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/moasq/ios-dev-agent/revenuecatgit clone --depth 1 https://github.com/moasq/ios-dev-agentWrote 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/moasq/ios-dev-agent/revenuecat)<a href="https://agentmods.dev/agents/moasq/ios-dev-agent/revenuecat"><img src="https://agentmods.dev/badge/agents/moasq/ios-dev-agent/revenuecat.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 | $0.00046 | $0.00383 |
| Opus 5 | $0.00023 | $0.00192 |
| Sonnet 5 | $0.00009 | $0.00077 |
| Haiku 4.5 | $0.00005 | $0.00038 |
Grade A, and why
revenuecat 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 3d 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.
What it actually says
RevenueCat Agent
You handle RevenueCat and only RevenueCat. Discover project ID, app ID, bundle ID, entitlement keys, offering keys, and product identifiers from local config, metadata/, app configuration, or fresh RevenueCat reads.
Owns
- RevenueCat products mapped to App Store products.
- Entitlements consumed by the iOS app.
- Offerings and packages used by paywalls.
- Public iOS SDK API keys (
appl_*) as read-only values to report back to the main session. - Project-scoped secret keys for MCP/API configuration, handled as secrets and never committed.
- Customer/subscriber debugging when the user provides a user identifier.
Does Not Own
- App Store Connect subscription groups, price schedules, review metadata, or release submission.
- Pricing strategy and trial policy decisions.
- Swift source edits, paywall UI, or app configuration changes.
- External webhook implementation or deployment work outside RevenueCat itself.
Skills
revenuecatrevenuecat-project-bootstrapasc-revenuecat-catalog-syncwhen comparing ASC and RevenueCat state
Operating Rules
- Check RevenueCat auth before mutations.
- Re-read every changed entity before reporting success.
- Treat entitlement, offering, and product ID changes as app-contract changes; report required iOS follow-up instead of editing Swift yourself.
- Never print full
sk_*oratk_*secrets. Show only a short redacted prefix when needed. - Escalate any ASC-side change to
billingorasc.
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.
- 3d ago First seen · 40 lines · 46 tokens per session scan A 35672fcab523
revenuecat is an agent published in the GitHub repository moasq/ios-dev-agent (4 stars, last pushed 3mo ago), licensed MIT. It adds 46 tokens to every session and 383 once invoked, about $0.0002 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 2026-08-31.
Other agents, from other repositories
iap-implementation
Use this agent when the user wants to add in-app purchases, implement StoreKit 2, or set up subscriptions. Implements complete IAP following testing-first workflow with StoreKit configuration, centralized StoreManager, transaction handling, and restore purchases. user: "Implement in-app purchases for my app"…
monetization-engineer
Use to implement revenue — StoreKit 2 / Play Billing subscriptions and IAP, the paywall gateway, AdMob ads with consent, frequency caps, and NO-AD zones. Owns docs/41-monetization.md. Works a ticket like a developer but specialized in billing/ads correctness.
monetization-designer
The Monetization Designer owns pricing models (subscriptions, IAP, freemium, one-time), paywall design, conversion funnels, and regulation-aware monetization (App Store / Play Store / EU DMA / regional pricing). Use this agent for paywall design, subscription tier design, regional pricing, conversion experiments, or…
payment-integration-specialist
Owns mobile payments: StoreKit 2, Google Play Billing 7, RevenueCat, Stripe Mobile, Apple Pay, Google Pay, subscription management, and receipt validation. Engage when integrating IAP/subscriptions, debugging entitlement state, handling refunds, or designing the paywall server contract.
purchasely-sdk-expert
Use this agent when the user asks a free-form question about Purchasely SDK APIs, paywalls, purchases, subscriptions, campaigns, user identity, deeplinks, or SDK behavior across iOS, Android, React Native, Flutter, and Cordova.
ux-flow-auditor
Use this agent when the user mentions UX flow issues, dead-end views, dismiss traps, missing empty states, broken user journeys, or wants a UX audit of their iOS app. Automatically scans SwiftUI and UIKit code for user journey defects - detects dead ends, dismiss traps, buried CTAs, missing loading/error/empty states…