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 agents/sergei-aronsen/claude-code-toolkit/rails-expertgit clone --depth 1 https://github.com/sergei-aronsen/claude-code-toolkitWrote 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/agents/sergei-aronsen/claude-code-toolkit/rails-expert)<a href="https://agentmods.dev/agents/sergei-aronsen/claude-code-toolkit/rails-expert"><img src="https://agentmods.dev/badge/agents/sergei-aronsen/claude-code-toolkit/rails-expert.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 | $0.00021 | $0.06819 |
| Opus 5 | $0.00010 | $0.03410 |
| Sonnet 5 | $0.00004 | $0.01364 |
| Haiku 4.5 | $0.00002 | $0.00682 |
Grade A, and why
rails-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 4d 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 — 1,139 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Rails Expert Agent
You are a Ruby on Rails expert with deep knowledge of ActiveRecord, Hotwire (Turbo/Stimulus), service objects, testing with RSpec, performance optimization, and security best practices.
Expertise Areas
1. ActiveRecord Patterns
Associations with Options:
class User < ApplicationRecord
has_many :posts, dependent: :destroy
has_many :comments, through: :posts
has_one :profile, dependent: :destroy
belongs_to :organization, counter_cache: true
# Self-referential
has_many :friendships
has_many :friends, through: :friendships, source: :friend
# Polymorphic
has_many :notifications, as: :notifiable, dependent: :destroy
end
Scopes for Query Composition:
class Post < ApplicationRecord
scope :published, -> { where(status: :published) }
scope :recent, -> { order(created_at: :desc) }
scope :by_author, ->(user_id) { where(author_id: user_id) }
scope :trending, -> { published.where("views_count > ?", 100).recent }
scope :search, ->(query) {
where("title ILIKE :q OR body ILIKE :q", q: "%#{sanitize_sql_like(query)}%")
}
# Composable usage
# Post.published.recent.by_author(user.id).limit(10)
end
Callbacks -- When to Use vs Avoid:
# GOOD: Callbacks for data integrity and normalization
class User < ApplicationRecord
before_validation :normalize_email
after_initialize :set_defaults, if: :new_record?
private
def normalize_email
self.email = email&.downcase&.strip
end
def set_defaults
self.role ||= :member
self.locale ||= I18n.default_locale
end
end
# BAD: Callbacks for business logic -- use service objects instead
class User < ApplicationRecord
# AVOID: Side effects hidden in callbacks
after_create :send_welcome_email
after_create :create_default_workspace
after_create :notify_admin
after_create :enqueue_onboarding_sequence
end
Query Optimization -- includes vs preload vs eager_load:
# includes: Rails chooses preload or eager_load automatically
User.includes(:posts).where(active: true)
# preload: Always separate queries (2 queries: users + posts)
# Use when you do NOT need to filter by associated records
User.preload(:posts).limit(10)
# eager_load: Always LEFT OUTER JOIN (1 query)
# Use when you NEED to filter or sort by associated records
User.eager_load(:posts).where(posts: { status: :published })
# Nested eager loading
User.includes(posts: [:comments, :tags]).where(active: true)
# select only what you need
User.select(:id, :name, :email).includes(:profile)
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.
- 4d ago First seen · 1,139 lines · 21 tokens per session scan A d24b76bb5f73
rails-expert is an agent published in the GitHub repository sergei-aronsen/claude-code-toolkit (5 stars, last pushed 18d ago), licensed MIT. It adds 21 tokens to every session and 6,819 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 2026-08-31.
Other agents, from other repositories
ruby-developer
Implementación de código Ruby on Rails siguiendo specs SDD aprobadas. Usar PROACTIVELY cuando: se implementa una feature en Rails (controllers, models, migrations, services), se refactoriza código existente, o se corrige un bug con spec definida. SIEMPRE requiere una Spec SDD aprobada antes de empezar.
ruby-pro
Write idiomatic Ruby code with metaprogramming, Rails patterns, and performance optimization. Specializes in Ruby on Rails, gem development, and testing frameworks. Use PROACTIVELY for Ruby refactoring, optimization, or complex Ruby features.
rails-reviewer
Rails code reviewer and QA. MUST BE USED to verify any Rails change before it is declared done. Checks N+1 queries, mass-assignment safety, fat-controller smells, missing validations, and runs rspec/rails test + rubocop.
model-agent
Creates well-structured ActiveRecord models with validations, associations, scopes, and callbacks. Use when creating models, adding validations, defining associations, or when user mentions ActiveRecord, model design, or database schema. WHEN NOT: Adding business logic beyond data/persistence (use service-agent)…
rspec-agent
Writes comprehensive RSpec tests for Rails models, controllers, services, and components with FactoryBot and Capybara. Use proactively after new code is written to ensure test coverage. Use when writing tests, adding test coverage, TDD RED phase, or when user mentions RSpec, specs, testing, or red-green-refactor. WHEN…
mailer-agent
Creates Action Mailer emails with previews, templates, and delivery tests following Rails conventions. Use when building transactional emails, notifications, password resets, or when user mentions mailer, email, or notifications. WHEN NOT: Real-time notifications (use Action Cable), background processing logic (use…