Borrowing it
Nothing to install: this file belongs to esparkman/rails-agents. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/esparkman/rails-agents/main/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/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<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="Reviewed on agentmods" width="80" 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 5.5 | $0.00898 | $0.00898 |
| Sonnet 5.5 | $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 2mo 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.
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.
- 2mo ago Changed · +37 lines · +699 tokens per session d00dd2e2843b
- 2mo 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 1mo ago), licensed MIT. It adds 2,245 tokens to every session, about $0.0090 per session on Opus 5.5. 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.
rails-agents CLAUDE.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| rails-agents CLAUDE.mdesparkman/rails-agents | Instructions file | 23 | 1mo ago | MIT | A | 2,245 | Claude Code |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | yesterday | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |