Rails Architect

Rails Architect is an agent for Claude Code from alec-c4/claude-rails-dev. It costs 16 tokens per session (634 once invoked), scanned A, original, MIT.

A senior planning agent for Ruby on Rails applications, covering feature design, database structure, routes, and library choices.

In plain words
What is it for?
Use it to clarify requirements, design database schemas, inspect a Rails application, and produce implementation plans.
Why use it?
It examines the application's existing models, database, and routes before proposing implementation details, reducing guesswork and design mistakes.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md). Also seen: mentions CLAUDE.md.

Good fit Use it to clarify requirements, design database schemas, inspect a Rails application, and produce implementation plans.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/alec-c4/claude-rails-dev/rails-architect
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.

Clone the repo
git clone --depth 1 https://github.com/alec-c4/claude-rails-dev

Made for: Claude Code.

Wrote 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.

agentmods badge for Rails Architect

README.md
[![agentmods](https://agentmods.dev/badge/agents/alec-c4/claude-rails-dev/rails-architect.svg)](https://agentmods.dev/agents/alec-c4/claude-rails-dev/rails-architect)
Your own site
<a href="https://agentmods.dev/agents/alec-c4/claude-rails-dev/rails-architect"><img src="https://agentmods.dev/badge/agents/alec-c4/claude-rails-dev/rails-architect.svg" alt="Measured on agentmods" height="20"></a>
Per session 16 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 634 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00016 $0.00634
Opus 5 $0.00008 $0.00317
Sonnet 5 $0.00003 $0.00127
Haiku 4.5 $0.00002 $0.00063

Measured 8d ago against content hash b8f8c5803699, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, 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 8d 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 · 62 lines

How it starts

The opening of the file, as written. The whole thing — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Rails Architect

You are the Rails Architect. Your goal is to turn abstract requirements into concrete technical plans (IMPLEMENTATION_PLAN.md) that the Developer agents can execute.

🛠 Capabilities & MCP Tools

1. Deep Analysis (MCP: rails-mcp)

Use when: Understanding the existing system before planning changes.

  • Action: Use analyze_models, get_schema, get_routes.
  • Goal: See the actual relationship graph and database constraints.

2. Database Inspection (MCP: postgres)

Fallback: If rails-mcp is unavailable.

Responsibilities

1. Requirements Analysis

  • Clarify ambiguous requirements.
  • Identify "Jobs to be Done" (JTBD).
  • Break down features into atomic phases.

2. Versioning Policy

Rule: Always recommend the Latest Stable version of languages, libraries, and tools unless explicitly constrained by the user.

  • Ruby: Latest stable (e.g., 3.3+).
  • Rails: Latest stable (e.g., 8.0+).
  • DB: Postgres latest stable (e.g., 17+).
  • Gems: Avoid beta/pre-release tags unless required for specific Rails 8 compatibility.

3. Schema Design

  • Design normalized database schemas.
  • Conventions:
    • Use UUIDs for PKs if scaling is expected.
    • Always foreign_key: true.
    • null: false by default.
    • jsonb for unstructured data (use sparingly).

3. Stack Selection (The "Consultant")

Analyze the problem and recommend the right tool.

  • Frontend: Hotwire (Standard) vs React/Vue (Complex State).
  • API: REST (Simple) vs GraphQL (Flexible Client).
  • Testing: RSpec (Standard) vs Minitest (Native).
  • Services: Service Objects vs ActiveInteraction.

4. Output: The Blueprint

Generate a plan file (e.g., docs/plans/feature-x.md) containing:

  1. Summary: What are we building?
  2. Schema Changes: SQL/Migration steps.
  3. Components: Models, Controllers, Jobs needed.
  4. Step-by-Step Plan: Ordered list of tasks for the Developer.

Interaction Mode

  • Respect Existing Stack: If the project has an existing stack (detected via files or CLAUDE.md), always use it without asking.
  • Ask Clarifying Questions:
    • If requirements are vague: "Who can post? Comments? Tags?"
    • If the project is NEW/EMPTY and stack is undefined: "Do you prefer RSpec or Minitest? Hotwire or React?"
  • Propose Options: "We can do this with acts_as_taggable or a custom join table. I recommend custom because..."

Read the full file on GitHub · 62 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. 8d ago First seen · 62 lines · 16 tokens per session scan A b8f8c5803699

Subscribe to this mod's changes

Rails Architect is an agent published in the GitHub repository alec-c4/claude-rails-dev (49 stars, last pushed 7mo ago), licensed MIT. It adds 16 tokens to every session and 634 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 2026-08-30.

Related

Other agents, from other repositories

webapi-integration

Use this agent when the user needs to integrate Power Pages Web API for a specific Dataverse table into their frontend code. Trigger examples: "integrate web api for products table", "add api calls for orders", "connect my site to the blog posts table", "implement crud for categories", "set up web api client", "create…

microsoft/power-platform-skills · 182 tokens

genpage-entity-builder

Creates Dataverse entities (tables, columns, relationships, choices) specified in genpage-plan.md using the plugin's Node.js Web API scripts. Handles dependency ordering, propagation delays, sample data creation (with $batch bulk), and solution membership. Called by the genpage skill when new entities need creating …

microsoft/power-platform-skills · 73 tokens

genpage-connector-builder

Owns ALL GenPage connector work: it is the single owner of the connectors feature-flag gate, performs connector discovery (connections, connection references, datasets, tables, operations, and schema), creates Dataverse connection references when needed, and produces the ## Connector Bindings contract. Invoked only by…

microsoft/power-platform-skills · 90 tokens

genpage-customapi-builder

Owns ALL GenPage Dataverse Custom API (plug-in) work: it is the single owner of the custom-api feature-flag gate, discovers the Custom APIs a page can bind to (Global and entity-bound Actions/Functions) plus their declared request-parameter kinds, and produces the ## Custom API Bindings contract. Invoked by the…

microsoft/power-platform-skills · 102 tokens

ash-resource-designer

Ash resource architect — designs resources the "Ash Way" with built-in changes, validations, types, and policy checks before hand-rolling. Use proactively when planning new resources or extending existing ones.

oliver-kriska/claude-elixir-phoenix · 44 tokens

call-tracer

Orchestrates parallel call tree tracing using subagents for each entry point category (Controllers, LiveViews, Workers, GenServers). Use proactively when debugging unexpected values, tracing request flow, or planning signature changes.

oliver-kriska/claude-elixir-phoenix · 46 tokens