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/geoffjay/claude-plugins/sinatra-patternsnpx skills add geoffjay/claude-plugins --skill sinatra-patternsgit clone --depth 1 https://github.com/geoffjay/claude-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 | $0.00028 | $0.03054 |
| Opus 5 | $0.00014 | $0.01527 |
| Sonnet 5 | $0.00006 | $0.00611 |
| Haiku 4.5 | $0.00003 | $0.00305 |
Grade A, and why
sinatra-patterns 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 — 657 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Sinatra Patterns Skill
Tier 1: Quick Reference
Common Routing Patterns
Basic Routes:
get '/' do
'Hello World'
end
post '/users' do
# Create user
end
put '/users/:id' do
# Update user
end
delete '/users/:id' do
# Delete user
end
Route Parameters:
# Named parameters
get '/users/:id' do
User.find(params[:id])
end
# Parameter constraints
get '/users/:id', :id => /\d+/ do
# Only matches numeric IDs
end
# Wildcard
get '/files/*.*' do
# params['splat'] contains matched segments
end
Query Parameters:
get '/search' do
query = params[:q]
page = params[:page] || 1
results = search(query, page: page)
end
Basic Middleware
# Session middleware
use Rack::Session::Cookie, secret: ENV['SESSION_SECRET']
# Security middleware
use Rack::Protection
# Logging
use Rack::CommonLogger
# Compression
use Rack::Deflater
Simple Error Handling
not_found do
'Page not found'
end
error do
'Internal server error'
end
error 401 do
'Unauthorized'
end
Helpers
helpers do
def logged_in?
!session[:user_id].nil?
end
def current_user
@current_user ||= User.find_by(id: session[:user_id])
end
end
Tier 2: Detailed Instructions
Advanced Routing
Modular Applications:
# app/controllers/base_controller.rb
class BaseController < Sinatra::Base
configure do
set :views, Proc.new { File.join(root, '../views') }
set :public_folder, Proc.new { File.join(root, '../public') }
end
helpers do
def json_response(data, status = 200)
content_type :json
halt status, data.to_json
end
end
end
# app/controllers/users_controller.rb
class UsersController < BaseController
get '/' do
users = User.all
json_response(users.map(&:to_hash))
end
get '/:id' do
user = User.find(params[:id]) || halt(404)
json_response(user.to_hash)
end
post '/' do
user = User.create(params[:user])
if user.persisted?
json_response(user.to_hash, 201)
else
json_response({ errors: user.errors }, 422)
end
end
end
# config.ru
map '/users' do
run UsersController
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 · 657 lines · 28 tokens per session scan A 831963e30e78
sinatra-patterns is a skill published in the GitHub repository geoffjay/claude-plugins (8 stars, last pushed 10mo ago), licensed MIT. It adds 28 tokens to every session and 3,054 once invoked, about $0.0001 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 2026-08-31.
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…