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/slbug/claude-ruby-grape-railsWrote 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/plugins/slbug/claude-ruby-grape-rails/ruby-grape-rails)<a href="https://agentmods.dev/plugins/slbug/claude-ruby-grape-rails/ruby-grape-rails"><img src="https://agentmods.dev/badge/plugins/slbug/claude-ruby-grape-rails/ruby-grape-rails/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/plugins/slbug/claude-ruby-grape-rails/ruby-grape-rails"><img src="https://agentmods.dev/badge/plugins/slbug/claude-ruby-grape-rails/ruby-grape-rails.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
ruby-grape-rails 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 15d 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.
What it actually says
{
"name": "ruby-grape-rails",
"version": "1.16.19",
"description": "Specialist agents, Iron Laws, parallel code review, and plan→work→verify→review→compound workflow for Ruby, Rails, Grape, Sidekiq, Hotwire, Active Record, and Sequel projects.",
"keywords": ["ruby", "rails", "grape", "sidekiq", "hotwire", "turbo", "stimulus", "active-record", "sequel", "postgres", "redis", "rspec", "minitest", "brakeman", "rubocop", "karafka", "solid-queue", "tidewave", "iron-laws", "code-review", "specialist-agents", "plan-work-verify"],
"author": {
"name": "Alexander Grebennik",
"url": "https://github.com/slbug"
},
"homepage": "https://github.com/slbug/claude-ruby-grape-rails",
"repository": "https://github.com/slbug/claude-ruby-grape-rails"
}
What it installs
The manifest is a name and a version. 52 skills, 19 agents, 17 hooks travel with it, and installing the plugin installs all of them — 3,023 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Skill rb:plan A 52 tokens
- Skill rb:triage A 48 tokens
- Skill rb:research A 44 tokens
- Skill rb:verify A 53 tokens
- Skill rb:dry-rb-patterns A 45 tokens
- Skill rb:sequel-patterns A 32 tokens
- Skill rb:work A 46 tokens
- Skill rb:async-patterns A 28 tokens
- Skill rb:brainstorm A 39 tokens
- Skill rb:compound A 39 tokens
- Skill ruby-idioms A 57 tokens
- Skill safe-migrations A 55 tokens
- Skill sidekiq A 56 tokens
- Skill hotwire-patterns A 49 tokens
- Skill rb:brief A 42 tokens
- Skill rb:hotwire-native A 31 tokens
- Skill rb:karafka A 28 tokens
- Skill rb:runtime A 32 tokens
- Skill rb:state-audit A 33 tokens
- Skill rb:techdebt A 55 tokens
- Skill rails-idioms A 52 tokens
- Skill rb:full A 92 tokens
- Skill rb:learn A 41 tokens
- Skill rb:provenance-scan A 64 tokens
- Skill iron-laws A 53 tokens
- Skill rb:boundaries A 37 tokens
- Skill rb:document A 36 tokens
- Skill rb:review A 48 tokens
- Skill intent-detection A 68 tokens
- Skill rb:challenge A 33 tokens
- Skill security A 50 tokens
- Skill rb:discovery-report A 88 tokens
- Skill rb:investigate A 47 tokens
- Skill rb:audit A 40 tokens
- Skill rb:intro A 42 tokens
- Skill rails-contexts A 47 tokens
- Skill testing A 52 tokens
- Skill active-record-patterns A 50 tokens
- Skill rb:trace A 43 tokens
- Skill grape-idioms A 55 tokens
- Skill rb:init B 45 tokens
- Skill rb:perf A 44 tokens
- Skill rb:constraint-debug A 44 tokens
- Skill rb:n1-check A 46 tokens
- Skill rb:quick A 46 tokens
- Skill rb:examples A 22 tokens
- Skill rubydoc-fetcher A 39 tokens
- Skill rb:secrets B 36 tokens
- Skill rb:compression-report C 37 tokens
- Skill rb:deploy C 26 tokens
- Skill rb:permissions D 42 tokens
- Skill rb:pr-review A 56 tokens
- Agent iron-law-judge A 30 tokens
- Agent data-integrity-reviewer A 32 tokens
- Agent migration-safety-reviewer A 29 tokens
- Agent web-researcher A 35 tokens
- Agent verification-runner A 38 tokens
- Agent dependency-analyzer A 35 tokens
- Agent security-analyzer A 37 tokens
- Agent deep-bug-investigator A 41 tokens
- Agent output-verifier A 37 tokens
- Agent ruby-reviewer A 26 tokens
- Agent deployment-validator A 36 tokens
- Agent rails-architect A 28 tokens
- Agent ruby-gem-researcher A 31 tokens
- Agent ruby-runtime-advisor A 29 tokens
- Agent sidekiq-specialist A 38 tokens
- Agent testing-reviewer A 33 tokens
- Agent rails-patterns-analyst A 40 tokens
- Agent active-record-schema-designer A 34 tokens
- Agent call-tracer A 29 tokens
- Hook PostToolUse A not measured
- Hook PostToolUseFailure A not measured
- Hook FileChanged A not measured
- Hook UserPromptSubmit A not measured
- Hook UserPromptExpansion A not measured
- Hook CwdChanged A not measured
- Hook PermissionDenied A not measured
- Hook PermissionRequest A not measured
- Hook PreToolUse A not measured
- Hook SessionStart A not measured
- Hook SubagentStart A not measured
- Hook PostCompact A not measured
- Hook PostToolBatch A not measured
- Hook DirectoryAdded A not measured
- Hook PreCompact A not measured
- Hook Stop A not measured
- Hook StopFailure A not measured
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.
- 15d ago Changed a0299d5604ec
- 1mo ago Changed ca9a06866bcf
- 1mo ago First seen · 13 lines scan A b21faa136853
ruby-grape-rails is a plugin published in the GitHub repository slbug/claude-ruby-grape-rails (7 stars, last pushed 16d ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 plugins, from other repositories
jvm-languages
JVM language development including Java, Scala, and C# with enterprise patterns and frameworks.
functional-programming
Functional programming with Elixir, OTP patterns, Phoenix framework, and distributed systems.
rails-consultant
A collection of skills for Rails development and consulting, with an emphasis on learning, communication, and client success.
activerecord
ActiveRecord patterns for Rails models and queries.
rspec
RSpec and FactoryBot testing patterns for Rails.
ruby-rails
Ruby on Rails development toolkit with skills for Rails, Ruby, RSpec, RuboCop, SimpleCov, Brakeman, TestProf performance diagnosis, and code review with Sandi Metz principles.