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 instructions/esparkman/rails-agents/claude-mdgit clone --depth 1 https://github.com/esparkman/rails-agentsWrote 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/instructions/esparkman/rails-agents/claude-md)<a href="https://agentmods.dev/instructions/esparkman/rails-agents/claude-md"><img src="https://agentmods.dev/badge/instructions/esparkman/rails-agents/claude-md.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 5.1 | $0.02245 | $0.02245 |
| Opus 5 | $0.01123 | $0.01123 |
| Sonnet 5 | $0.00449 | $0.00449 |
| Haiku 4.5 | $0.00225 | $0.00225 |
Grade A, and why
rails-agents CLAUDE.md 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 today.
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 — 147 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Repository Overview
This is a collection of specialized AI agent prompt files for Ruby on Rails development. These agents are designed to work together as a codebase-aware development team that can be dropped into any Rails project.
Not a Rails application - This repository contains only Markdown agent definition files, not executable Ruby code.
Agent Architecture
Nineteen specialized agents form a complete Rails development team:
| Agent | Role | Model | Tools |
|---|---|---|---|
rails-architect |
Technical lead, system design, architectural decisions | opus | Read, Glob, Grep, Bash |
rails-security-performance |
Security audits, performance optimization | opus | Read, Glob, Grep, Bash |
dhh-code-reviewer |
Post-write review against DHH's standards — mandatory gate after any Ruby/JS/Svelte change | opus | Read, Write, Edit, Glob, Grep, Bash |
rails-model-engineer |
Models, migrations, ActiveRecord, database | sonnet | Read, Write, Edit, Glob, Grep, Bash |
rails-controller-engineer |
Controllers, routing, authentication, APIs | sonnet | Read, Write, Edit, Glob, Grep, Bash |
rails-hotwire-engineer |
Views, Hotwire, Stimulus, frontend | sonnet | Read, Write, Edit, Glob, Grep, Bash |
rails-viewcomponent-engineer |
ViewComponent design, slots, variants, component-driven UI | sonnet | Read, Write, Edit, Glob, Grep, Bash |
rails-authentication |
Magic links, sessions, identity patterns, OAuth | sonnet | Read, Write, Edit, Glob, Grep, Bash |
rails-background-jobs |
Background jobs, Solid Queue, recurring tasks, async processing | sonnet | Read, Write, Edit, Glob, Grep, Bash |
rails-mailer |
Action Mailer, email templates, previews, delivery configuration | sonnet | Read, Write, Edit, Glob, Grep, Bash |
rails-data-migration |
Data migrations, seeds, backfills, bulk data operations | sonnet | Read, Write, Edit, Glob, Grep, Bash |
rails-domain-logic |
Service objects, form objects, query objects, POROs | sonnet | Read, Write, Edit, Glob, Grep, Bash |
rails-api-serializer |
JSON API serialization, versioning, pagination | sonnet | Read, Write, Edit, Glob, Grep, Bash |
rails-accessibility |
WCAG compliance, ARIA, keyboard navigation, screen readers | sonnet | Read, Write, Edit, Glob, Grep, Bash |
rails-i18n |
Locale files, translations, date/time formatting | sonnet | Read, Write, Edit, Glob, Grep, Bash |
rails-active-storage |
File uploads, image variants, direct uploads, cloud storage | sonnet | Read, Write, Edit, Glob, Grep, Bash |
rails-testing-expert |
Tests, fixtures, coverage | sonnet | Read, Write, Edit, Glob, Grep, Bash |
rails-deployment |
Kamal, Docker, production configuration, server operations | sonnet | Read, Write, Edit, Glob, Grep, Bash |
rails-git-workflow |
Branching, commit hygiene, pull requests, merges, releases, tags | sonnet | Read, Grep, Glob, Bash, Edit |
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.
- today Changed · +37 lines · +699 tokens per session d00dd2e2843b
- 5d ago First seen · 110 lines · 1,546 tokens per session scan A ae505b01a40d
rails-agents CLAUDE.md is an instructions file published in the GitHub repository esparkman/rails-agents (23 stars, last pushed today), licensed MIT. It adds 2,245 tokens to every session, about $0.0112 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.
Other instructions, from other repositories
comma copilot-instructions.md
Copilot instructions for comma-csv/comma, covering copilot instructions for comma, build, test, and lint commands, install dependencies for the base gemfile, install all appraisal gemfiles used by ci and build the gem.
nosia AGENTS.md
AGENTS.md instructions for dilolabs/nosia, covering 37signals rails configuration, tech stack, architecture, core philosophy and key commands.
rails_api_base CLAUDE.md
Instructions for rootstrap/rails_api_base, covering claude.md, what this repo is, common commands, testing notes and architecture.
metasploit-framework tests.instructions.md
Instructions for rapid7/metasploit-framework, covering rspec test instructions, conventions, running tests, test data and module specs.
ruby2d AGENTS.md
Instructions for ruby2d/ruby2d, covering ruby 2d guide for ai coding agents, testing, architecture, multi-ruby support and documentation.
concerns_on_rails CLAUDE.md
Claude Code instructions for VSN2015/concerns_on_rails, covering claude.md, commands, run a single spec file, run a single example by line number and build the gem.