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 skills add igmarin/rails-agent-skills --skill upgrade-enginegit clone --depth 1 https://github.com/igmarin/rails-agent-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/skills/igmarin/rails-agent-skills/upgrade-engine)<a href="https://agentmods.dev/skills/igmarin/rails-agent-skills/upgrade-engine"><img src="https://agentmods.dev/badge/skills/igmarin/rails-agent-skills/upgrade-engine/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/skills/igmarin/rails-agent-skills/upgrade-engine"><img src="https://agentmods.dev/badge/skills/igmarin/rails-agent-skills/upgrade-engine.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 5.1 | $0.00033 | $0.00759 |
| Opus 5 | $0.00016 | $0.00380 |
| Sonnet 5 | $0.00007 | $0.00152 |
| Haiku 4.5 | $0.00003 | $0.00076 |
Grade A, and why
upgrade-engine 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 10d 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 — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Upgrade Engine
Core principle: Every claimed Rails/Ruby version must be in the CI matrix. Prefer explicit support targets over accidental compatibility.
HARD-GATE
Before claiming support for a Rails/Ruby version:
1. bundle exec rake zeitwerk:check # verify autoloading on each version
2. bundle exec rspec # full suite per matrix version
3. CI matrix must pass — not just main Rails version
DO NOT ship compatibility changes without verifying both autoloading and full suite.
Core Process
- Define supported Ruby and Rails versions — state them in gemspec and README.
- Run
bundle exec rake zeitwerk:check— file paths must match constant names exactly (e.g.my_engine/widget_policy.rb→MyEngine::WidgetPolicy). - Check initializer behavior across boot and reload — use
config.to_preparefor reload-sensitive hooks; hooks placed at load time are reload-unsafe in development. - Verify gemspec dependency bounds match tested versions:
spec.add_dependency "rails", ">= 7.0", "< 8.0"— bounds must reflect what CI actually tests. Unbounded or overclaiming constraints (>= 5.2without testing 5.2/6.x) are silent incompatibilities. - Replace
Rails.versionbranching with feature detection — version checks are brittle across patch releases:
# ❌ Bad — brittle, wrong for patch versions
if Rails.version >= "7.0"
config.active_support.cache_format_version = 7.0
end
# ✅ Good — detect the capability directly
if ActiveSupport::Cache.respond_to?(:format_version=)
config.active_support.cache_format_version = 7.0
end
- Check optional integrations (jobs, mailers, assets, routes, install generators, dummy-app mounts) per version. State the check even if an integration is absent.
- CI matrix must run against each claimed Rails/Ruby combination:
strategy:
matrix:
include:
- { ruby: "3.2", rails: "7.1" }
- { ruby: "3.3", rails: "7.2" }
Extended Resources
What ships with it
4 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.
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.
- 10d ago First seen · 78 lines · 33 tokens per session scan A c6d0585699d3
upgrade-engine is a skill published in the GitHub repository igmarin/rails-agent-skills (24 stars, last pushed 19d ago), licensed MIT. It adds 33 tokens to every session and 759 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 2026-08-30.
Other skills, from other repositories
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…
ruby
Ruby development guidelines covering idiomatic code style, Ruby 3.x features, testing with RSpec, and best practices for building maintainable Ruby applications.
rspec
RSpec testing best practices for Ruby and Rails applications, covering test organization, data management, and isolation patterns.
testunit-skill
Generates Test::Unit tests in Ruby. Classic xUnit-style testing with assert methods and test case classes. Use when user mentions "Test::Unit", "assertequal Ruby", "Ruby test-unit". Triggers on: "Test::Unit", "Ruby test-unit", "assertequal Ruby" (not RSpec).
rspec
This skill should be used when the user asks to "write specs", "create spec", "add RSpec tests", "fix failing spec", or mentions RSpec, describe blocks, it blocks, expect syntax, test doubles, or matchers. Should also be used when editing spec.rb files, working in spec/ directory, planning implementation phases that…
rails-testing
Ruby on Rails testing best practices for writing effective, maintainable test suites with RSpec. This skill should be used when writing, reviewing, or refactoring Rails tests to ensure proper test design, data management, and coverage patterns. Triggers on tasks involving RSpec specs, model tests, request specs…