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/levifig/rails-instructions/rails-coregit clone --depth 1 https://github.com/levifig/rails-instructionsWrote 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/levifig/rails-instructions/rails-core)<a href="https://agentmods.dev/instructions/levifig/rails-instructions/rails-core"><img src="https://agentmods.dev/badge/instructions/levifig/rails-instructions/rails-core.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 | $0.01317 | $0.01317 |
| Opus 5 | $0.00659 | $0.00659 |
| Sonnet 5 | $0.00263 | $0.00263 |
| Haiku 4.5 | $0.00132 | $0.00132 |
Grade A, and why
rails-instructions rails-core.instructions.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 5d 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 — 217 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Rails 8 Core Principles Guide
Core Philosophy
- Follow Rails conventions religiously - they exist for good reasons
- Embrace the monolith - most applications don't need microservices
- Use Rails 8's built-in features before reaching for external gems
- Write code that's a joy to work with, not just functional
- Optimize for developer happiness and productivity
Rails 8 Stack Defaults
- Use SQLite for development and production by default
- Leverage Solid Queue for background job processing
- Implement Solid Cache for caching with database backend
- Use Solid Cable for WebSocket connections
- Embrace Propshaft for asset pipeline simplicity
Framework Principles
- Convention over configuration in all decisions
- Database-driven design with Active Record at the center
- RESTful resources and routes by default
- Server-side rendering with Hotwire enhancements
- Progressive enhancement over client-side complexity
Model Design Principles
- Keep models focused on data integrity and business rules
- Use Active Record validations extensively
- Implement scopes for common query patterns
- Add database indexes for foreign keys and frequently queried columns
- Use concerns for shared behavior across models
Model Best Practices
- Include schema annotations in all model files
- Order model contents consistently: constants, includes, associations, validations, callbacks, scopes, methods
- Keep callbacks minimal - consider service objects for complex logic
- Use
dependent:options on associations to maintain referential integrity - Implement proper counter caches for performance
Controller Principles
- Keep controllers thin and focused on HTTP concerns
- Use before_action filters for common setup and authorization
- Respond to multiple formats (HTML, Turbo Stream, JSON) appropriately
- Follow REST conventions for action names
- Handle errors gracefully with proper HTTP status codes
Controller Patterns
- Use strong parameters for all user input
- Prefer redirect_to with notice/alert over render after mutations
- Implement resourceful routes whenever possible
- Keep business logic out of controllers
- Use concerns for shared controller behavior
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.
- 5d ago First seen · 217 lines · 1,317 tokens per session scan A 37b4a2d04624
rails-instructions rails-core.instructions.md is an instructions file published in the GitHub repository levifig/rails-instructions (54 stars, last pushed 1y ago), licensed MIT. It adds 1,317 tokens to every session, about $0.0066 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
mcp AGENTS.md
AGENTS.md instructions for MicrosoftDocs/mcp, covering agents.md, plugin ecosystems, sync rules, cli and validation.
llm-ide-rules AGENTS.md
AGENTS.md instructions for iloveitaly/llm-ide-rules, covering code comments, important workflow rules, alembic migrations, default content for new non-nullable columns and 1. add the column as nullable (no default needed).
llm-ide-rules pytest-integration-tests.instructions.md
Instructions for iloveitaly/llm-ide-rules, covering pytest integration tests and example integration test.
llm-ide-rules copilot-instructions.md
Copilot instructions for iloveitaly/llm-ide-rules, covering code comments and important workflow rules.
llm-ide-rules python-app.instructions.md
Instructions for iloveitaly/llm-ide-rules, covering python app, factories and database & orm.
llm-ide-rules react.instructions.md
Instructions for iloveitaly/llm-ide-rules, covering react, mock data, react hook form and styling.