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.
git clone --depth 1 https://github.com/geoffjay/claude-pluginsWrote 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/commands/geoffjay/claude-plugins/sinatra-review)<a href="https://agentmods.dev/commands/geoffjay/claude-plugins/sinatra-review"><img src="https://agentmods.dev/badge/commands/geoffjay/claude-plugins/sinatra-review/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/commands/geoffjay/claude-plugins/sinatra-review"><img src="https://agentmods.dev/badge/commands/geoffjay/claude-plugins/sinatra-review.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 | $0.00017 | $0.03521 |
| Opus 5.5 | $0.00007 | $0.01408 |
| Sonnet 5.5 | $0.00003 | $0.00704 |
| Haiku 4.5 | $0.00002 | $0.00352 |
Grade A, and why
sinatra-review 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 — 648 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Sinatra Review Command
Performs comprehensive code review of Sinatra applications, identifying security vulnerabilities, performance issues, routing conflicts, and deviations from best practices.
Arguments
- $1: path (optional) - Path to review (defaults to current directory)
Usage Examples
# Review current directory
/sinatra-review
# Review specific directory
/sinatra-review /path/to/sinatra-app
# Review specific file
/sinatra-review app/controllers/users_controller.rb
Workflow
Step 1: Scan and Identify Application Files
Discovery Phase:
- Locate
config.ruto identify Rack application - Find Sinatra application files (controllers, routes)
- Identify application structure (classic vs modular)
- Scan for middleware configuration
- Locate view templates and helpers
- Find configuration files
- Identify database and model files
File Patterns to Search:
# Application files
*.rb files inheriting from Sinatra::Base
config.ru
app.rb (classic style)
app/controllers/*.rb
lib/**/*.rb
# View templates
views/**/*.erb
views/**/*.haml
views/**/*.slim
# Configuration
config/*.rb
Gemfile
.env files
Step 2: Analyze Route Definitions
Route Conflict Detection:
Check for:
- Duplicate routes with same path and HTTP method
- Overlapping routes where order matters (specific before generic)
- Missing route constraints leading to ambiguous matching
- Wildcard route conflicts
Examples of Issues:
# ISSUE: Route order conflict
get '/users/new' do
# Never reached because of wildcard below
end
get '/users/:id' do
# This catches /users/new
end
# FIX: Specific routes before wildcards
get '/users/new' do
# Now reached first
end
get '/users/:id' do
# Only catches other IDs
end
# ISSUE: Duplicate routes
get '/api/users' do
# First definition
end
get '/api/users' do
# Overwrites first - only this runs
end
# ISSUE: Missing validation
get '/users/:id' do
user = User.find(params[:id]) # What if id is not numeric?
end
# FIX: Add validation
get '/users/:id', id: /\d+/ do
user = User.find(params[:id])
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.
- 1mo ago First seen · 648 lines · 17 tokens per session scan A 2d77c4a5a2dc
sinatra-review is a command published in the GitHub repository geoffjay/claude-plugins (8 stars, last pushed 11mo ago), licensed MIT. It adds 17 tokens to every session and 3,521 once invoked, about $0.0001 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 2026-08-31.
Other commands, from other repositories
review-ruby-code
Review Ruby/Rails code with Sandi Metz rules and SOLID principles.
cleanup
You are a senior Rails developer tasked with reviewing a branch of code with extreme attention to architectural and code quality issues. Your goal is to provide a thorough, systematic analysis of the code, focusing on specific categories and potential issues.
rails-review
Ruby on Rails code review with severity-based filtering.
devkit.typescript.code-review
Provides comprehensive TypeScript monorepo code review for Nx workspaces including NestJS backend, React web, and React Native mobile apps. Use when reviewing architecture, boundaries, security, performance, CI/CD and Nx-specific practices.
review-uv-script
Review uv Python script for PEP 723 compliance and best practices.
package-review
Review the current Python package for best-practice violations — project structure, pyproject.toml, typing, testing, CI/CD, documentation, versioning, API design, packaging, security, and developer experience.