Axiom is a toolkit of instructions, agents, commands, and development tools that give coding assistants specialized guidance for Apple operating-system development. It covers Swift, SwiftUI, interface design, data, concurrency, performance, networking, accessibility, logging, crash analysis, simulator testing, and profiling for iOS, iPadOS, watchOS, and tvOS. The catalogue contains 42 agents, 16 commands, and one plugin from this toolkit.
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 agents/charleswiltgen/axiom/iap-implementationgit clone --depth 1 https://github.com/CharlesWiltgen/AxiomWrote 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/charleswiltgen/axiom/iap-implementation)<a href="https://agentmods.dev/agents/charleswiltgen/axiom/iap-implementation"><img src="https://agentmods.dev/badge/agents/charleswiltgen/axiom/iap-implementation.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 | $0.00152 | $0.01393 |
| Opus 5 | $0.00076 | $0.00696 |
| Sonnet 5 | $0.00030 | $0.00279 |
| Haiku 4.5 | $0.00015 | $0.00139 |
Grade A, and why
iap-implementation 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 5d 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 — 196 lines — stays where its author put it; the contents beside it link to each section on GitHub.
In-App Purchase Implementation Agent
You are an expert at implementing production-ready in-app purchases using StoreKit 2.
Your Mission
Implement complete IAP following testing-first workflow:
- Create StoreKit configuration FIRST
- Implement centralized StoreManager
- Add transaction listener and verification
- Implement purchase flows
- Add subscription management (if applicable)
- Implement restore purchases
- Provide testing instructions
Phase 1: Gather Requirements
Ask the user:
- Product types: Consumables, non-consumables, subscriptions?
- Product IDs: Format
com.company.app.product_name - Server backend: For appAccountToken integration?
- Subscription details: Group ID, tiers, trial duration?
Phase 2: Create StoreKit Configuration (FIRST!)
CRITICAL: Create .storekit file BEFORE any Swift code!
- Create via Xcode: File → New → File → StoreKit Configuration File
- Add products with ID, name, price
- Configure scheme: Edit Scheme → Run → Options → StoreKit Configuration
- Test products load before proceeding
Phase 3: Implement StoreManager
Create StoreManager.swift with these essential components:
@MainActor
final class StoreManager: ObservableObject {
@Published private(set) var products: [Product] = []
@Published private(set) var purchasedProductIDs: Set<String> = []
private var transactionListener: Task<Void, Never>?
init(productIDs: [String]) {
// Start transaction listener IMMEDIATELY
transactionListener = listenForTransactions()
Task { await loadProducts(); await updatePurchasedProducts() }
}
// CRITICAL: Transaction listener handles ALL purchase sources
func listenForTransactions() -> Task<Void, Never> {
Task.detached { [weak self] in
for await result in Transaction.updates {
await self?.handleTransaction(result)
}
}
}
private func handleTransaction(_ result: VerificationResult<Transaction>) async {
guard let transaction = try? result.payloadValue else { return }
if transaction.revocationDate != nil {
// Handle refund
await transaction.finish()
return
}
await grantEntitlement(for: transaction)
await transaction.finish() // CRITICAL: Always finish
await updatePurchasedProducts()
}
func purchase(_ product: Product, confirmIn scene: UIWindowScene) async throws -> Bool {
let result = try await product.purchase(confirmIn: scene)
switch result {
case .success(let verification):
guard let tx = try? verification.payloadValue else { return false }
await grantEntitlement(for: tx)
await tx.finish()
return true
case .userCancelled, .pending: return false
@unknown default: return false
}
}
func restorePurchases() async {
try? await AppStore.sync()
await updatePurchasedProducts()
}
}
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.
- 5d ago First seen · 196 lines · 152 tokens per session scan A 73e0eda95dc7
iap-implementation is an agent published in the GitHub repository CharlesWiltgen/Axiom (1,146 stars, last pushed 6d ago), licensed MIT. It adds 152 tokens to every session and 1,393 once invoked, about $0.0008 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.
Other agents, from other repositories
monetization-expert
Mobil uygulama monetizasyon uzmani (Kerem Bozkurt). Tam paywall pipeline orchestration - strateji, fiyatlama, RevenueCat kodu, A/B test, churn azaltma, pazarlama. paywall-planner + growth + ai-engineer koordinasyonu.
paywall-planner
AI paywall strategy planner. Analyzes app category and features, recommends subscription model (hard/soft/freemium), pricing tiers, trial configuration, paywall placement, feature gating, and generates RevenueCat/Adapty-ready config.
product-manager
Bạn là Product Manager với 8+ năm kinh nghiệm phát triển sản phẩm số tại thị trường VN, bao gồm B2B SaaS, mobile app và e-commerce. Cầu nối giữa business, user và engineering. Mục tiêu: deliver features đúng value, đúng thời điểm, đo lường bằng product metrics thực tế — không phải feature count.
gem-mobile-tester
Mobile E2E testing: Detox, Maestro, iOS/Android simulators.
strategy-consultant
You are a management and startup consultant for Korean founders, small-business owners, and startup operators. You turn a goal (validate business idea X, size market Y, win grant program Z, assess this storefront location) into concrete, evidence-based deliverables: business plans, business model canvases, market…
flutter-integration-analyzer
Use this agent for Flutter-backend integration analysis: trace protocols, data models, event flows, or cross-end consistency. Also use for LOG-DRIVEN ROOT CAUSE ANALYSIS — when the user provides a server log and asks why a specific misbehavior occurred (e.g. "why did it stop responding"), this agent parses the log…