skills/auth-architect"><img src="https://agentmods.dev/badge/skills/mturac/hermes-supercode-skills/auth-architect.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 | $0.00166 | $0.01931 |
| Opus 5 | $0.00083 | $0.00966 |
| Sonnet 5 | $0.00033 | $0.00386 |
| Haiku 4.5 | $0.00017 | $0.00193 |
Grade A, and why
auth-architect 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 5d 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 — 260 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Auth Architect
You are an authentication and identity specialist. You design login systems that are understandable, auditable, and resistant to common failure modes. You use audited libraries and platform standards, and you treat token lifecycle, session state, and authorization boundaries as first-class design work.
Core Concepts
OAuth2 And OIDC
- Authorization Code + PKCE: default for browser and mobile clients
- Client Credentials: service-to-service access with scoped credentials
- OIDC: identity layer over OAuth2; validate issuer, audience, nonce, signature, and expiration
- Never treat an OAuth access token as proof of user identity unless OIDC identity claims were issued and validated correctly
JWT Design
- Use asymmetric signing such as RS256 or ES256 across multiple services
- Use HS256 only when one service owns both signing and verification or when secret distribution risk is explicitly accepted
- Keep payloads minimal: subject, issuer, audience, expiry, issued-at, scopes, tenant, and stable authorization hints
- Rotate keys through
kidheaders and a JWKS endpoint - Use short-lived access tokens and refresh token rotation
Authorization Models
- RBAC: roles map to permissions; good default for product teams
- ABAC: policies use resource and actor attributes; useful for multi-tenant, ownership, region, or data-sensitivity constraints
- Enforce authorization near the resource action, not only in routing middleware
Workflow
1. Recon
Identify actors, clients, trust boundaries, token consumers, and existing identity providers:
Application: B2B SaaS
Clients:
- web_app: browser, first-party
- api: public REST API
- worker: internal service
Identity Providers:
- Google OIDC
- GitHub OAuth
Tenancy:
model: organization
isolation_key: org_id
Current Tokens:
access_token_ttl: 15m
refresh_token_ttl: 30d
Collect current session storage, cookie settings, JWT claims, key management, password reset or magic link behavior, MFA requirements, and API key usage.
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.
- 5d ago First seen · 260 lines · 166 tokens per session scan A 5b2ad84276b2
auth-architect is a skill published in the GitHub repository mturac/hermes-supercode-skills (2 stars, last pushed 3mo ago), licensed MIT. It adds 166 tokens to every session and 1,931 once invoked, about $0.0008 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 2026-08-31.
Other skills, from other repositories
swift-networking
Builds a protocol-based async/await networking layer with URLSession, testable abstractions, error handling, and mock support for Swift projects. Use when user says "add networking", "create an API layer", "fetch data from API", "build a network service", "add URLSession", "implement HTTP requests", "create a REST…
swift-architecture-audit
Audits an existing Swift/SwiftUI/UIKit codebase for MVVM compliance, testability issues, architectural violations, concurrency problems, and anti-patterns. Use when user says "audit the codebase", "review the architecture", "why is this hard to test", "onboard to this project", "analyze the code structure", "find…
swift-code-review
Reviews Swift, SwiftUI, and UIKit code for MVVM compliance, testing standards, naming conventions, async correctness, and anti-patterns. Produces structured feedback grouped by severity. Use when user says "review this code", "check this PR", "code review", "is this correct", "give me feedback on", "review my…
swiftui-component
Creates SwiftUI views and screens following MVVM with thin view layers, ViewModel extraction, previews, accessibility support, and loading/error states. Use when user says "create a SwiftUI view", "build a screen", "add a new view", "create a component", "build the UI for", "add a SwiftUI screen", or "make a new…
swift-persistence
Implements a persistence layer using SwiftData or CoreData following MVVM — models, repository abstraction, and testable in-memory setup. Use when user says "add CoreData", "set up SwiftData", "persist data", "save to database", "add a data model", "create Core Data entities", or "use SwiftData models".
swift-project-setup
Bootstraps a new Swift/SwiftUI/UIKit project with MVVM architecture, standard folder structure, testing targets, and CLAUDE.md configuration. Use when user says "create a new project", "setup a new app", "start a new iOS project", "scaffold a Swift project", "initialize an Xcode project", or "new SwiftUI app".