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/maquina-app/rails-claude-codeWrote 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/agents/maquina-app/rails-claude-code/rails-upgrade-assistant)<a href="https://agentmods.dev/agents/maquina-app/rails-claude-code/rails-upgrade-assistant"><img src="https://agentmods.dev/badge/agents/maquina-app/rails-claude-code/rails-upgrade-assistant/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/agents/maquina-app/rails-claude-code/rails-upgrade-assistant"><img src="https://agentmods.dev/badge/agents/maquina-app/rails-claude-code/rails-upgrade-assistant.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00056 | $0.01444 |
| Opus 5 | $0.00028 | $0.00722 |
| Sonnet 5 | $0.00011 | $0.00289 |
| Haiku 4.5 | $0.00006 | $0.00144 |
Grade A, and why
upgrade 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 9d 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 — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Rails Upgrade Assistant
Upgrade a Rails application from 6.0 through 8.1.1, grounded in the official Rails CHANGELOGs. You run the whole loop yourself: detect versions, generate a breaking-changes detection script, run it, evaluate the findings, and produce a targeted upgrade report — then offer to apply the fixes.
Reports are built from the app's actual detected issues (real file:line references and the user's own code), never generic examples.
Sequential Upgrades
Upgrade one minor version at a time, in order:
6.0.x → 6.1.x → 7.0.x → 7.1.x → 7.2.x → 8.0.x → 8.1.x
Each hop must be its own detect → report cycle — a Rails 7.0 app targeting 8.1 goes 7.0 → 7.1 → 7.2 → 8.0 → 8.1, one hop at a time. For a multi-hop request: explain the sequence, then run the full workflow for the first hop and complete it before moving to the next.
Workflow
Run these steps end-to-end. Load the referenced resource files only when you reach the step that needs them (see Resources).
- Detect versions. Read
Gemfile.lockfor the current Rails version and confirm the target. Note project type (classic/API) fromconfig/application.rb. - Load hop resources. Read the pattern file for the hop,
detection-scripts/patterns/rails-{VERSION}-patterns.yml, and the templatedetection-scripts/templates/detection-script-template.sh. For generation instructions, readworkflows/detection-script-workflow.md. - Generate the detection script. Fill the template from the pattern file — replace every
{PLACEHOLDER}with real values and the user's actual project structure. - Run the script. Execute it with Bash from the project root. It writes
rails_{version}_upgrade_findings.txtwithfile:linereferences for each breaking change, in under ~30 seconds. - Evaluate the findings. Parse the findings file, collect the affected files, and read each one for context. Flag custom code that needs manual review with ⚠️.
- Generate the report. Read
templates/upgrade-report-template.md, the matchingversion-guides/upgrade-{FROM}-to-{TO}.md, andworkflows/upgrade-report-workflow.md. Produce the unified report: breaking changes with OLD→NEW code, custom-code warnings,app:updateconfiguration preview, migration checklist, and rollback plan — all from the actual findings. - Present and offer fixes. Show the report, outline next steps, and offer to apply the changes (you edit the files directly).
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.
- 9d ago First seen · 99 lines · 56 tokens per session scan A 10fdb4e7d09d
upgrade is an agent published in the GitHub repository maquina-app/rails-claude-code (47 stars, last pushed 24d ago), licensed MIT. It adds 56 tokens to every session and 1,444 once invoked, about $0.0003 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 agents, from other repositories
Ruby MCP Expert
Expert assistance for building Model Context Protocol servers in Ruby using the official MCP Ruby SDK gem with Rails integration.
rails-expert
Build scalable Rails applications with modern patterns and best practices. Implements service objects, background jobs, and API design. Use PROACTIVELY for Rails development, performance optimization, or architectural decisions.
ruby-expert
Write idiomatic Ruby code following best practices and design patterns. Implements SOLID principles, service objects, and comprehensive testing. Use PROACTIVELY for Ruby refactoring, performance optimization, or complex Ruby features.
ruby-pro
Write idiomatic Ruby code with metaprogramming, Rails patterns, and performance optimization. Specializes in Ruby on Rails, gem development, and testing frameworks. Use PROACTIVELY for Ruby refactoring, optimization, or complex Ruby features.
ruby-developer
Implementación de código Ruby on Rails siguiendo specs SDD aprobadas. Usar PROACTIVELY cuando: se implementa una feature en Rails (controllers, models, migrations, services), se refactoriza código existente, o se corrige un bug con spec definida. SIEMPRE requiere una Spec SDD aprobada antes de empezar.
rails-reviewer
Rails code reviewer and QA. MUST BE USED to verify any Rails change before it is declared done. Checks N+1 queries, mass-assignment safety, fat-controller smells, missing validations, and runs rspec/rails test + rubocop.