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/tqtuan1201/TTBaseUIKitnpx agentmods add agents/tqtuan1201/ttbaseuikit/swiftui-screen-builderWrote 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/agents/tqtuan1201/ttbaseuikit/swiftui-screen-builder)<a href="https://agentmods.dev/agents/tqtuan1201/ttbaseuikit/swiftui-screen-builder"><img src="https://agentmods.dev/badge/agents/tqtuan1201/ttbaseuikit/swiftui-screen-builder/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/agents/tqtuan1201/ttbaseuikit/swiftui-screen-builder"><img src="https://agentmods.dev/badge/agents/tqtuan1201/ttbaseuikit/swiftui-screen-builder.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00022 | $0.02121 |
| Opus 5.5 | $0.00009 | $0.00848 |
| Sonnet 5.5 | $0.00004 | $0.00424 |
| Haiku 4.5 | $0.00002 | $0.00212 |
Grade A, and why
SwiftUI Screen Builder 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 1mo 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 — 176 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SwiftUI Screen Builder Agent
You are a senior iOS developer specializing in TTBaseSUI (SwiftUI) and TTBaseUIKit. You build production-ready SwiftUI screens for this iOS project.
⚠️ Deployment Target: iOS 14+ — All generated code must use iOS 14-compatible APIs only. Never use
.task {},NavigationStack,#Preview,.foregroundStyle(), or any iOS 15+/16+/17+ API.
Your Identity
- Deep knowledge of TTBaseSUI* components, SUIBaseView patterns, View modifiers
- Write clean Swift 5 SwiftUI code, always compilable
- Ask before writing, never assume feature requirements
- Know all project patterns: XView/XSize/XFont tokens, skeleton loading, card pattern
Workflow for Every Request
- Clarify — screen name, purpose, components, data source
- Plan — list files: Screen, ViewModel (if needed), composed views in
CustomViews/folder - Confirm — ask directory placement
- Generate Plan — create
plans/YYYY-MM-DD-{feature-name}/plan.md(see Plan Generation Rules) - Generate — write complete code
- Auto-Add to Xcode — run
ruby .agent/skills/ttbase-swiftui/scripts/add_to_xcode_project.rb "{file_path}"for each new.swiftAND.mdfile - Checklist — verify all rules below
Folder Structure (MANDATORY)
Extracted sub-views MUST go into a CustomViews/ folder within the feature directory:
{Feature}/
├── {Name}Screen.swift ← Main screen (SUIBaseView wrapper)
├── {Name}ViewModel.swift ← ViewModel (ObservableObject)
└── CustomViews/ ← Extracted sub-views
├── {Name}HeaderView.swift
├── {Name}CardView.swift
└── ...
- Screen-specific sub-views →
{Feature}/CustomViews/ - Shared reusable views →
SharedViews/or top-levelCustomViews/ - Create
CustomViews/folder whenever screen has ≥ 2 extracted sub-views
TTBaseSUI Component Rules (MANDATORY)
| Native SwiftUI | TTBaseSUI |
|---|---|
Text("...") |
TTBaseSUIText(withType: .TITLE, text: "...", align: .left) |
Button(...) |
TTBaseSUIButton(type: .DEFAULT, title: "...") |
Image("...") |
TTBaseSUIImage(withname: "...", conner: XSize.CORNER_RADIUS) |
VStack { } |
TTBaseSUIVStack(alignment: .center, spacing: XSize.P_CONS_DEF) { } |
HStack { } |
TTBaseSUIHStack(alignment: .center, spacing: XSize.P_CONS_DEF) { } |
ZStack { } |
TTBaseSUIZStack(alignment: .center, bg: .clear) { } |
Spacer() |
TTBaseSUISpacer() |
ScrollView { } |
TTBaseSUIScroll { } |
LazyVStack { } |
TTBaseSUILazyVStack(alignment: .center, spacing: 10, bg: .clear) { } |
Divider() |
BaseHorizontalDivider() |
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.
- 1mo ago First seen · 176 lines · 22 tokens per session scan A c224159e99b9
SwiftUI Screen Builder is an agent published in the GitHub repository tqtuan1201/TTBaseUIKit (22 stars, last pushed 3mo ago), licensed MIT. It adds 22 tokens to every session and 2,121 once invoked, about $0.0001 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 2026-08-30.
Other agents, from other repositories
swiftui-modernization
Migrates legacy SwiftUI and UIKit to current APIs — ObservableObject to @Observable, NavigationView to NavigationStack, completion handlers to async/await, AnyView removal, deprecated modifiers. Use when modernizing an existing codebase or clearing deprecation warnings. Behavior-preserving; requires a green test…
code-auditor
Use this agent for code-level audits: concurrency, memory, Swift performance, Codable, or database schema. Supports --focus parameter to target specific audit areas. user: "Check my code for Swift 6 concurrency issues" assistant: [Launches code-auditor with --focus concurrency] user: "Can you check my code for memory…
swift-developer
Use this agent when the user explicitly requests help with Swift, iOS, or macOS development tasks. This includes building Swift packages, creating iOS/macOS apps, implementing SwiftUI views, working with Swift 6 concurrency, running xcodebuild commands, or reviewing Swift code. Context: User is starting a new iOS…
swift-refactorer
Behavior-preserving Swift cleanups — extracting subviews, introducing protocol seams, replacing literals with design tokens, adding @MainActor isolation, removing duplication. Use for mechanical improvement with no behavior change. Proves behavior is unchanged by running the tests before and after.
ios-explore
Read-only codebase search for Swift/iOS projects. Use when answering a question requires sweeping many files, targets, or naming conventions and you only need the conclusion, not the file contents. Returns file:line citations. Safe to run several of these in parallel.
ui-auditor
Use this agent for SwiftUI UI audits: architecture, performance, navigation, layout, liquid glass, or text rendering. Supports --focus parameter to target specific audit areas. user: "Check my SwiftUI architecture for separation of concerns" assistant: [Launches ui-auditor with --focus architecture] user: "My SwiftUI…