Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/maquina-app/rails-claude-codenpx agentmods add skills/maquina-app/rails-claude-code/rails-hotwire-driverWrote 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/maquina-app/rails-claude-code/rails-hotwire-driver)<a href="https://agentmods.dev/skills/maquina-app/rails-claude-code/rails-hotwire-driver"><img src="https://agentmods.dev/badge/skills/maquina-app/rails-claude-code/rails-hotwire-driver/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/maquina-app/rails-claude-code/rails-hotwire-driver"><img src="https://agentmods.dev/badge/skills/maquina-app/rails-claude-code/rails-hotwire-driver.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium MCP Rug Pull · line 81 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 109 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
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 | $0.00213 | $0.04777 |
| Opus 5 | $0.00106 | $0.02388 |
| Sonnet 5 | $0.00043 | $0.00955 |
| Haiku 4.5 | $0.00021 | $0.00478 |
Grade A, and why
rails-hotwire-driver scanned grade A with 1 finding 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 10d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
description: Drive a running local Rails dev server from the terminal instead of a browser — log in (incl. OTP/magic-link codes read straight from the dev log), submit ERB forms with correct CSRF tokens, trigger and insp How it starts
The opening of the file, as written. The whole thing — 355 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Rails Hotwire Driver
Exercise a running local Rails dev server from the shell: authenticate, submit
forms, trigger and read Turbo Streams, and read the development log — including
OTP/verification codes that Rails prints to the log in development. This is the
runtime complement to rails-mcp-server, which only reads code statically.
When this fits (and when it doesn't)
Good fit: ERB + Hotwire apps with minimal JavaScript. The server renders HTML and
text/vnd.turbo-stream.html; you are verifying that server-rendered contract.
The core scripts (req.sh, submit_form.rb, readlog.sh, flow.sh) will not
execute JavaScript, by design — no Stimulus controllers run, no DOM morphing, no
requestSubmit, no ActionCable-broadcast rendering. Don't try to fake JS here.
For the JS-dependent residual, this skill also ships a thin layer of optional scripts around the agent-browser CLI — see Pairing with a browser below. They cover the common cases (screenshots, waiting for a broadcast to actually update the DOM, Stimulus controller state, structural diffs) without reaching for a separate MCP or writing Playwright test code. Anything past that — full end-to-end flows, cross-browser testing — is still better served by a dedicated browser-testing tool.
Prerequisites — confirm before driving
- The Rails app is running locally in development (e.g.
bin/rails s), and you know its port. SetBASE_URL(defaulthttp://localhost:3000). The scripts refuse any non-local host (allowed:localhost, loopback IPs, and any*.localhostname). Nokogiriis available — it ships with essentially every Rails bundle. Run the Ruby script via the project's bundle:bundle exec ruby .../submit_form.rb.- Recommended for best log correlation: request-id tagging on. In
config/environments/development.rb:
Without it,config.log_tags = [ :request_id ]readlog.sh requestfalls back to a context window instead of an exact filter — still useful, just noisier.
What ships with it
13 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.
- references/config.md 1.9 KB
- scripts/browser-errors.sh 2.4 KB runs code
- scripts/dom-diff.sh 2.8 KB runs code
- scripts/flow.sh 5.2 KB runs code
- scripts/jar_to_storage.rb 3.2 KB runs code
- scripts/readlog.sh 1.9 KB runs code
- scripts/req.sh 3.3 KB runs code
- scripts/screenshot-diff.sh 5.5 KB runs code
- scripts/screenshot.sh 8.9 KB runs code
- scripts/stimulus.sh 4.2 KB runs code
- scripts/storage_to_jar.rb 1.8 KB runs code
- scripts/submit_form.rb 5.8 KB runs code
- scripts/turbo-wait.sh 3.9 KB runs code
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.
- 10d ago First seen · 355 lines · 213 tokens per session scan A f4a6b9ff3f27
rails-hotwire-driver is a skill published in the GitHub repository maquina-app/rails-claude-code (47 stars, last pushed 25d ago), licensed MIT. It adds 213 tokens to every session and 4,777 once invoked, about $0.0011 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
browse
Drive a real browser through Aside: open a page, read it, click through a flow, take screenshots, check console errors. (gstack).
playwright-cli
A command-line tool for controlling Chromium, Firefox, and WebKit browsers, including navigation, page interaction, screenshots, PDFs, and recorded actions.
webapp-testing
Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.
create-verification-skill
Create a repo-local verification skill and exhaustive feature map for driving a real app through its UI, CLI, or API. Use for "create a verification skill", "make a verify skill for this repo", or "document how agents can verify this app".
browser-qa
A browser-based quality check for deployed web pages and user flows. It uses browser automation to test rendering, navigation, forms, interactions, responsive behaviour, and accessibility-related issues.
test-electron-app
Drive the real running PostHog Electron app (live tRPC, workspace-server, real data) over CDP with agent-browser. Connect to the running app on port 9222, test desktop changes against a local Django stack, snapshot the accessibility tree, inspect network requests, and screenshot only when explicitly asked. Use when…