sorbet-adoption

sorbet-adoption is a skill for Claude Code from sorah/config. It costs 170 tokens per session (4,492 once invoked), scanned A, original, MIT.

A step-by-step playbook for adding Sorbet type checking to an existing Ruby or Rails project. Sorbet checks Ruby code for type errors, and the rollout is done in reviewable changes.

In plain words
What is it for?
Use it to survey a Ruby codebase, prepare its configuration, add type annotations in stages, and review the rollout.
Why use it?
It helps teams introduce types gradually without treating a passing check with missing method signatures as a finished result.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions CLAUDE.md; names the AskUserQuestion tool.

Part of the sorah-guides plugin — 15 skills, 3 commands, 1 agent shipped together

Good fit Use it to survey a Ruby codebase, prepare its configuration, add type annotations in stages, and review the rollout.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/sorah/config/sorbet-adoption
View source ↗ sorah/config
Install

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.

Any agent
npx skills add sorah/config --skill sorbet-adoption
Clone the repo
git clone --depth 1 https://github.com/sorah/config

Made for: Claude Code.

Or install sorah-guides, the plugin that ships this one along with the rest of its 15 skills, 3 commands, 1 agent.

Wrote 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.

agentmods badge for sorbet-adoption

README.md
[![agentmods](https://agentmods.dev/badge/skills/sorah/config/sorbet-adoption/github.svg)](https://agentmods.dev/skills/sorah/config/sorbet-adoption)
Your own site
<a href="https://agentmods.dev/skills/sorah/config/sorbet-adoption"><img src="https://agentmods.dev/badge/skills/sorah/config/sorbet-adoption/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.

agentmods 80×15 button for sorbet-adoption

Your own site · 80×15
<a href="https://agentmods.dev/skills/sorah/config/sorbet-adoption"><img src="https://agentmods.dev/badge/skills/sorah/config/sorbet-adoption.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 170 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,492 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00170 $0.04492
Opus 5.5 $0.00068 $0.01797
Sonnet 5.5 $0.00034 $0.00898
Haiku 4.5 $0.00017 $0.00449

Measured yesterday against content hash f1ee5e276e8d, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

sorbet-adoption 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 yesterday.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/stamp_sigils.rb), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

claude/marketplace/plugins/sorah-guides/skills/sorbet-adoption/SKILL.md · 231 lines

How it starts

The opening of the file, as written. The whole thing — 231 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Sorbet Adoption

This is a playbook for bringing an untyped Ruby or Rails codebase to Sorbet # typed: strict through a series of reviewable PRs. It is distilled from a rollout that took a Rails app and its client gem from no annotations to about 300 strict files in 22 stacked PRs.

Load sorah-guides:sorbet before writing any annotation. That skill defines how types are written. This one decides order, scope and mechanics. For branch and stack mechanics use /gh-stack; for commits and PR bodies use /sorah-guides:commit and /sorah-guides:pull-request.

The rollout runs in this order:

  1. Survey and decide
  2. Infra PR
  3. Prep PRs
  4. Sigils PR
  5. Slices, bottom-up
  6. Integrate
  7. Review
  8. Keep current

Lessons that shaped this playbook

  • typed: true is not the goal.
    • The first pass of the original rollout raised 17 slices to true and was green. Yet the code carried 6 method signatures across about 1750 methods, because true demands none and the exit condition was "bump and srb tc green".
    • Every slice had to be redone to strict, which surfaced over 3000 errors (about two thirds of them missing signatures).
    • Plan for strict from the start.
  • Casts are debt.
    • The strict pass then left more than 250 #: as !nil casts, and a later pass replaced them with restructures, raising readers and Must.
    • Write nil and union handling the sorbet skill's way from the first commit.
  • Shared shims belong in the infra PR. Slices that each added the same logger method or the same timestamp cast produced add/add conflicts and duplicated work. One shim at the bottom of the stack removed every copy.
  • Cross-slice errors appear only after stacking. Slices typed in parallel are each green alone. Once chained, a single wrong return type in a low layer caused 87 errors above it. Budget an integration pass.
  • Agent output needs a real review. Many agents writing casts in security-sensitive code surfaced real bugs: a positional initialize that silently received a Hash, and controllers reading current_user under a gate that a machine credential passes. They also produced workarounds that turned out to be unnecessary.

Read the full file on GitHub · 231 lines

Files

What ships with it

3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

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.

  1. yesterday First seen · 231 lines · 0 tokens per session scan A f1ee5e276e8d

Subscribe to this mod's changes

sorbet-adoption is a skill published in the GitHub repository sorah/config (31 stars, last pushed yesterday), licensed MIT. It adds 170 tokens to every session and 4,492 once invoked, about $0.0007 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 2026-10-17.

Related

Other skills, from other repositories

rubyllm

Build and maintain Ruby or Rails applications with the RubyLLM AI framework. Use for chats, agents, tools, MCP servers, structured output, judgments, evaluations, media generation, transcription, OCR, moderation, embeddings, reranking, tracing, Rails integration, and RubyLLM upgrades; not for contributing to the…

crmne/ruby_llm · 70 tokens

new

Create a new project to start development quickly.

clacky-ai/openclacky · 10 tokens

rspec-conventions

Rootstrap RSpec conventions. Use when writing, reviewing, or editing RSpec test files (spec//spec.rb, spec/railshelper.rb, spec/spechelper.rb, spec/support//.rb) or factories. Covers describe/context structure, let/subject, matchers, factories, mocking/stubbing, shared examples, and spec types (model, request…

rootstrap/rails_api_base · 82 tokens

dhh-rails-style

This skill should be used when writing Ruby and Rails code in DHH's distinctive 37signals style. It applies when writing Ruby code, Rails applications, creating models, controllers, or any Ruby file. Triggers on Ruby/Rails code generation, refactoring requests, code review, or when the user mentions DHH, 37signals…

davekilleen/Dex · 115 tokens

ruby-patterns

Ruby/Rails: blocks, metaprogramming, ActiveRecord, Sidekiq, RSpec, Sorbet, Hanami. Triggers: Ruby, Rails, ActiveRecord, Sidekiq, RSpec, Gemfile, bundler, Hanami, Sorbet.

softspark/ai-toolkit · 60 tokens

ruby-idioms

Modern Ruby (3.x) idioms: pattern matching, keyword arguments, immutable data structures, error hierarchies, and RSpec testing. Use when writing, modifying, or reviewing Ruby scripts, gems, or business logic. Pair with rails-idioms for Rails applications.

irahardianto/awesome-agv · 61 tokens