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.
git clone --depth 1 https://github.com/igmarin/rails-ai-bridgeWrote 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/rules/igmarin/rails-ai-bridge/rails-mcp-tools)<a href="https://agentmods.dev/rules/igmarin/rails-ai-bridge/rails-mcp-tools"><img src="https://agentmods.dev/badge/rules/igmarin/rails-ai-bridge/rails-mcp-tools/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/rules/igmarin/rails-ai-bridge/rails-mcp-tools"><img src="https://agentmods.dev/badge/rules/igmarin/rails-ai-bridge/rails-mcp-tools.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 | $0.00323 | $0.00323 |
| Opus 5.5 | $0.00129 | $0.00129 |
| Sonnet 5.5 | $0.00065 | $0.00065 |
| Haiku 4.5 | $0.00032 | $0.00032 |
Grade A, and why
rails-mcp-tools 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 1mo 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.
What it actually says
MCP Tool Reference
Detail levels: summary | standard (default) | full
rails_get_schema
Params: table, detail, limit, offset, format
rails_get_schema(detail:"summary")— all tables with column countsrails_get_schema(table:"users")— full detail for one tablerails_get_schema(detail:"summary", limit:20, offset:40)— paginate
rails_get_model_details
Params: model, detail
rails_get_model_details(detail:"summary")— list model namesrails_get_model_details(model:"User")— full detail
rails_get_routes
Params: controller, detail, limit, offset
rails_get_routes(detail:"summary")— counts per controllerrails_get_routes(controller:"users")— one controller
rails_get_controllers
Params: controller, detail
rails_get_controllers(detail:"summary")— names + action countsrails_get_controllers(controller:"UsersController")— full detail
Other tools
rails_get_config— cache, session, middlewarerails_get_test_info— framework, factories, CIrails_get_gems— categorized gemsrails_get_conventions— architecture patternsrails_search_code(pattern:"regex", file_type:"rb", max_results:20)
Start with detail:"summary", then drill into specifics.
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.
- 1mo ago First seen · 38 lines · 323 tokens per session scan A b0f729053561
rails-mcp-tools is a cursor rule published in the GitHub repository igmarin/rails-ai-bridge (16 stars, last pushed yesterday), licensed MIT. It adds 323 tokens to every session, about $0.0013 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 2026-09-15.
Other cursor rules, from other repositories
hatch3r-ruby-rails-patterns
Ruby 3.3+ and Rails 8.x conventions covering Hotwire (Turbo + Stimulus), ActiveRecord patterns, Sidekiq jobs, RSpec testing, RuboCop / Standard, and YJIT performance.
graftcode-ruby
Mandatory Graftcode architecture rules for building Ruby backend services (plain classes exposed via Graftcode Gateway, not REST). Ruby is a supported gg runtime but has no dedicated Quick Start yet.
workato-connector-sdk
Cursor rule "workato-connector-sdk" from rkawaishi/workato-dev-kit, covering workato connector sdk (connector.rb), file structure, top-level structure of connector.rb, authorization types and required keys for an action.
skill-rails-api
Padrões DARE para APIs em Ruby on Rails 8 — API mode, ActiveRecord, Solid Queue, Solid Cable, Action Cable, strong parameters, services, serializers (Blueprinter/Alba), Devise/JWT, rack-attack, rswag/grape-swagger.
rails-cursorrules-prompt-file
description: "Cursor rules for Rails development with basic setup." globs: / alwaysApply: false.
rails
Rails: thin controllers, service objects, Turbo.