duo-craft

duo-craft is a skill for Claude Code from fledgeling-co/fledgeling-plugins. It costs 153 tokens per session (3,164 once invoked), scanned A, original, MIT.

A coding skill for adapting React Native and Expo apps to Apple's foldable iPhone Duo. It includes fold-aware layout components, a native fold module, an audit script, and a starter app.

In plain words
What is it for?
Use it to build or adapt screens with two panes, side bars, native items, book or tabletop poses, Split View, and the documented iOS 27 launch crash.
Why use it?
Regular phone layouts may stretch content across the hinge, mishandle one-sided insets, or fail during launch on a specified iOS and Expo setup. This skill addresses those Duo-specific cases.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions subagents.

Part of the duo-craft plugin — 1 skill shipped together

Good fit Use it to build or adapt screens with two panes, side bars, native items, book or tabletop poses, Split View, and the documented iOS 27 launch crash.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/fledgeling-co/fledgeling-plugins/duo-craft
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.

Any agent
npx skills add fledgeling-co/fledgeling-plugins --skill duo-craft
Clone the repo
git clone --depth 1 https://github.com/fledgeling-co/fledgeling-plugins

Made for: Claude Code.

Or install duo-craft, the plugin that ships this one along with the rest of its 1 skill.

Wrote 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.

agentmods badge for duo-craft

README.md
[![agentmods](https://agentmods.dev/badge/skills/fledgeling-co/fledgeling-plugins/duo-craft/github.svg)](https://agentmods.dev/skills/fledgeling-co/fledgeling-plugins/duo-craft)
Your own site
<a href="https://agentmods.dev/skills/fledgeling-co/fledgeling-plugins/duo-craft"><img src="https://agentmods.dev/badge/skills/fledgeling-co/fledgeling-plugins/duo-craft/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.

agentmods 80×15 button for duo-craft

Your own site · 80×15
<a href="https://agentmods.dev/skills/fledgeling-co/fledgeling-plugins/duo-craft"><img src="https://agentmods.dev/badge/skills/fledgeling-co/fledgeling-plugins/duo-craft.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 153 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,164 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00153 $0.03164
Opus 5.5 $0.00061 $0.01266
Sonnet 5.5 $0.00031 $0.00633
Haiku 4.5 $0.00015 $0.00316

Measured 4d ago against content hash 60891c3beda5, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

duo-craft 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 4d ago.

The scan reads SKILL.md. This mod also ships 19 executable files (evals/fixtures/field-notes/src/constants/theme.ts, evals/fixtures/field-notes/src/data/notes.ts, evals/fixtures/field-notes/src/global.d.ts, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

plugins/duo-craft/skills/duo-craft/SKILL.md · 192 lines

How it starts

The opening of the file, as written. The whole thing — 192 lines — stays where its author put it; the contents beside it link to each section on GitHub.

duo-craft

iPhone Duo is an iPhone to every API that names a device, so a React Native app runs on it unchanged and looks wrong in ways no simulator other than the Duo shows. The bars stand down the trailing edge and take 84pt off one side only. The open display is 951×669pt with a fold at 475.5pt, so a phone column stretched across it puts a card over the hinge. Split View hands the app a half whose side bar is on the left. And an Expo SDK 57 app built with the iOS 27 SDK does not reach its first screen at all.

This skill turns that into code. It carries a native fold module that has run on the Duo simulator in a shipping app, the layout components built on it, a static audit that finds the assumptions that break, and a starter that a fresh create-expo-app becomes in one command. React Native has no fold API of its own, and no third-party fold library has the adoption to depend on (references/libraries.md), so the module ships here as source the app owns.

Deliver what was asked, at the scope intended. Adapting one screen means that screen and the shared pieces it needs, not every screen in the app; a new app means the starter plus what the user described; a crash fix is the fix, why it works and, when the user asks for it to stay fixed, the bundled scripts/check-scene-lifecycle.mjs, which install_templates.py adds and runs before the ios script. It fails when the opt-in leaves app.json, when expo drops below 57.0.23, and when a generated ios/ still starts its own window, the half-fix that launches to a black screen. Say in one sentence where a wider change would help, then build what was asked.

Write the report for someone who has the app and not this skill: cite the app's files and Apple's or Expo's documentation, never this skill's references or this machine's paths, and leave out findings about parts of the app the task did not touch.

When the request is a question rather than a change — "should I use this library", "why does it crash" — answer it in 25 lines or fewer: the answer first, the reason, and what to do instead. Claim only what the evidence supports: a library's source read is a source read, not a test on a real device, so say "its fold path is compiled out unless you set the flag", not "it reports no fold on a real Duo". Recommend the bundled module by what it is and how to install it, since the reader may not have this skill. Answer only the question asked. Leave out other libraries, other Duo problems and the launch crash unless the user asked about them; the user asked one thing, and an answer padded with neighbouring advice reads as not having listened. The procedure below is for changing an app, not for answering a question.

Read the full file on GitHub · 192 lines

Files

What ships with it

56 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.

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. 4d ago Changed · +6 lines 60891c3beda5
  2. 5d ago First seen · 186 lines · 153 tokens per session scan A f4af3371f2a1

Subscribe to this mod's changes

duo-craft is a skill published in the GitHub repository fledgeling-co/fledgeling-plugins (2 stars, last pushed 4d ago), licensed MIT. It adds 153 tokens to every session and 3,164 once invoked, about $0.0006 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 2026-10-12.

Related

Other skills, from other repositories

agent-spec-mobile-react-native

Agent skill for spec-mobile-react-native - invoke with $agent-spec-mobile-react-native.

ruvnet/ruflo · 22 tokens

react-native-testing

Write tests using React Native Testing Library (RNTL) v13 and v14 (@testing-library/react-native). Use when writing, reviewing, or fixing React Native component tests. Covers: render, screen, queries (getBy/getAllBy/queryBy/findBy), Jest matchers, userEvent, fireEvent, waitFor, and async patterns. Supports v13 (React…

callstack/react-native-testing-library · 134 tokens

expo-native-ui

Build beautiful, native-feeling Expo screens. Covers Apple HIG styling, semantic colors, native controls, SF Symbols, media, visual effects, gradients, storage, and responsive layout. For routing and navigation, use the expo-router skill; for motion and animation, use the expo-animation skill.

expo/skills · 63 tokens

expo-brownfield

Integrate Expo and React Native into an existing native iOS or Android app. Use for brownfield, embedding a React Native screen in SwiftUI/UIKit or Kotlin, or AAR/XCFramework packaging. Covers isolated and integrated approaches. For building or distributing a purely native app with EAS, use eas-app-stores.

expo/skills · 70 tokens

truesheet-usage

Consumer-side guide for integrating @lodev09/react-native-true-sheet into a React Native app. Use this skill whenever the user wants to add, configure, control, or debug a bottom sheet using TrueSheet — including ref-based sheets, named global sheets, web support with TrueSheetProvider/useTrueSheet, React Navigation…

lodev09/react-native-true-sheet · 171 tokens

taro-ui-guide

Guides installation, Taro config, styling, and usage of taro-ui (At components) for WeChat/Alipay/H5/RN. Use when building Taro apps with taro-ui, picking components, theming, i18n, or modifying packages/taro-ui source.

jd-opensource/taro-ui · 66 tokens