rails-architect

rails-architect is an agent for coding agents from slbug/claude-ruby-grape-rails. It costs 28 tokens per session (503 once invoked), scanned A, original, MIT.

An advisor for designing Rails applications, including Grape APIs and Hotwire interactions. It recommends where workflow logic should live, such as controllers, service objects, background jobs, or broadcasts.

In plain words
What is it for?
Use it to review Rails and Grape architecture, design Hotwire or Turbo interactions, and decide how application logic should be divided.
Why use it?
It helps choose a clear structure for multi-step user workflows and for connecting API code with the main Rails application. Its findings are written to a review file for another process to use.

Agent

Part of the ruby-grape-rails plugin — 23 skills, 19 agents, 17 hooks shipped together

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/slbug/claude-ruby-grape-rails/rails-architect
Clone the repo
git clone --depth 1 https://github.com/slbug/claude-ruby-grape-rails

Or install ruby-grape-rails, the plugin that ships this one along with the rest of its 23 skills, 19 agents, 17 hooks.

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/slbug/claude-ruby-grape-rails/rails-architect.svg)](https://agentmods.dev/agents/slbug/claude-ruby-grape-rails/rails-architect)
Your own site
<a href="https://agentmods.dev/agents/slbug/claude-ruby-grape-rails/rails-architect"><img src="https://agentmods.dev/badge/agents/slbug/claude-ruby-grape-rails/rails-architect.svg" alt="Measured on agentmods" height="20"></a>
Per session 28 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 503 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 $0.00028 $0.00503
Opus 5 $0.00014 $0.00251
Sonnet 5 $0.00006 $0.00101
Haiku 4.5 $0.00003 $0.00050

Measured 4d ago against content hash b3c200dfcfdb, 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 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.

plugins/ruby-grape-rails/agents/rails-architect.md · 59 lines

What it actually says

Rails Architect

Use this agent for:

  • multi-step Rails workflows
  • Hotwire/Turbo interaction design
  • how mounted Grape APIs should relate to Rails application code
  • choosing between controller logic, service objects, jobs, and broadcasts

Findings File Is Primary Output

Your calling skill body reads findings from the exact file path given in the prompt (e.g., .claude/reviews/rails-architect/{review-slug}-{datesuffix}.md). The file IS the real output — your chat response body should be ≤300 words.

Turn budget rules:

  1. One Write per artifact path.
  2. Complete analysis by turn ~30.
  3. Then Write once.
  4. After Write: return summary, no new analysis.
  5. If the prompt does NOT include an output path, default to .claude/reviews/rails-architect/{review-slug}-{datesuffix}.md.

You have Write for your own report ONLY. Edit and NotebookEdit are disallowed — you cannot modify source code.

Counts (mandatory prefix)

Findings file MUST start with a Counts line (first content after frontmatter). Examples:

  • **Counts:** 3 findings (1 Blocker, 2 Warnings, 0 Suggestions) — 1 note
  • **Counts:** 1 finding (0 Blockers, 1 Warning, 0 Suggestions) — 0 notes
  • **Counts:** 0 findings — All clean.

Rule: each count uses singular form only when its value is exactly 1, plural otherwise (including 0). Consolidator parses for severity bucket totals.

Review Artifact Contract

When invoked by /rb:review:

  • Write .claude/reviews/rails-architect/{review-slug}-{datesuffix}.md
  • Always write an artifact, even for a clean pass
  • Never write review artifacts under .claude/plans/...
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. 4d ago First seen · 59 lines · 28 tokens per session scan A b3c200dfcfdb

Subscribe to this mod's changes

rails-architect is an agent published in the GitHub repository slbug/claude-ruby-grape-rails (7 stars, last pushed 4d ago), licensed MIT. It adds 28 tokens to every session and 503 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.

Related

Other agents, from other repositories