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/stevegeek/claude-ruby-plugins/inlinenpx skills add stevegeek/claude-ruby-plugins --skill inlinegit clone --depth 1 https://github.com/stevegeek/claude-ruby-pluginsWhat 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 | $0.00030 | $0.00968 |
| Opus 5 | $0.00015 | $0.00484 |
| Sonnet 5 | $0.00006 | $0.00194 |
| Haiku 4.5 | $0.00003 | $0.00097 |
Grade A, and why
inline-rbs 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 2d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
def fetch(n = nil) How it starts
The opening of the file, as written. The whole thing — 191 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Inline RBS Annotations
Write type signatures directly in Ruby source files using special comments. Requires the rbs-inline gem.
Quick Start
Every file needs the magic comment:
# rbs_inline: enabled
class Person
attr_reader :name #: String
attr_reader :age #: Integer?
#: (String, ?Integer?) -> void
def initialize(name, age = nil)
@name = name
@age = age
end
end
Method Annotation Styles
1. Primitive #: (Most Concise)
# Before method
#: (String) -> Integer
def count(text)
text.length
end
# Inline return type
def name #: String
@name
end
# Multiple overloads
#: () -> String?
#: (Integer) -> Array[String]
def fetch(n = nil)
n ? @items.take(n) : @items.first
end
2. Keyword # @rbs (Structured)
# @rbs (String, Integer) -> String
def format(text, width)
text.ljust(width)
end
# Overloading with pipe
# @rbs (String) -> Integer
# | (Integer) -> Integer
def double(value)
value * 2
end
3. Doc-Style Parameters (Self-Documenting)
# @rbs text: String -- Input text
# @rbs width: Integer -- Max width
# @rbs strict: bool -- Strict mode
# @rbs return: Array[String]
def wrap(text, width: 80, strict: false)
# Implementation
end
Attributes and Variables
attr_reader :name #: String
attr_accessor :count #: Integer
# @rbs @items: Array[String] # Instance variable
# @rbs self.@cache: Hash[Symbol, T] # Class instance variable
VERSION = "1.0" #: String # Constant
Block Annotations
# Required block
# @rbs () { (String) -> void } -> void
def each(&block)
@items.each(&block)
end
# Optional block (? before type)
# @rbs () { (Integer) -> void }? -> Integer?
def process(&block)
yield(42) if block
end
# Using boolish for filters
#: () { (String) -> boolish } -> Array[String]
def select(&block)
@items.select(&block)
end
Generic Classes
# @rbs generic T
class Container
# @rbs (T) -> void
def initialize(value)
@value = value
end
#: () -> T
def get
@value
end
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.
- 2d ago First seen · 191 lines · 30 tokens per session scan A fd92bc09c0bf
inline-rbs is a skill published in the GitHub repository stevegeek/claude-ruby-plugins (19 stars, last pushed 4mo ago), licensed Unlicense. It adds 30 tokens to every session and 968 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 2026-08-30.
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…