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 instructions/srnichols/plan-forge/swiftuigit clone --depth 1 https://github.com/srnichols/plan-forgeWrote 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/instructions/srnichols/plan-forge/swiftui)<a href="https://agentmods.dev/instructions/srnichols/plan-forge/swiftui"><img src="https://agentmods.dev/badge/instructions/srnichols/plan-forge/swiftui.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 | $0.01004 | $0.01004 |
| Opus 5 | $0.00502 | $0.00502 |
| Sonnet 5 | $0.00201 | $0.00201 |
| Haiku 4.5 | $0.00100 | $0.00100 |
Grade A, and why
plan-forge swiftui.instructions.md 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 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.
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 — 163 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SwiftUI Patterns
State Management
Property Wrappers Guide
| Wrapper | Use Case |
|---|---|
@State |
Local view state (primitive types) |
@Binding |
Two-way binding from parent |
@StateObject |
Owned ViewModel (created by this view) |
@ObservedObject |
Injected ViewModel (created externally) |
@EnvironmentObject |
App-wide shared state |
@Environment |
System values (colorScheme, dismiss, etc.) |
ViewModel Pattern
@MainActor
final class ItemListViewModel: ObservableObject {
@Published private(set) var items: [Item] = []
@Published private(set) var isLoading = false
@Published var errorMessage: String?
private let service: any ItemService
init(service: some ItemService) {
self.service = service
}
func load() async {
isLoading = true
defer { isLoading = false }
do {
items = try await service.fetchAll()
} catch {
errorMessage = error.localizedDescription
}
}
}
Rules
- Always
@MainActoron ViewModels that publish to@Published - Never call
DispatchQueue.main.async— use@MainActorinstead - Inject services via
init— not as globals or singletons - Use
@StateObjectwhen the view owns the VM;@ObservedObjectwhen injected
View Structure
struct ItemListView: View {
@StateObject private var viewModel: ItemListViewModel
init(service: some ItemService) {
_viewModel = StateObject(wrappedValue: ItemListViewModel(service: service))
}
var body: some View {
content
.navigationTitle("Items")
.task { await viewModel.load() }
.alert("Error", isPresented: Binding(
get: { viewModel.errorMessage != nil },
set: { if !$0 { viewModel.errorMessage = nil } }
)) {
Button("OK") { viewModel.errorMessage = nil }
} message: {
Text(viewModel.errorMessage ?? "")
}
}
@ViewBuilder
private var content: some View {
if viewModel.isLoading {
ProgressView()
} else {
List(viewModel.items) { item in
ItemRow(item: item)
}
}
}
}
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.
- 2d ago First seen · 163 lines · 1,004 tokens per session scan A c7886b9b1f2c
plan-forge swiftui.instructions.md is an instructions file published in the GitHub repository srnichols/plan-forge (5 stars, last pushed 3d ago), licensed MIT. It adds 1,004 tokens to every session, about $0.0050 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 2026-09-03.
Other instructions, from other repositories
android-harness-kit GEMINI.md
Instructions for rabee-elkholy/android-harness-kit: Follow AGENTS.md and .agents/rules/harness-rules.md. That file wins.
ios-agent-skills AGENTS.md
Instructions for rusel95/ios-agent-skills: This repository contains production-tested iOS Agent Skills.
ios-agent-skills AGENTS.md
Instructions for koshkinvv/ios-agent-skills, covering ios agent skills, available skills, ios-swiftui, ios-architecture and ios-networking.
ios-skills-collection CLAUDE.md
Claude Code instructions for JordanCoin/ios-skills-collection, a project described as: 200+ iOS/Swift/Xcode agent skills from 28 authors with phase-aware routing. Claude Code plugin + Codex CLI + Mac App. Full lifecycle: ideation → design → develop → test → deploy → iterate.
swift-kmp-skill AGENTS.md
Instructions for sorunokoe/swift-kmp-skill, covering agents.md — swift-kmp, what this repository is, repository structure, how to apply this skill and skill loading order.
NutriSport CLAUDE.md
Instructions for satanyakiv/NutriSport, covering nutrisport, rules, commands, skills and quick reference.