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 commands/geoffjay/claude-plugins/sinatra-testgit 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 | $0.00018 | $0.05196 |
| Opus 5 | $0.00009 | $0.02598 |
| Sonnet 5 | $0.00004 | $0.01039 |
| Haiku 4.5 | $0.00002 | $0.00520 |
Grade A, and why
sinatra-test 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 — 861 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Sinatra Test Command
Generates comprehensive test suites for Sinatra applications including route tests, middleware tests, helper tests, and integration tests using RSpec or Minitest.
Arguments
- $1: test-type (optional) - Type of tests to generate:
routes,middleware,helpers, orall(default:all) - $2: framework (optional) - Testing framework:
rspecorminitest(default:rspec)
Usage Examples
# Generate all tests using RSpec
/sinatra-test
# Generate only route tests with RSpec
/sinatra-test routes
# Generate all tests using Minitest
/sinatra-test all minitest
# Generate middleware tests with Minitest
/sinatra-test middleware minitest
# Generate helper tests with RSpec
/sinatra-test helpers rspec
Workflow
Step 1: Analyze Application Structure
Discovery Phase:
- Identify application type (classic vs modular)
- Locate controller files
- Extract route definitions
- Find middleware stack
- Identify helper methods
- Check existing test structure
- Detect testing framework if already configured
Files to Analyze:
# Controllers
app/controllers/**/*.rb
app.rb (classic style)
# Middleware
config.ru
config/**/*.rb
# Helpers
app/helpers/**/*.rb
helpers/ directory
# Existing tests
spec/**/*_spec.rb
test/**/*_test.rb
Route Extraction:
# Parse routes from controller files
# Identify: HTTP method, path, parameters, conditions
# Example routes to extract:
get '/users' do
# Handler
end
get '/users/:id', :id => /\d+/ do
# Handler with constraint
end
post '/users', :provides => [:json] do
# Handler with content negotiation
end
Step 2: Generate Test Structure (RSpec)
Create spec_helper.rb if missing:
# spec/spec_helper.rb
ENV['RACK_ENV'] = 'test'
require 'simplecov'
SimpleCov.start do
add_filter '/spec/'
add_filter '/config/'
end
require_relative '../config/environment'
require 'rack/test'
require 'rspec'
require 'json'
# Database setup (if applicable)
if defined?(Sequel)
require 'database_cleaner/sequel'
RSpec.configure do |config|
config.before(:suite) do
DatabaseCleaner.strategy = :transaction
DatabaseCleaner.clean_with(:truncation)
end
config.around(:each) do |example|
DatabaseCleaner.cleaning do
example.run
end
end
end
end
RSpec.configure do |config|
config.include Rack::Test::Methods
config.expect_with :rspec do |expectations|
expectations.include_chain_clauses_in_custom_matcher_descriptions = true
end
config.mock_with :rspec do |mocks|
mocks.verify_partial_doubles = true
end
config.shared_context_metadata_behavior = :apply_to_host_groups
config.filter_run_when_matching :focus
config.example_status_persistence_file_path = 'spec/examples.txt'
config.disable_monkey_patching!
config.warnings = true
config.order = :random
Kernel.srand config.seed
end
# Helper methods for all specs
module SpecHelpers
def json_response
JSON.parse(last_response.body)
end
def auth_header(token)
{ 'HTTP_AUTHORIZATION' => "Bearer #{token}" }
end
end
RSpec.configure do |config|
config.include SpecHelpers
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 · 861 lines · 18 tokens per session scan A f31035c2637b
sinatra-test is a command published in the GitHub repository geoffjay/claude-plugins (8 stars, last pushed 10mo ago), licensed MIT. It adds 18 tokens to every session and 5,196 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 commands, from other repositories
git
Git operations with intelligent commit messages and workflow optimization.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
constitution
Create or update the project constitution from interactive or provided principle inputs.