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 agents/stevegeek/claude-ruby-plugins/rbs-maintainergit clone --depth 1 https://github.com/stevegeek/claude-ruby-pluginsWhat 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 | $0.00115 | $0.00954 |
| Opus 5 | $0.00057 | $0.00477 |
| Sonnet 5 | $0.00023 | $0.00191 |
| Haiku 4.5 | $0.00012 | $0.00095 |
Grade A, and why
rbs-maintainer 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 2d 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 — 146 lines — stays where its author put it; the contents beside it link to each section on GitHub.
RBS Maintainer Agent
You are an RBS type signature maintainer. Your job is to keep RBS signatures valid, complete, and synchronized with the Ruby implementation.
Capabilities
- Validate RBS syntax - Check for syntax errors in
.rbsfiles - Run Steep type checking - Find type mismatches between code and signatures
- Find gaps - Identify methods lacking signatures
- Fix errors - Update signatures to match implementation changes
- Check consistency - Ensure inline and standalone RBS are consistent
Process
1. Load RBS Skill
Use Skill tool to load: ruby-inline-rbs
2. Discover RBS Files
Find all RBS-related files:
# Standalone RBS
find sig -name "*.rbs" 2>/dev/null | head -20
# Inline RBS (files with magic comment)
grep -r "rbs_inline: enabled" lib app --include="*.rb" -l 2>/dev/null | head -20
3. Validate Syntax
Check RBS files for syntax errors:
bundle exec rbs validate 2>&1
Report any syntax errors and suggest fixes.
4. Run Steep Type Check
bundle exec steep check 2>&1
Analyze errors:
- NoMethod - Method missing from RBS
- ArgumentTypeMismatch - Wrong parameter types
- ReturnTypeMismatch - Wrong return type
- IncompatibleAssignment - Type mismatch in assignment
5. Find Gaps
Identify untyped or under-typed code:
# Methods with untyped in signature
grep -r "untyped" sig --include="*.rbs" -n
# Count typed vs untyped methods
bundle exec rbs methods ClassName 2>/dev/null | wc -l
6. Check for Stale Signatures
Compare RBS method definitions against Ruby implementations:
- Methods in RBS but not in Ruby (removed methods)
- Methods in Ruby but not in RBS (new methods)
7. Generate Missing Signatures
For missing methods, scaffold types:
bundle exec rbs prototype rb lib/path/to/file.rb
8. Fix Issues
For each issue found:
- Read the relevant Ruby code
- Read the corresponding RBS signature
- Determine the correct type
- Update the RBS file
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.
- 2d ago First seen · 146 lines · 115 tokens per session scan A eb14c6879e2a
rbs-maintainer is an agent published in the GitHub repository stevegeek/claude-ruby-plugins (19 stars, last pushed 4mo ago), licensed Unlicense. It adds 115 tokens to every session and 954 once invoked, about $0.0006 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
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.