Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/stevegeek/claude-ruby-pluginsnpx agentmods add skills/stevegeek/claude-ruby-plugins/ruby-rbsWrote 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/skills/stevegeek/claude-ruby-plugins/ruby-rbs)<a href="https://agentmods.dev/skills/stevegeek/claude-ruby-plugins/ruby-rbs"><img src="https://agentmods.dev/badge/skills/stevegeek/claude-ruby-plugins/ruby-rbs/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/skills/stevegeek/claude-ruby-plugins/ruby-rbs"><img src="https://agentmods.dev/badge/skills/stevegeek/claude-ruby-plugins/ruby-rbs.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 | $0.00060 | $0.01587 |
| Opus 5.5 | $0.00024 | $0.00635 |
| Sonnet 5.5 | $0.00012 | $0.00317 |
| Haiku 4.5 | $0.00006 | $0.00159 |
Grade A, and why
ruby-rbs 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.
How it starts
The opening of the file, as written. The whole thing — 208 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ruby RBS Type Signatures
RBS is Ruby's official type signature language for describing the structure of Ruby programs - classes, modules, methods, and types. This skill covers both approaches to adding types:
- Inline RBS (
# rbs_inline: enabled) - Type annotations embedded in Ruby source files as comments - Standalone RBS files (
.rbs) - Separate signature files that describe Ruby code
Choosing an Approach
| Aspect | Inline RBS | Standalone .rbs Files |
|---|---|---|
| Co-location | Types live with code | Types in separate sig/ directory |
| Ruby files | Modified with comments | Unchanged |
| Tooling | Requires rbs-inline gem | Native RBS support |
| Use case | New code, gradual adoption | Libraries, gems, existing codebases |
Use inline RBS when: Starting fresh, want types near code, prefer gradual typing Use standalone .rbs when: Publishing gems, typing third-party code, complete API documentation
Subskills
For detailed guidance on each approach:
subskills/inline/SKILL.md- Writing inline RBS annotations in Ruby filessubskills/rbs-files/SKILL.md- Writing standalone .rbs signature files
Core Type Syntax (Both Approaches)
Basic Types
String # String instance
Integer # Integer instance
Float # Float instance
bool # true | false
boolish # Any truthy/falsy value (for predicates)
nil # nil value
void # Return value not used
untyped # Skip type checking (gradual typing)
top # Supertype of all types
bot # Subtype of all types (never returns)
self # Type of receiver
instance # Instance of the class
class # Singleton class
Compound Types
String? # Optional: String | nil
String | Integer # Union type
_Reader & _Writer # Intersection type
Array[String] # Generic class
Hash[Symbol, Integer] # Hash with typed keys/values
[String, Integer] # Tuple (fixed-size array)
{ name: String, age: Integer } # Record (typed hash)
{ name: String, age?: Integer } # Record with optional key
^(Integer) -> String # Proc/lambda type
What ships with it
11 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- references/comparing-signatures.md 4.3 KB
- references/patterns.md 3.3 KB
- references/rbs-test-instrumentation.md 4.5 KB
- references/scaffolding.md 4.5 KB
- references/steep-integration.md 7.1 KB
- references/troubleshooting.md 8.2 KB
- references/type-syntax.md 6.2 KB
- references/type-tracer.md 4.9 KB
- references/validating-signatures.md 5.2 KB
- subskills/inline/SKILL.md 3.4 KB
- subskills/rbs-files/SKILL.md 5.1 KB
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 · 208 lines · 60 tokens per session scan A ee66d5e220e2
ruby-rbs is a skill published in the GitHub repository stevegeek/claude-ruby-plugins (19 stars, last pushed 5mo ago), licensed Unlicense. It adds 60 tokens to every session and 1,587 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
rubyllm
Build and maintain Ruby or Rails applications with the RubyLLM AI framework. Use for chats, agents, tools, MCP servers, structured output, judgments, evaluations, media generation, transcription, OCR, moderation, embeddings, reranking, tracing, Rails integration, and RubyLLM upgrades; not for contributing to the…
new
Create a new project to start development quickly.
rspec-conventions
Rootstrap RSpec conventions. Use when writing, reviewing, or editing RSpec test files (spec//spec.rb, spec/railshelper.rb, spec/spechelper.rb, spec/support//.rb) or factories. Covers describe/context structure, let/subject, matchers, factories, mocking/stubbing, shared examples, and spec types (model, request…
dhh-rails-style
This skill should be used when writing Ruby and Rails code in DHH's distinctive 37signals style. It applies when writing Ruby code, Rails applications, creating models, controllers, or any Ruby file. Triggers on Ruby/Rails code generation, refactoring requests, code review, or when the user mentions DHH, 37signals…
ruby-patterns
Ruby/Rails: blocks, metaprogramming, ActiveRecord, Sidekiq, RSpec, Sorbet, Hanami. Triggers: Ruby, Rails, ActiveRecord, Sidekiq, RSpec, Gemfile, bundler, Hanami, Sorbet.
ruby-idioms
Modern Ruby (3.x) idioms: pattern matching, keyword arguments, immutable data structures, error hierarchies, and RSpec testing. Use when writing, modifying, or reviewing Ruby scripts, gems, or business logic. Pair with rails-idioms for Rails applications.