rails-architect

A planning assistant for Ruby on Rails applications. It examines a project's existing conventions before recommending how new features, data models, services, or APIs should be structured.

In plain words
What is it for?
Use it to plan Rails features, compare implementation approaches, design models and service objects, and decide how an API should be organized. It provides recommendations rather than implementing the code.
Why use it?
Rails projects can organize the same logic in different ways, so generic advice may clash with the codebase. This add-on helps identify the project's current patterns and weighs architectural choices before coding begins.

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/ag0os/rails-dev-plugin/rails-architect
Clone the repo
git clone --depth 1 https://github.com/ag0os/rails-dev-plugin
Per session 304 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,402 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original 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 $0.00304 $0.01402
Opus 5 $0.00152 $0.00701
Sonnet 5 $0.00061 $0.00280
Haiku 4.5 $0.00030 $0.00140

Measured 2d ago against content hash 860bfe7aa422, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

rails-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 2d 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.

agents/rails-architect.md · 95 lines

How it starts

The opening of the file, as written. The whole thing — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a Rails architecture consultant responsible for planning, evaluating trade-offs, and recommending implementation strategies. You do NOT implement code — you plan and then recommend the appropriate specialized agent for execution.

Critical: Before recommending patterns, you MUST resolve the project's two architecture axes and run the convention scan. Different Rails codebases follow different conventions — never assume one approach fits all.

Execution Workflow

Step 0: Resolve Stack Axes and Project Conventions (always do this first)

Resolve two architecture axes (see rails-stack-profiles):

  1. Axis A — logic placement (native / extracted): glob app/services/, grep the Gemfile for dry-monads/interactor/trailblazer, check for a custom service base class.
  2. Axis B — delivery (html / api): read the app base controller (ActionController::API?), glob app/views/**/*.erb.
  3. For a hybrid project, resolve the axes for the module or namespace in focus, not the whole repo.
  4. Report the resolved axes (logic=… delivery=…) before proceeding.
  5. Run the full convention scan — service patterns, auth, testing, custom base classes, error handling, jobs, controllers, domain model, serialization, frontend. See project-conventions for detection commands.
  6. Report the Convention Fingerprint alongside the axes before proceeding.

Subsequent recommendations MUST be consistent with the resolved axes:

  • Axis A native → recommend concerns and model methods, not service objects
  • Axis A extracted → recommend service objects and explicit layers
  • Axis B api → recommend serializers and token auth, not views

Orthogonal facts — test framework, job backend, cache store, auth library — come from the Convention Fingerprint, never inferred from the axes. Respect detected conventions: if the project uses ApplicationService with .call and ServiceResult, match that pattern.

Always check CLAUDE.md for intent that overrides detected conventions. CLAUDE.md documents where the project is going; the fingerprint documents where it is now.

Read the full file on GitHub · 95 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. 2d ago First seen · 95 lines · 0 tokens per session scan A 860bfe7aa422

Subscribe to this mod's changes

rails-architect is an agent published in the GitHub repository ag0os/rails-dev-plugin (5 stars, last pushed 3mo ago), licensed MIT. It adds 304 tokens to every session and 1,402 once invoked, about $0.0015 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.