agentmods.dev

convert

convert is a command for Claude Code from heyadam/claudedesign-to-swiftui. It costs 19 tokens per session (492 once invoked), scanned A, original, MIT.

A command that turns a Claude-generated web design into a SwiftUI view file for an Xcode project. SwiftUI is Apple’s code-based system for building app screens.

In plain words
What is it for?
Use it when you have a Claude design link or local archive and need its screen recreated in SwiftUI inside the active Xcode workspace.
Why use it?
It removes the manual work of copying a web mockup into a native iPhone or Apple-platform interface. It also includes steps for building the project and addressing reported issues.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the claudedesign-to-swiftui plugin — 1 skill, 1 command shipped together

not rated 92repo 4mo ago A scan 19 tokens original MIT

Good fit Use it when you have a Claude design link or local archive and need its screen recreated in SwiftUI inside the active Xcode workspace.

Compare 6 commands from other repositories ↓
View source ↗ heyadam/claudedesign-to-swiftui
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add heyadam/claudedesign-to-swiftui
Claude Code
/plugin install claudedesign-to-swiftui

Made for: Claude Code.

Or install claudedesign-to-swiftui, the plugin that ships this one along with the rest of its 1 skill, 1 command.

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 convert

README.md
[![agentmods](https://agentmods.dev/badge/commands/heyadam/claudedesign-to-swiftui/convert/github.svg)](https://agentmods.dev/commands/heyadam/claudedesign-to-swiftui/convert)
Your own site
<a href="https://agentmods.dev/commands/heyadam/claudedesign-to-swiftui/convert"><img src="https://agentmods.dev/badge/commands/heyadam/claudedesign-to-swiftui/convert/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 convert

Your own site · 80×15
<a href="https://agentmods.dev/commands/heyadam/claudedesign-to-swiftui/convert"><img src="https://agentmods.dev/badge/commands/heyadam/claudedesign-to-swiftui/convert.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 19 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 492 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 $0.00019 $0.00492
Opus 5 $0.00010 $0.00246
Sonnet 5 $0.00004 $0.00098
Haiku 4.5 $0.00002 $0.00049

Measured 10d ago against content hash 1ff074cce664, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

convert 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 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.

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.

commands/convert.md · 22 lines

What it actually says

The user has invoked the converter with $ARGUMENTS.

If $ARGUMENTS is empty, ask for a Claude design URL (e.g. https://api.anthropic.com/v1/design/h/<id>?open_file=<name>) or a local .tar.gz path before proceeding. Design URLs may be one-shot/short-lived — fetch immediately.

Invoke the claude-design-to-swiftui skill and follow its workflow end to end:

  1. Fetch: "${CLAUDE_PLUGIN_ROOT}/skills/claude-design-to-swiftui/scripts/fetch.sh" "$ARGUMENTS"
  2. Render the entry HTML in Chrome at 390x844 via claude-in-chrome and screenshot.
  3. Read the HTML and any linked CSS files.
  4. Translate to SwiftUI using the reference mappings in ${CLAUDE_PLUGIN_ROOT}/skills/claude-design-to-swiftui/references/.
  5. Find the active Xcode workspace via mcp__plugin_claudedesign-to-swiftui_xcode-tools__XcodeListWindows, then write the file with mcp__plugin_claudedesign-to-swiftui_xcode-tools__XcodeWrite.
  6. Build with mcp__plugin_claudedesign-to-swiftui_xcode-tools__BuildProject and patch any errors via mcp__plugin_claudedesign-to-swiftui_xcode-tools__XcodeListNavigatorIssues + mcp__plugin_claudedesign-to-swiftui_xcode-tools__XcodeUpdate.
  7. Render the preview with mcp__plugin_claudedesign-to-swiftui_xcode-tools__RenderPreview, visually diff against the prototype screenshot, and iterate.

Required setup (remind the user if anything is missing): Xcode 26.3+ with Settings → Intelligence → Xcode Tools = ON, and the target Xcode project open. The claude-in-chrome MCP must also be installed.

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. 10d ago First seen · 22 lines · 19 tokens per session scan A 1ff074cce664

Subscribe to this mod's changes

convert is a command published in the GitHub repository heyadam/claudedesign-to-swiftui (92 stars, last pushed 4mo ago), licensed MIT. It adds 19 tokens to every session and 492 once invoked, about $0.0001 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.

Mobile
Related

Other commands, from other repositories

app-store-audit

Run an enterprise pre submission compliance audit on an iOS or Android app against Apple App Store and Google Play rejection rules. Pass a project path or run from the project root.

mjmirza/app-store-compliance · 35 tokens

initialize-ios

Manual override: initialize ast-index for iOS/Swift/ObjC project.

defendend/Claude-ast-index-search · 18 tokens

maestro-selectors-instructions

Guide to using Maestro selectors for targeting UI elements in tests.

appboypov/pew-pew-plaza-packs · 19 tokens

mobile-performance-check

Analyze mobile app for performance issues using the mobile-best-practices database.

tungnk123/mobile-best-practices · 14 tokens

flutter-review

Review Flutter/Dart code for idiomatic patterns, widget best practices, state management, performance, accessibility, and security. Invokes the flutter-reviewer agent.

DekaPrayoga/AurixAgent · 32 tokens

flutter-test

Run Flutter/Dart tests, report failures, and incrementally fix test issues. Covers unit, widget, golden, and integration tests.

DekaPrayoga/AurixAgent · 27 tokens