What is claude-on-rails CLAUDE.md?

A set of instructions for ClaudeOnRails, a tool that coordinates AI agents while building Ruby on Rails applications.

Use it when developing ClaudeOnRails or working on Rails projects with Claude-Swarm. It covers configuration files, prompts, file references, and development guidance.

It gives the agent project rules, explains how to reference files, and helps protect the developer’s existing configuration from being overwritten.

How obie/claude-on-rails configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to obie/claude-on-rails. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/obie/claude-on-rails/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/obie/claude-on-rails

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/obie/claude-on-rails/claude-md/github.svg)](https://agentmods.dev/instructions/obie/claude-on-rails/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/obie/claude-on-rails/claude-md"><img src="https://agentmods.dev/badge/instructions/obie/claude-on-rails/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/obie/claude-on-rails/claude-md"><img src="https://agentmods.dev/badge/instructions/obie/claude-on-rails/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 725 This file is loaded in full into every session.

When invoked 725 The same file — it is already loaded in full.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00725	$0.00725
Opus 5.5	$0.00290	$0.00290
Sonnet 5.5	$0.00145	$0.00145
Haiku 4.5	$0.00072	$0.00072

Measured 2mo ago against content hash 6fc427f5473c, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

claude-on-rails 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.

CLAUDE.md · 60 lines

How it starts

The opening of the file, as written. The whole thing — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.

ClaudeOnRails Development

Project Overview

ClaudeOnRails is a Ruby gem that leverages claude-swarm to create intelligent AI agent teams for Rails development. It generates swarm configurations that allow developers to describe what they want to build in natural language, and the swarm coordinates implementation across all Rails layers.

Guidelines

1. File References in Claude

Use @filepath syntax for file references, not /file:filepath
File references are the preferred way to include content without duplicating it

2. Never Overwrite User Configuration

Always check if CLAUDE.md exists before writing to it
Use file references to include framework content rather than appending
Store framework-specific content in separate files (e.g., .claude-on-rails/context.md)

3. Claude-Swarm Integration

The default configuration file is claude-swarm.yml, not swarm.yml
Command is simply claude-swarm, not claude-swarm orchestrate
claude-swarm is a dependency, so no need to tell users to install it separately

4. Documentation Clarity

Clearly distinguish between shell commands and Claude prompts
Use > prefix for Claude prompts to avoid confusion with bash commands
Be explicit about where commands should be run vs where prompts should be typed

5. Ruby Gem Best Practices

Keep development dependencies in Gemfile, not gemspec (RuboCop rule)
Always run bundle exec rake before committing changes to catch syntax and style issues
Use bundle exec rake release for gem releases (creates tag, pushes to RubyGems)
...then create GitHub releases separately with gh release create

6. Generator Best Practices

Check for directory existence before creating agents
Make generators idempotent (running multiple times shouldn't duplicate content)
Provide clear next steps after generation
Show what will be created during the analysis phase

7. Testing Considerations

Make sure that user confirms that they have tested changes with a real Rails project before releasing
Consider different Rails configurations (API-only, full-stack, with/without GraphQL)
IMPORTANT: This project uses RSpec exclusively for testing. NEVER use Minitest or any other testing framework. Do not add minitest gems, create test/ directories, or write any Minitest-style tests. All tests must be written in RSpec format and placed in the spec/ directory.

Read the full file on GitHub · 60 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.

2mo ago First seen · 60 lines · 725 tokens per session scan A 6fc427f5473c

Subscribe to this mod's changes

claude-on-rails CLAUDE.md is an instructions file published in the GitHub repository obie/claude-on-rails (817 stars, last pushed 1y ago), licensed MIT. It adds 725 tokens to every session, about $0.0029 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.

Building agents

claude-on-rails CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
claude-on-rails CLAUDE.mdobie/claude-on-rails	Instructions file	817	1y ago	MIT	A	725	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

claude-on-rails: Instructions file for Claude Code