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 sandeepmvl/rails-skills --skill 08-devise-pundit-rodauthgit clone --depth 1 https://github.com/sandeepmvl/rails-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/sandeepmvl/rails-skills/08-devise-pundit-rodauth)<a href="https://agentmods.dev/skills/sandeepmvl/rails-skills/08-devise-pundit-rodauth"><img src="https://agentmods.dev/badge/skills/sandeepmvl/rails-skills/08-devise-pundit-rodauth/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/sandeepmvl/rails-skills/08-devise-pundit-rodauth"><img src="https://agentmods.dev/badge/skills/sandeepmvl/rails-skills/08-devise-pundit-rodauth.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 | $0.00161 | $0.04113 |
| Opus 5 | $0.00081 | $0.02056 |
| Sonnet 5 | $0.00032 | $0.00823 |
| Haiku 4.5 | $0.00016 | $0.00411 |
Grade A, and why
devise-pundit-rodauth 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 12d 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 — 450 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Devise + Pundit + Rodauth
Authentication = "who you are". Authorization = "what you can do". AI agents conflate them and reach for whatever gem name they saw most recently. This skill picks the right combo per use case and locks in the secure defaults.
The opinion
Default monolith stack: Devise (authn) + Pundit (authz). When Devise hits its limits (MFA, WebAuthn, audit logging, account-level password policies, OAuth2 server), switch to Rodauth. For API-only apps, devise-jwt or rodauth-rails. For tiny apps, Rails 8's built-in
bin/rails generate authenticationis enough — skip Devise.
Counter-positions:
- CanCanCan (ability-based DSL): popular historically. We default to Pundit — its plain-Ruby policy-per-model maps cleaner to OOP. CanCanCan's centralized Ability class becomes hard to read at scale.
- Clearance (thoughtbot): minimalist, no email confirmation. Fine for greenfield, but Devise's modules cover more out of the box.
- Rolling your own auth: don't. Auth is hard. Use a library.
Decision matrix — pick the auth stack
| Use case | Stack |
|---|---|
| Rails 8 monolith, simple login/signup, you don't need confirmable | bin/rails generate authentication (built-in) + Pundit |
| Rails 7/8 monolith, standard features (confirm, recover, lockable, password complexity) | Devise + Pundit |
| Rails monolith with MFA, WebAuthn, audit logging, JWT API | Rodauth (rodauth-rails) |
| API-only Rails app | devise-jwt + Pundit, OR rodauth-rails JWT |
| Multi-tenant SaaS with per-account roles | Devise + Pundit (with namespaced policies) |
| Anything regulated (HIPAA, PCI, SOC 2) | Rodauth (max-security defaults) — see v0.3 compliance skills |
Core patterns
Pattern 1: Rails 8 built-in authentication (simplest)
For new apps that need just sign-in/sign-up:
bin/rails generate authentication
Generates a User, Session, PasswordsController, secure cookie-based sessions. Doesn't bring confirmable / recoverable. When you outgrow it, swap to Devise — the model migration is straightforward.
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.
- 12d ago First seen · 450 lines · 161 tokens per session scan A 6f4e9ff0a3da
devise-pundit-rodauth is a skill published in the GitHub repository sandeepmvl/rails-skills (21 stars, last pushed 3mo ago), licensed MIT. It adds 161 tokens to every session and 4,113 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 2026-08-30.
Other skills, from other repositories
rubyllm
Build and maintain Ruby or Rails applications with the RubyLLM AI framework. Use for chats, agents, tools, structured output, media generation, transcription, OCR, moderation, embeddings, reranking, Rails integration, and RubyLLM upgrades; not for contributing to the framework itself.
new
Create a new project to start development quickly.
rspec-conventions
Rootstrap RSpec conventions. Use when writing, reviewing, or editing RSpec test files (spec//spec.rb, spec/railshelper.rb, spec/spechelper.rb, spec/support//.rb) or factories. Covers describe/context structure, let/subject, matchers, factories, mocking/stubbing, shared examples, and spec types (model, request…
ruby-patterns
Ruby/Rails: blocks, metaprogramming, ActiveRecord, Sidekiq, RSpec, Sorbet, Hanami. Triggers: Ruby, Rails, ActiveRecord, Sidekiq, RSpec, Gemfile, bundler, Hanami, Sorbet.
ruby-rules
Ruby coding rules: style, patterns, security, testing. Triggers: .rb, Gemfile, .gemspec, Rails, ActiveRecord, Sidekiq, RSpec, Sorbet, rubocop.
simplify
Simplifies and refines Ruby on Rails code following 37signals patterns and the One Person Framework philosophy, while preserving exact functionality. Focuses on recently modified code unless instructed otherwise. Use this skill when simplifying or refactoring Rails code, reviewing recently written Rails code for…