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/st0012/ruby-skills/claude-mdgit clone --depth 1 https://github.com/st0012/ruby-skillsWrote 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/st0012/ruby-skills/claude-md)<a href="https://agentmods.dev/instructions/st0012/ruby-skills/claude-md"><img src="https://agentmods.dev/badge/instructions/st0012/ruby-skills/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 | $0.01197 | $0.01197 |
| Opus 5 | $0.00598 | $0.00598 |
| Sonnet 5 | $0.00239 | $0.00239 |
| Haiku 4.5 | $0.00120 | $0.00120 |
Grade A, and why
ruby-skills 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 — 156 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ruby Skills - Development Guide
For Claude: When to Run Tests
Run these tests automatically when:
- You modify any
.shscript in the plugin - You change detection logic in
detect.shordetect-all-managers.sh - Before committing changes
- When debugging issues reported by the user
Minimum verification before any commit:
- Run
detect.shand verify it outputs valid key=value pairs - Test that
ACTIVATION_COMMANDactually switches Ruby versions
Project Structure
This repository is a plugin marketplace containing one plugin:
ruby-skills/ # Marketplace root
├── .claude-plugin/
│ └── marketplace.json # Marketplace definition
├── plugins/
│ └── ruby-skills/ # Plugin
│ ├── .claude-plugin/plugin.json
│ ├── hooks/
│ │ ├── hooks.json
│ │ └── session-start.sh
│ └── skills/
│ ├── ruby-version-manager/
│ │ ├── SKILL.md
│ │ ├── detect.sh
│ │ ├── detect-all-managers.sh
│ │ └── set-preference.sh
│ ├── ruby-resource-map/
│ │ └── SKILL.md # Authoritative resource map
│ └── ruby-test-frameworks/
│ └── SKILL.md # minitest vs test-unit divergences
├── CLAUDE.md # This file
└── README.md # User documentation
Test Suite
Test 1: Basic Detection
When to run: After any change to detect.sh or detect-all-managers.sh
cd /path/to/ruby/project
/path/to/ruby-skills/plugins/ruby-skills/skills/ruby-version-manager/detect.sh
Verify:
- Output contains
VERSION_MANAGER=<manager>(not empty or "none" if manager is installed) - Output contains
ACTIVATION_COMMAND=<command>(not empty) - Output contains
VERSION_AVAILABLE=true(if the Ruby version is installed)
Test 2: Activation Command Works
When to run: After any change to activation logic
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 · 156 lines · 1,197 tokens per session scan A 4d9ac8a982f0
ruby-skills CLAUDE.md is an instructions file published in the GitHub repository st0012/ruby-skills (125 stars, last pushed 2mo ago), licensed MIT. It adds 1,197 tokens to every session, about $0.0060 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
rails_api_base CLAUDE.md
Instructions for rootstrap/rails_api_base, covering claude.md, what this repo is, common commands, testing notes and architecture.
ruby2d AGENTS.md
Instructions for ruby2d/ruby2d, covering ruby 2d guide for ai coding agents, testing, architecture, multi-ruby support and documentation.
nosia AGENTS.md
Instructions for dilolabs/nosia, covering 37signals rails configuration, tech stack, architecture, core philosophy and key commands.
planner AGENTS.md
AGENTS.md instructions for codebar/planner, covering agents.md, project overview, development workflow, branching strategy and development setup.
roundhouse AGENTS.md
AGENTS.md instructions for rubys/roundhouse, covering working on roundhouse (agents & contributors), start here, invariants — do not break these, workflow and the actual goal.
rails-hyperdrive CLAUDE.md
Instructions for rails-hyperdrive/rails-hyperdrive, covering claude.md, what this repo is, commands, ci matrix is ruby {3.2, 3.3, 3.4} × rails {7.2, 8.1} and reproduce a specific slot locally.