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 skills/maquina-app/rails-claude-code/hotwire-patternsnpx skills add maquina-app/rails-claude-code --skill hotwire-patternsgit clone --depth 1 https://github.com/maquina-app/rails-claude-codeWrote 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/hotwire-patterns)<a href="https://agentmods.dev/skills/maquina-app/rails-claude-code/hotwire-patterns"><img src="https://agentmods.dev/badge/skills/maquina-app/rails-claude-code/hotwire-patterns.svg" alt="Measured on agentmods" 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 | $0.00152 | $0.02924 |
| Opus 5 | $0.00076 | $0.01462 |
| Sonnet 5 | $0.00030 | $0.00585 |
| Haiku 4.5 | $0.00015 | $0.00292 |
Grade A, and why
hotwire-patterns 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 6d 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 — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Hotwire Patterns
Internals-informed patterns for building and debugging Hotwire applications. Core philosophy: enhance the browser, don't reinvent it. Start by imagining a JS-free, plain-HTML version of every feature, then compose the separate pages into an integrated UI with Turbo. HTML is the source of truth for state, everywhere.
The escalation ladder (choose the cheapest tool that works)
Hotwire is a cost/benefit dial, not a single approach. Escalate only when the previous rung stops being a good tradeoff:
- Turbo Drive + Morphing refreshes — re-render everything server-side; fastest to build.
- Turbo Frames — decompose the page; localize updates without touching the rest.
- Turbo Stream actions — surgical DOM updates; more precise, more maintenance cost.
- Stimulus — small client-side behavior where a server round-trip makes no sense.
- Island of reactive framework (React/Vue) or API calls — only for genuinely high-interactivity widgets (maps, editors).
Different parts of one app can sit on different rungs; it all composes.
Turbo Drive essentials
- Drive intercepts link clicks and form submissions, fetches via
fetch, replaces<body>wholesale, and diff-merges<head>children (identical nodes untouched → assets not re-parsed; that's the speed win). Order of head children isn't preserved and doesn't matter. - Assets must live in
<head>. Modernasyncscripts + HTTP/2 remove old reasons for body-bottom scripts. - UJS replacements:
data: {turbo_method: :delete}for non-GET links;data: {turbo_confirm: "..."}for confirm dialogs (works on forms and non-GET links; addturbo_method: :getto use on plain links). Customize globally viaTurbo.config.forms.confirm = (message, formEl, submitter) => Promise<boolean>. - Submit buttons auto-disable during submission.
turbo:submit-start/turbo:submit-endevents carryevent.detail.formSubmission.submitter— use for loaders. - Failed form submissions must return 4xx (
render :new, status: :unprocessable_entity). Turbo requires a redirect on success; it renders 4xx bodies happily. Turbo.visit(location)is the programmatic navigation entry point;Turbo.visit(location, { frame })navigates a frame.- Non-GET links work by Turbo building a hidden form on the fly and submitting it — everything true of forms is true of these links.
- Visit types:
advance(link click),replace(redirect after form submit),restore(history). This matters for morphing (below). - Link prefetch fires after 100ms hover on plain GET links (no turbo-stream expectation, no confirm dialog). GET idempotency becomes mandatory; the
X-Sec-Purpose: prefetchheader identifies prefetches server-side if you must special-case.
What ships with it
5 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.
- 6d ago First seen · 105 lines · 152 tokens per session scan A 83a1e7579cbd
hotwire-patterns is a skill published in the GitHub repository maquina-app/rails-claude-code (47 stars, last pushed 20d ago), licensed MIT. It adds 152 tokens to every session and 2,924 once invoked, about $0.0008 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 skills, from other repositories
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
systematic-debugging
Use when debugging a failing test, build error, or runtime issue that isn't immediately obvious. Guides a 4-phase root cause analysis instead of random fix attempts.
diagnose
Trace from a reproduced symptom to the source code that causes it. Pin the specific file and approximate line, rate confidence in the cause and clarity of the fix independently, and always propose a concrete fix.
azsdk-common-pipeline-analysis
Analyze Azure SDK CI/CD pipeline failures into a structured diagnosis, and define the required output format. Load this skill before calling azsdkanalyzepipeline, which returns raw failure data that this skill interprets and formats. USE FOR: "pipeline failed", "build failure", "CI check failing", "tests failing in…
repro-admin
Reproduce an EmDash admin UI bug. Attach a container, start the demo dev server, drive the admin with agent-browser using the dev-bypass session, and capture the reproduction as screenshots plus a replayable transcript.
log-error-digest
Analyze log files to troubleshoot errors, identify peak error periods, and produce error clustering, frequency statistics, and time distribution reports. Supports JSON, syslog, and Nginx formats with automatic detection. Use when a user uploads a .log file and asks to analyze errors, find patterns, debug issues, or…