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-securitynpx skills add geoffjay/claude-plugins --skill sinatra-securitygit 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 | $0.00032 | $0.04340 |
| Opus 5 | $0.00016 | $0.02170 |
| Sonnet 5 | $0.00006 | $0.00868 |
| Haiku 4.5 | $0.00003 | $0.00434 |
Grade A, and why
sinatra-security 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 — 772 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Sinatra Security Skill
Tier 1: Quick Reference - Essential Security
CSRF Protection
# Enable Rack::Protection
use Rack::Protection
# Or specifically CSRF
use Rack::Protection::AuthenticityToken
XSS Prevention
# In ERB templates - always escape by default
<%= user.bio %> # Escaped (safe)
<%== user.bio %> # Raw (dangerous!)
# In JSON responses - use proper JSON encoding
require 'json'
json({ name: user.name }.to_json)
SQL Injection Prevention
# BAD: String interpolation
DB["SELECT * FROM users WHERE email = '#{email}'"]
# GOOD: Parameterized queries
DB["SELECT * FROM users WHERE email = ?", email]
# GOOD: Hash conditions
User.where(email: email)
Secure Sessions
use Rack::Session::Cookie,
secret: ENV['SESSION_SECRET'], # Long random string
same_site: :strict,
httponly: true,
secure: production?
Input Validation
helpers do
def validate_email(email)
email.to_s.match?(/\A[\w+\-.]+@[a-z\d\-]+(\.[a-z\d\-]+)*\.[a-z]+\z/i)
end
def validate_integer(value)
Integer(value)
rescue ArgumentError, TypeError
nil
end
end
post '/users' do
halt 400, 'Invalid email' unless validate_email(params[:email])
# Process...
end
Authentication Check
helpers do
def authenticate!
halt 401, json({ error: 'Unauthorized' }) unless current_user
end
def current_user
@current_user ||= User.find_by(id: session[:user_id])
end
end
before '/admin/*' do
authenticate!
end
Tier 2: Detailed Instructions - Security Implementation
Comprehensive CSRF Protection
Configuration:
class Application < Sinatra::Base
# Enable CSRF protection
use Rack::Protection::AuthenticityToken,
except: [:json], # Skip for JSON APIs with token auth
allow_if: -> (env) {
# Skip for API endpoints with bearer token
env['HTTP_AUTHORIZATION']&.start_with?('Bearer ')
}
# Manual CSRF token generation
helpers do
def csrf_token
session[:csrf] ||= SecureRandom.hex(32)
end
def csrf_tag
"<input type='hidden' name='authenticity_token' value='#{csrf_token}'>"
end
def verify_csrf_token
token = params[:authenticity_token] || request.env['HTTP_X_CSRF_TOKEN']
halt 403, 'Invalid CSRF token' unless token == session[:csrf]
end
end
# Include in forms
post '/users' do
verify_csrf_token unless request.content_type == 'application/json'
# Process...
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 · 772 lines · 32 tokens per session scan A 7ae94493d613
sinatra-security is a skill published in the GitHub repository geoffjay/claude-plugins (8 stars, last pushed 10mo ago), licensed MIT. It adds 32 tokens to every session and 4,340 once invoked, about $0.0002 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.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
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…
agent-host-chat-contributions
Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.