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/el-feo/ai-context/rubynpx skills add el-feo/ai-context --skill rubygit clone --depth 1 https://github.com/el-feo/ai-contextWhat 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 | $0.00101 | $0.01467 |
| Opus 5 | $0.00051 | $0.00733 |
| Sonnet 5 | $0.00020 | $0.00293 |
| Haiku 4.5 | $0.00010 | $0.00147 |
Grade A, and why
ruby 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 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.
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 — 229 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ruby Language Skill
Error Handling Conventions
Weirich raise/fail Convention
Use fail for first-time exceptions, raise only for re-raising:
def process(order)
fail ArgumentError, "Order cannot be nil" if order.nil?
begin
gateway.charge(order)
rescue PaymentError => e
logger.error("Payment failed: #{e.message}")
raise # re-raise with raise
end
end
Custom Exception Hierarchies
Group domain exceptions under a base error:
module MyApp
class Error < StandardError; end
class PaymentError < Error; end
class InsufficientFundsError < PaymentError; end
end
# Rescue at any granularity:
rescue MyApp::InsufficientFundsError # specific
rescue MyApp::PaymentError # category
rescue MyApp::Error # all app errors
Result Objects for Expected Failures
Use result objects instead of exceptions for expected failure paths:
class Result
attr_reader :value, :error
def self.success(value) = new(value: value)
def self.failure(error) = new(error: error)
def initialize(value: nil, error: nil) = (@value, @error = value, error)
def success? = error.nil?
def failure? = !success?
end
Caller-Supplied Fallback
Let callers define error handling via blocks:
def fetch_user(id, &fallback)
User.find(id)
rescue ActiveRecord::RecordNotFound => e
fallback ? fallback.call(e) : raise
end
user = fetch_user(999) { |_| User.new(name: "Guest") }
See references/error_handling.md for full patterns and retry strategies.
Modern Ruby (3.x+)
Pattern Matching
case response
in { status: 200, body: { users: [{ name: }, *] } }
"First user: #{name}"
in { status: (400..), error: message }
"Error: #{message}"
end
# Find pattern
case array
in [*, String => str, *]
"Found string: #{str}"
end
# Pin operator
expected = 200
case response
in { status: ^expected, body: }
process(body)
end
Other 3.x+ Features
# Endless methods (3.0+)
def square(x) = x * x
def admin? = role == "admin"
# Numbered block parameters (2.7+)
[1, 2, 3].map { _1 * 2 }
# Data class - immutable value objects (3.2+)
Point = Data.define(:x, :y)
p = Point.new(x: 1, y: 2)
p.with(x: 3) # => Point(x: 3, y: 2)
# Hash#except (3.0+)
params.except(:password, :admin)
# filter_map (2.7+) - select + map in one pass
users.filter_map { |u| u.email if u.active? }
# tally (2.7+)
%w[a b a c b a].tally # => {"a"=>3, "b"=>2, "c"=>1}
What ships with it
3 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.
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 · 229 lines · 101 tokens per session scan A beb2c08210f0
ruby is a skill published in the GitHub repository el-feo/ai-context (12 stars, last pushed 1mo ago), licensed MIT. It adds 101 tokens to every session and 1,467 once invoked, about $0.0005 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 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…