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 slbug/claude-ruby-grape-rails --skill runtime-integrationgit clone --depth 1 https://github.com/slbug/claude-ruby-grape-railsWrote 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/slbug/claude-ruby-grape-rails/runtime-integration)<a href="https://agentmods.dev/skills/slbug/claude-ruby-grape-rails/runtime-integration"><img src="https://agentmods.dev/badge/skills/slbug/claude-ruby-grape-rails/runtime-integration/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/slbug/claude-ruby-grape-rails/runtime-integration"><img src="https://agentmods.dev/badge/skills/slbug/claude-ruby-grape-rails/runtime-integration.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 | $0.00032 | $0.01705 |
| Opus 5.5 | $0.00013 | $0.00682 |
| Sonnet 5.5 | $0.00006 | $0.00341 |
| Haiku 4.5 | $0.00003 | $0.00170 |
Grade A, and why
rb:runtime 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 2mo 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 — 270 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Runtime Integration
Integrate with Tidewave Rails to enhance context with live system data from your running Rails application.
Prerequisites
Tidewave Rails must be installed in your project:
bundle add tidewave --group development
And ensure Tidewave is installed and connected to your Rails app.
Note: Runtime features require both:
- Tidewave gem in your project
- Tidewave MCP tools available in your Claude Code session
What Runtime Integration Provides
- Execute Ruby code in your running Rails app context
- Query database directly via SQL
- Fetch documentation for your exact gem versions
- Read application logs in real-time
- Introspect models and source locations
- Auto-capture errors during investigations
Detection
The detect-runtime.sh hook runs automatically at session start and detects:
# Detected from Gemfile:
TIDEWAVE_GEM_PRESENT=true
TIDEWAVE_PROJECT_CAPABLE=true
# Example subset persisted in .claude/.runtime_env for hook coordination:
HOOK_MODE=default
BETTERLEAKS_AVAILABLE=true
RTK_AVAILABLE=true
These values are persisted in ${REPO_ROOT}/.claude/.runtime_env as a
sourceable cache of startup detection results. Contributor tooling and hooks
may read or source that file when they want the cached values, but they are not
automatically exported into every hook process environment and current hooks do
not rely on it exclusively.
If Tidewave is not detected, runtime commands will provide setup guidance.
Commands
/rb:runtime inspect
Display runtime capability status:
/rb:runtime inspect
Shows:
- Tidewave gem detected in project
- MCP tool availability status
- Rails/Ruby version info
/rb:runtime execute <ruby-code>
Execute Ruby code in Rails console context:
/rb:runtime execute "User.recent.count"
/rb:runtime execute "Rails.application.config.active_job.queue_adapter"
What ships with it
3 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.
- 2mo ago First seen · 270 lines · 32 tokens per session scan A ac49f603dece
rb:runtime is a skill published in the GitHub repository slbug/claude-ruby-grape-rails (7 stars, last pushed 5d ago), licensed MIT. It adds 32 tokens to every session and 1,705 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 2026-09-03.
rb:runtime compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| rb:runtimeslbug/claude-ruby-grape-rails | Skill | 7 | 5d ago | MIT | A | 32 | Claude Code |
| api-errorscyanheads/obsidian-mcp-server | Skill | 702 | 7d ago | Apache-2.0 | A | 54 | Claude Code |
| a-unslop-codeimisic/claude-marketplace | Skill | 1 | 20d ago | MIT | A | 187 | Claude Code, Codex |
| drupal-debuggingedutrul/drupal-ai | Skill | 74 | 5mo ago | MIT | A | 31 | Claude Code |
| fastify-troubleshootingRadOrigin-LLC/RAD-Claude-Skills | Skill | 5 | 2mo ago | Apache-2.0 | A | 103 | Claude Code |
| node-debuggingCodeInfinity1/Stram | Skill | 10 | 2mo ago | MIT | A | 27 | Claude Code, Codex |
| mcp-ai-sdk-v2-server-opsnvdigitalsolutions/mcp-ai-wpoos | Skill | 7 | today | none | A | 206 | Claude Code, Codex |