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 skills/dallay/agents-skills/ruby-developmentnpx skills add dallay/agents-skills --skill ruby-developmentgit clone --depth 1 https://github.com/dallay/agents-skillsWhat 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 | $0.00046 | $0.02533 |
| Opus 5 | $0.00023 | $0.01267 |
| Sonnet 5 | $0.00009 | $0.00507 |
| Haiku 4.5 | $0.00005 | $0.00253 |
Grade A, and why
ruby-development scanned grade A with 1 finding 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 yesterday.
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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
urls.map { |url| fetch(url) }.each(&block) How it starts
The opening of the file, as written. The whole thing — 400 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ruby Development
Production patterns and idioms for Ruby programming, covering project structure, gems, blocks, testing, metaprogramming, and error handling.
When to Use This Skill
- Starting or structuring a Ruby project
- Working with Bundler and gem dependencies
- Writing idiomatic Ruby with blocks, procs, and lambdas
- Testing with RSpec or Minitest
- Applying Ruby style conventions
- Writing Rake tasks for automation
- Understanding metaprogramming basics
Core Concepts
1. Project Layout
myapp/
├── lib/
│ ├── myapp.rb # Main entry, requires sub-modules
│ └── myapp/
│ ├── client.rb
│ ├── parser.rb
│ └── errors.rb
├── spec/ # RSpec tests
│ ├── spec_helper.rb
│ ├── myapp/
│ │ ├── client_spec.rb
│ │ └── parser_spec.rb
│ └── support/
│ └── shared_contexts.rb
├── bin/
│ └── myapp # CLI executable
├── Gemfile
├── Gemfile.lock
├── Rakefile
├── myapp.gemspec # If building a gem
└── README.md
2. Key Principles
| Principle | Ruby Idiom |
|---|---|
| Duck typing | Respond to methods, not check class |
| Convention | snake_case methods, PascalCase classes |
| Blocks everywhere | Yield to blocks for callbacks and iteration |
| Open classes | Extend existing classes carefully |
| POLA | Principle of Least Astonishment |
Quick Start
# Create a new gem skeleton
bundle gem myapp
# Install dependencies
bundle install
# Run tests
bundle exec rspec
bundle exec rake test # Minitest
# Run linter
bundle exec rubocop
# Interactive console
bundle exec irb -r ./lib/myapp
Patterns
Pattern 1: Error Handling
module MyApp
# Define a hierarchy of custom errors
class Error < StandardError; end
class NotFoundError < Error; end
class ValidationError < Error
attr_reader :field
def initialize(field, message)
@field = field
super("Validation failed on #{field}: #{message}")
end
end
class AuthenticationError < Error; end
end
# Raise and rescue with specificity
class UserService
def find!(id)
user = repository.find(id)
raise MyApp::NotFoundError, "User #{id} not found" unless user
user
end
def create(params)
validate!(params)
repository.save(User.new(params))
rescue MyApp::ValidationError => e
logger.warn("Validation failed: #{e.message}")
raise
rescue StandardError => e
logger.error("Unexpected error: #{e.message}")
raise MyApp::Error, "Failed to create user: #{e.message}"
end
private
def validate!(params)
raise MyApp::ValidationError.new(:email, "is required") if params[:email].nil?
raise MyApp::ValidationError.new(:email, "is invalid") unless params[:email].match?(URI::MailTo::EMAIL_REGEXP)
end
end
# Ensure cleanup with ensure
def with_temp_file
file = Tempfile.new("myapp")
yield file
ensure
file&.close
file&.unlink
end
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.
- yesterday First seen · 400 lines · 46 tokens per session scan A b31de47d01df
ruby-development is a skill published in the GitHub repository dallay/agents-skills (2 stars, last pushed 9d ago), licensed MIT. It adds 46 tokens to every session and 2,533 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…