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 commands/stevegeek/claude-ruby-plugins/write-inline-rbsgit 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 | $0.00017 | $0.00647 |
| Opus 5 | $0.00009 | $0.00324 |
| Sonnet 5 | $0.00003 | $0.00129 |
| Haiku 4.5 | $0.00002 | $0.00065 |
Grade A, and why
write-inline-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 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 — 125 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Write Inline RBS Annotations
You are adding inline RBS type annotations directly in the Ruby source file at: $ARGUMENTS
Process
1. Load the RBS Skill
First, load the RBS skill for comprehensive type knowledge:
Use the Skill tool to load: ruby-inline-rbs
Then read the inline RBS subskill for syntax details:
subskills/inline/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. Add Magic Comment
Ensure the file has the magic comment at the top:
# rbs_inline: enabled
6. Add Inline Annotations
Add type annotations using comment syntax:
Method signatures:
#: (String, Integer) -> String
def format(text, width)
Attributes:
attr_reader :name #: String
attr_accessor :count #: Integer?
Instance variables:
# @rbs @items: Array[String]
Blocks:
#: () { (String) -> void } -> void
def each(&block)
Generics:
# @rbs generic T
class Container
7. Generate and Validate
Generate RBS from inline annotations:
bundle exec rbs-inline --output lib
Then validate:
bundle exec steep check lib/target.rb
Fix any errors before completing.
Output
- Modified Ruby file(s) with inline type annotations
- Generated
sig/generated/*.rbsfiles (if --output used) - Report what was typed and any decisions made
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 · 125 lines · 17 tokens per session scan A 0c400e8255c3
write-inline-rbs is a command published in the GitHub repository stevegeek/claude-ruby-plugins (19 stars, last pushed 4mo ago), licensed Unlicense. It adds 17 tokens to every session and 647 once invoked, about $0.0001 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 commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.