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 instructions/ruby-grape/grape-swagger-rails/claude-mdgit clone --depth 1 https://github.com/ruby-grape/grape-swagger-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/instructions/ruby-grape/grape-swagger-rails/claude-md)<a href="https://agentmods.dev/instructions/ruby-grape/grape-swagger-rails/claude-md"><img src="https://agentmods.dev/badge/instructions/ruby-grape/grape-swagger-rails/claude-md.svg" alt="Measured on agentmods" 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 | $0.01365 | $0.01365 |
| Opus 5 | $0.00682 | $0.00682 |
| Sonnet 5 | $0.00273 | $0.00273 |
| Haiku 4.5 | $0.00136 | $0.00136 |
Grade A, and why
grape-swagger-rails CLAUDE.md 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 4d 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 — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
What This Gem Does
grape-swagger-rails is a Rails Engine gem that mounts a Swagger UI interface for APIs documented with the grape-swagger gem. It provides a single mountable engine that renders Swagger UI v5 with configurable authentication, theming, and authorization hooks.
Commands
bundle exec rake # Run full suite: RuboCop + RSpec (default)
bundle exec rake spec # Run all RSpec tests only
bundle exec rake rubocop # Run RuboCop linting only
bundle exec rspec spec/features/swagger_spec.rb # Run a single spec file
yarn build:frontend # tsc → index.js, then esbuild → index.min.js (+ .map)
yarn build:frontend:js # Just tsc (readable bundle)
yarn build:frontend:min # Just esbuild (minified bundle, consumes index.js)
yarn typecheck # Type-check TypeScript without emitting
bundle exec rake swagger_ui:dist:update # Update bundled Swagger UI assets
SWAGGER_UI_VERSION=v5.32.5 bundle exec rake swagger_ui:dist:update # Pin to a version
Tests use Capybara + Selenium with Firefox. Firefox and geckodriver must be installed locally. On macOS, xvfb is not needed (unlike CI). Tests launch a real browser to validate UI behavior.
After editing TypeScript, run yarn build:frontend before running specs — the specs exercise app/assets/javascripts/grape_swagger_rails/index.js, which is the compiled output. Never edit the compiled JS directly. The build also emits index.min.js (+ sourcemap); the view picks the minified bundle in production (Rails.env.production?) via grape_swagger_rails_runtime_asset and the readable one everywhere else.
Architecture
The gem has minimal moving parts:
lib/grape-swagger-rails.rb— DefinesGrapeSwaggerRails.optionsas an OpenStruct. All configuration lives here (URL, auth type, headers, theme, before_action proc, etc.).lib/grape-swagger-rails/engine.rb— Rails Engine. Configures asset precompilation for both Sprockets and Propshaft pipelines.app/controllers/grape_swagger_rails/application_controller.rb— Singleindexaction. Runsoptions.before_action_procin controller context for authorization.app/views/grape_swagger_rails/application/index.html.haml— The entire UI. SerializesGrapeSwaggerRails.optionsas JSON intodata-swagger-options, then JavaScript parses it to initialize SwaggerUIBundle. Handles theme toggling and auth injection via Swagger UI'srequestInterceptor.frontend/grape_swagger_rails/index.ts— TypeScript source for the browser runtime.tsccompiles it toapp/assets/javascripts/grape_swagger_rails/index.js(readable, ES5);esbuildthen minifies that intoindex.min.js(+.map). Both files are checked in so they ship with the gem. The TypeScript interfaceSwaggerPageOptionsis the authoritative schema for options consumed by JS.config/routes.rb— Single root route →ApplicationController#index.lib/tasks/swagger_ui.rake— Rake task that clonesswagger-api/swagger-uiand copies dist files intoapp/assets/.
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.
- 4d ago First seen · 81 lines · 1,365 tokens per session scan A c455685f3f69
grape-swagger-rails CLAUDE.md is an instructions file published in the GitHub repository ruby-grape/grape-swagger-rails (261 stars, last pushed 15d ago), licensed MIT. It adds 1,365 tokens to every session, about $0.0068 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 2026-08-30.
Other instructions, from other repositories
mcp-pandoc AGENTS.md
Instructions for vivekVells/mcp-pandoc, covering agents.md, what this is, where things are, deeper context and commands.
agentic-resume-builder CLAUDE.md
Claude Code instructions for WtotdeD/agentic-resume-builder, covering agentic-resume-builder development guidelines, what this repo is, active technologies, package manager and validation.
fcp-sheets CLAUDE.md
Instructions for os-tack/fcp-sheets, covering fcp-sheets, project overview, architecture, key patterns and commands.
paperless-ngx-mcp-server CLAUDE.md
Claude Code instructions for cbsmiley/paperless-ngx-mcp-server, covering claude.md, project overview, common commands, architecture and entry points.
hermes-procurement-pricing-mcp AGENTS.md
AGENTS.md instructions for felix-windsor/hermes-procurement-pricing-mcp, a project described as: Secure procurement quotation comparison MCP service with document parsing, mock market pricing, anomaly detection, and Telegram/Hermes integration.
mcp-svg-marp CLAUDE.md
Claude Code instructions for koppe-pan/mcp-svg-marp, covering mcp-svg-marp tool instructions, mcp tools available, 📊 convertsvgtomarp, 🔍 analyzesvg and automatic slide creation workflow.