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/stevegeek/claude-ruby-pluginsWrote 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/commands/stevegeek/claude-ruby-plugins/write-rbs)<a href="https://agentmods.dev/commands/stevegeek/claude-ruby-plugins/write-rbs"><img src="https://agentmods.dev/badge/commands/stevegeek/claude-ruby-plugins/write-rbs/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/commands/stevegeek/claude-ruby-plugins/write-rbs"><img src="https://agentmods.dev/badge/commands/stevegeek/claude-ruby-plugins/write-rbs.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 | $0.00029 | $0.00593 |
| Opus 5.5 | $0.00012 | $0.00237 |
| Sonnet 5.5 | $0.00006 | $0.00119 |
| Haiku 4.5 | $0.00003 | $0.00059 |
Grade A, and why
write-rbs 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 1mo 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 — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Write Standalone RBS Signatures
You are writing RBS type signatures in standalone .rbs files for the Ruby code at: $ARGUMENTS
Process
1. Load the RBS Skill
First, load the RBS skill to get comprehensive type syntax knowledge:
Use the Skill tool to load: ruby-inline-rbs
Then read the standalone RBS subskill for file format details:
subskills/rbs-files/SKILL.md
2. Analyze Target
Read the Ruby file(s) specified by the user:
- Understand class/module structure
- Note method signatures, parameters, return patterns
- Identify instance variables
- Look for DSL usage (attr_*, delegate, etc.)
3. Find Tests
Search for related test files:
Glob for: test/**/*{target_name}*_test.rb, spec/**/*{target_name}*_spec.rb
Read tests to understand:
- Expected method behavior
- Edge cases (nil returns, exceptions)
- Type expectations from assertions
4. Use Type Tracer (If Tests Exist)
If tests exist, consider running the type tracer:
# First locate type_tracer.rb in plugin directory using find
ruby <TRACER_SCRIPT> -c 'TargetClass' -f json path/to/test.rb
Review tracer output to inform type decisions.
5. Generate Scaffold (Optional)
For complex files, generate an initial scaffold:
bundle exec rbs prototype rb lib/target.rb
6. Write RBS
Create the .rbs file in sig/ mirroring the lib/ structure:
lib/my_app/user.rb → sig/my_app/user.rbs
Follow these principles:
- Start with public API methods
- Use appropriate types (avoid
untypedwhere possible) - Consider generics for container classes
- Use interfaces for duck typing
- Add optional markers (
?) for nilable returns
7. Validate
Run validation to check your work:
bundle exec rbs validate
bundle exec steep check lib/target.rb
Fix any errors before completing.
Output
Create/update the following:
sig/**/*.rbs- Type signature files- Report what was typed and any decisions made
Tips
- Match RBS file structure to Ruby file structure
- Don't type private implementation details unless needed
- Use
untypedfor genuinely dynamic/complex code - Check gem_rbs_collection for third-party type definitions
- Reference
references/type-syntax.mdfor syntax questions
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.
- 1mo ago First seen · 101 lines · 29 tokens per session scan A 6b78484f823b
write-rbs is a command published in the GitHub repository stevegeek/claude-ruby-plugins (19 stars, last pushed 5mo ago), licensed Unlicense. It adds 29 tokens to every session and 593 once invoked, about $0.0001 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 2026-08-30.
Other commands, from other repositories
sdd-discover-standards
Extract tribal knowledge from an existing Rails codebase into new SDD standards.
initialize-ruby
Manual override: initialize ast-index for Ruby/Rails project.
review-ruby-code
Review Ruby/Rails code with Sandi Metz rules and SOLID principles.
index
Codegen-first polyglot web toolkit: one Rust core, 14 language bindings, spec-driven codegen (OpenAPI, AsyncAPI, GraphQL, gRPC, SQL to HTTP) and a 13-tool MCP server. Experimental, pre-1.0, MIT.
sinatra-review
Review Sinatra code for security issues, performance problems, route conflicts, and framework best practices.
rails-review
Ruby on Rails code review with severity-based filtering.