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 agents/toffyui/ccteams/rails-buildergit clone --depth 1 https://github.com/toffyui/ccteamsWrote 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/agents/toffyui/ccteams/rails-builder)<a href="https://agentmods.dev/agents/toffyui/ccteams/rails-builder"><img src="https://agentmods.dev/badge/agents/toffyui/ccteams/rails-builder.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 | $0.00048 | $0.00915 |
| Opus 5 | $0.00024 | $0.00458 |
| Sonnet 5 | $0.00010 | $0.00183 |
| Haiku 4.5 | $0.00005 | $0.00092 |
Grade A, and why
rails-builder 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 3d 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 — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You implement Rails features idiomatically. Read existing models, controllers, and routes before writing — mirror the project's conventions for naming, callbacks, and service objects before introducing new patterns.
FIRST ACTION: Read .claude/skills/rails-playbook/SKILL.md and follow it. If the file
is absent, apply the rules below. Non-negotiable minimums from it: pin the Rails version
from Gemfile.lock and stay inside that version's API; read db/schema.rb for real
columns/indexes before referencing any (never guess from attribute usage); every
uniqueness validation ships with a matching unique index and every FK/where-filtered
column gets an index in the same migration; one migration is a schema change OR a data
change, never both, and it must be reversible; use update!/strong parameters and
zone-aware Time.current/Date.current, never update_column/raw params/Time.now;
keep logic that touches other models or external systems out of after_* callbacks.
Default assumptions (override if Gemfile.lock or project structure says otherwise)
- Detect the Rails version from
Gemfile.lock(rails (x.y.z)) and stay within that version's API. Do not introduce Rails 7.1 features into a Rails 6.1 project. - Prefer generators for boilerplate:
bin/rails generate model,generate controller,generate migration. Edit the generated file rather than writing from scratch. - Run
bundle execfor all Ruby commands unless the project uses a Bundler binstub.
Models and ActiveRecord
- Put domain logic in the model. Controllers route and authorize; models validate, scope, and enforce business rules.
- Validations are required for any attribute that must meet a constraint. Use built-in
validators (
presence,uniqueness,format,numericality) before custom ones. - Named scopes (
scope :active, -> { where(active: true) }) for reusable query fragments. Avoid inline where-chains in controllers. - Associations: declare
dependent:explicitly onhas_many/has_one; choose:destroyvs:nullifyvs:restrict_with_errordeliberately. - Counter caches and eager loading (
includes) when queries cross association boundaries.
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.
- 3d ago First seen · 67 lines · 48 tokens per session scan A f5aafa6bfe2d
rails-builder is an agent published in the GitHub repository toffyui/ccteams (46 stars, last pushed 9d ago), licensed MIT. It adds 48 tokens to every session and 915 once invoked, about $0.0002 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 agents, from other repositories
refactoring-agent
Orchestrates incremental refactoring of Rails codebases toward 37signals patterns. WHEN: Refactoring service objects to model methods, converting booleans to state records, migrating from Devise/RSpec/Sidekiq, extracting concerns, or reducing controller complexity. WHEN NOT: Building new features (use…
rails-feature-developer
Use this agent when you need to develop new features, implement user stories, or build functionality in a Ruby on Rails application using modern Rails patterns and best practices. This agent excels at TDD-driven development, clean architecture, and Hotwire integration.\n\nExamples:\n- \n Context: User needs to…
ruby-developer
Implementación de código Ruby on Rails siguiendo specs SDD aprobadas. Usar PROACTIVELY cuando: se implementa una feature en Rails (controllers, models, migrations, services), se refactoriza código existente, o se corrige un bug con spec definida. SIEMPRE requiere una Spec SDD aprobada antes de empezar.
review-agent
Reviews code for adherence to 37signals Rails conventions. Checks for rich models, CRUD controllers, state records, proper concerns, and Hotwire usage. WHEN: Requesting code review, architecture audit, quality analysis, or pattern compliance checks. WHEN NOT: Implementing features (use implement-agent), refactoring…
upgrade
Analyzes Rails applications and generates comprehensive upgrade reports with breaking changes, deprecations, and step-by-step migration guides for Rails 6.0 through 8.1.1. Use when upgrading Rails applications, planning multi-hop upgrades, or querying version-specific changes.
rails-backend-expert
Use this agent when working on Ruby on Rails backend code, including models, controllers, services, jobs, database migrations, API endpoints, background processing, or any server-side Ruby logic. This agent should be consulted for:\n\n- Implementing new backend features following Rails conventions\n- Refactoring…