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 rules/levifig/rails-instructions/rails-rulesgit clone --depth 1 https://github.com/levifig/rails-instructionsWhat 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 | $0.03067 | $0.03067 |
| Opus 5 | $0.01533 | $0.01533 |
| Sonnet 5 | $0.00613 | $0.00613 |
| Haiku 4.5 | $0.00307 | $0.00307 |
Grade A, and why
rails-rules 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 2d 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 — 438 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Rails Development Rules - The Rails Way with AI Agents
Built for: Solo developer + AI agents, Linear MCP integration, maximum joy
Core Philosophy
You are building a Rails 8+ application following The Rails Way™. Code should be:
- Convention over configuration
- Database-first design
- Progressive enhancement with Hotwire
- Zero-build frontend approach
- Test-driven with Minitest
- Optimized for AI agent collaboration
- Lean, readable, and maintainable
Rails 8+ Stack Preferences
- Authentication: Rails built-in (
rails generate authentication) - Background Jobs: Solid Queue (default Rails 8)
- Caching: Solid Cache (database-backed, Redis when needed)
- WebSockets: Action Cable with Solid Cable adapter
- Database: PostgreSQL with Active Record
- Frontend: Hotwire (Turbo + Stimulus) + TailwindCSS
- Asset Pipeline: Propshaft (simpler, no-build approach)
- Testing: Minitest with fixtures (no RSpec, no factories)
- Rich Text: Action Text for content editing
- File Uploads: Active Storage with direct uploads
- Deployment: Kamal with Docker
- Code Quality: StandardRB for linting/formatting
- Development Tools: Bullet gem for N+1 detection, Annotate gem for schema docs
- Error Tracking: Rails built-in error reporter
Detailed Guides
This document provides core principles. For detailed implementation guidance, see:
- core.md - Rails 8 conventions and patterns
- models.md - Active Record patterns and best practices
- controllers.md - Controller design and RESTful patterns
- services.md - Service objects and business logic
- testing.md - Testing philosophy and Minitest patterns
- security.md - Security best practices and authorization
- performance.md - Database optimization and caching
- api.md - API design and versioning (when needed)
- importmaps.md - JavaScript without build steps
- hotwire.md - Turbo & Stimulus patterns
- views.md - View helpers and rendering
- styling.md - TailwindCSS integration
- background-jobs.md - Solid Queue configuration
- deployment.md - Kamal deployment guide
- mobile.md - Hotwire Native for mobile apps (optional)
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.
- 2d ago First seen · 438 lines · 3,067 tokens per session scan A 336d6087ac62
rails-rules is a cursor rule published in the GitHub repository levifig/rails-instructions (54 stars, last pushed 1y ago), licensed MIT. It adds 3,067 tokens to every session, about $0.0153 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 cursor rules, from other repositories
pytest-integration-tests
Below is an example test. Notice the following.
python-app
Cursor rule "python-app" from iloveitaly/llm-ide-rules, covering python app, factories and database & orm.
react-router
Cursor rule "react-router" from iloveitaly/llm-ide-rules, covering react router, loading mock data, how to use clientloader and loading backend data.
react
Cursor rule "react" from iloveitaly/llm-ide-rules, covering react, mock data, react hook form and styling.
creating-cursor-rules
Meta-rule for creating effective Cursor IDE rules with best practices, patterns, and examples.
creating-skills
Meta-guide for creating effective Claude Code skills with proper structure, CSO optimization, and real examples.