Rails Architecture

What it does

When your agent uses it

• Deciding where to put code
• Choosing between patterns (service objects vs concerns vs query objects)
• Designing feature architecture
• Refactoring for better organization

Example prompts

• “Use the rails-architecture skill to guide modern Rails 8 code architecture decisions and patterns”
• “/rails-architecture”

Workflow steps

9 steps, taken from the first numbered list in SKILL.md.

1. 1Model - Define data structure (@migration-agent, @model-agent)
2. 2Policy - Add authorization rules (@policy-agent)
3. 3Service - Create for complex logic (@service-agent)
4. 4Query - Add for complex queries (@query-agent)
5. 5Controller - Keep it thin (@controller-agent)
6. 6Presenter - Format for display (@presenter-agent)
7. 7Component - Build reusable UI (@viewcomponent-agent)
8. 8Mailer - Add transactional emails (@mailer-agent)
9. 9Job - Add background processing (@job-agent)

What it can do on your machine

Read from SKILL.md and the folder at commit 03622f2. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  No scripts in the folder and no shell commands in SKILL.md (its code samples are ruby).

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  No URLs in SKILL.md.

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names no API keys, tokens, secrets or passwords.

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Rails Architecture loads about 1.5k tokens when it runs, and up to ~12k if it reads all its reference files. Until then it costs about 124 tokens; SKILL.md has 384 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~124

When it runs · the whole SKILL.md, loaded when a task matches

~1.5k

With references · SKILL.md plus every file in references/, read only if the agent opens them

~12k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from ThibautBaissac/rails_ai_agents at commit 03622f2, republished under its MIT licence (© ThibautBaissac). 384 words, ~1,478 tokens.

name

rails-architecture

description

Guides modern Rails 8 code architecture decisions and patterns. Use when deciding where to put code, choosing between patterns (service objects vs concerns vs query objects), designing feature architecture, refactoring for better organization, or when user mentions architecture, code organization, design patterns, or layered design. WHEN NOT: Implementing specific patterns (use specialist agents like service-agent or query-agent), writing tests, or debugging runtime errors.

model

sonnet

effort

high

Where should this code go?
|
+- View/display formatting?       -> Presenter (@presenter-agent)
+- Complex business logic?        -> Service Object (@service-agent)
+- Complex database query?        -> Query Object (@query-agent)
+- Shared behavior across models? -> Concern (/rails-concern skill)
+- Authorization logic?           -> Policy (@policy-agent)
+- Reusable UI with logic?        -> ViewComponent (@viewcomponent-agent)
+- Async/background work?         -> Job (@job-agent, /solid-queue-setup skill)
+- Complex form (multi-model)?    -> Form Object (@form-agent)
+- Transactional email?           -> Mailer (@mailer-agent)
+- Real-time/WebSocket?           -> Channel (/action-cable-patterns skill)
+- Data validation only?          -> Model (@model-agent)
+- HTTP request/response only?    -> Controller (@controller-agent)

# GOOD: Thin controller delegates to service
class OrdersController < ApplicationController
  def create
    result = Orders::CreateService.call(user: current_user, params: order_params)
    if result.success?
      redirect_to result.data, notice: t(".success")
    else
      flash.now[:alert] = result.error
      render :new, status: :unprocessable_entity
    end
  end
end

Result = Data.define(:success, :data, :error) do
  def success? = success
  def failure? = !success
end

# GOOD: Scoped through account
def index
  @events = current_account.events.recent
end

© ThibautBaissac, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 5 other files (references) in .agents/skills/rails-architecture of ThibautBaissac/rails_ai_agents.

• SKILL.md
• references/error-handling.md
• references/layer-interactions.md
• references/query-patterns.md
• references/service-patterns.md
• references/testing-strategy.md

Open the folder on GitHubat commit 03622f2