show

A reusable procedure for checking a website visually across standard screen sizes.

In plain words
What is it for?
Use it when a change needs visual proof, with screenshots for mobile, tablet, and desktop views.
Why use it?
It helps find layout problems such as poor spacing, overflow, weak contrast, or broken elements that code review may miss.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/artttj/rapid-stack/show
Any agent
npx skills add artttj/rapid-stack --skill show
Clone the repo
git clone --depth 1 https://github.com/artttj/rapid-stack

Made for: Claude Code, Codex.

Per session 31 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 247 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00031 $0.00247
Opus 5 $0.00015 $0.00123
Sonnet 5 $0.00006 $0.00049
Haiku 4.5 $0.00003 $0.00025

Measured 2d ago against content hash 31af6c59c4f3, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

show 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 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

1. Serve: recipe `serve` in the background; wait until `curl -s localhost:<port>` answers (10 tries, 1s apart). Already running → reuse it.
plugins/op/skills/show/SKILL.md · 15 lines

What it actually says

op:show

  1. Serve: recipe serve in the background; wait until curl -s localhost:<port> answers (10 tries, 1s apart). Already running → reuse it.
  2. Screenshot the standard breakpoints: 375×812 (mobile), 768×1024 (tablet), 1440×900 (desktop). Offer 320, 1920, and 1512×982 (14" MacBook) as arrow-choice extras, or take whatever widths the request names. Both color schemes when the site has them (emulate prefers-color-scheme). Playwright MCP when available, else npx playwright screenshot.
  3. Look at every screenshot before writing a word. Verdict ≤5 bullets: hierarchy, spacing, overflow, contrast, anything broken at any viewport.
  4. Offer /rs:vibe for the full scorecard (arrow-choice; skip silently when rs is absent).
  5. Stop the server if this command started it.

Proof at end: the screenshot paths, listed.

Changes

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.

  1. 2d ago First seen · 15 lines · 31 tokens per session scan A 31af6c59c4f3

Subscribe to this mod's changes

show is a skill published in the GitHub repository artttj/rapid-stack (2 stars, last pushed 1mo ago), licensed MIT. It adds 31 tokens to every session and 247 once invoked, about $0.0002 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 2026-08-31.

Related

Other skills, from other repositories

ui-ux-pro-max

UI/UX design intelligence expert for web and mobile applications. Use when designing interfaces, selecting color palettes, typography, visual styles, building landing pages, dashboards, or reviewing code for UX issues. Covers 50+ design styles, 97 color palettes, 57 font pairings, 99 UX guidelines, 25 chart types…

shobcoder/shob · 104 tokens

flutter

Build production Flutter apps with Clean Architecture, Riverpod (preferred over Bloc/Provider), GoRouter navigation, Impeller rendering engine, Dart 3.7+ patterns, platform channels via Pigeon, and App Store/Play Store deployment.

EliasOulkadi/shokunin · 50 tokens

responsive-engine

Design multi-device layouts with Container Queries, clamp() fluid typography, :has() selector, subgrid, and modern CSS units (dvh/svh/lvh). Use when user asks to make a layout responsive, handle mobile/tablet/desktop breakpoints, create fluid typography, or use Container Queries. Do NOT use for full-page layouts (use…

EliasOulkadi/shokunin · 95 tokens

wordpress-manager

Manage WordPress remotely via local wp-cli over SSH. In this CodeAgents Mobile repo, primary use is selfhosted-ninja-prod — keep https://selfhosted.ninja/projects/codeagents-mobile/ in sync when product features, links, screenshots, or public copy change. Also supports updates, backups, restores, content, and custom…

eugenepyvovarov/CodeAgentsMobile · 76 tokens

flutter-codestyle

Custom Instructions: Senior Flutter & Dart Engineer.

GulajavaMinistudio/awesome-copilot-id · 13 tokens

swiftui-skills

Apple-authored SwiftUI and platform guidance extracted from Xcode. Helps AI agents write idiomatic, Apple-native SwiftUI with reduced hallucinations.

ameyalambat128/swiftui-skills · 34 tokens