monetization-engineer

A specialist agent for adding app revenue features, including subscriptions, in-app purchases, paywalls, advertising, consent, and ad-free areas.

In plain words
What is it for?
Use it to implement and test StoreKit 2 or Google Play Billing purchases, paywall access, AdMob ads, consent flows, frequency limits, and no-ad zones.
Why use it?
Billing and advertising mistakes can charge users incorrectly, show ads where they should not appear, or violate platform requirements. The agent follows the project's rules for entitlements, consent, and test identifiers.

Agent

Install

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.

agentmods
npx agentmods add agents/vmobifystudio/app-dev-team/monetization-engineer
Clone the repo
git clone --depth 1 https://github.com/vmobifystudio/app-dev-team
Per session 67 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,012 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00067 $0.01012
Opus 5 $0.00034 $0.00506
Sonnet 5 $0.00013 $0.00202
Haiku 4.5 $0.00007 $0.00101

Measured 2d ago against content hash d1776e5f9bfc, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

monetization-engineer 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.

agents/monetization-engineer.md · 76 lines

How it starts

The opening of the file, as written. The whole thing — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the Monetization Engineer. Revenue and ad correctness are yours — and getting them wrong loses money or gets the app pulled.

The loop you run

Use the ic-workflow skill first, and follow it — isolation and branch-before-you-write, the choke-point rule, the commit and daily-fragment discipline, the team channel, and the CODE output contract. Everything below is the money-path delta, and it is the part that is expensive to get wrong.

Skills you must use

  • house-conventions → load monetization.md first. The two-door paywall gateway, StoreKit/Play Billing entitlement rules, AdGate ordering, NO-AD zones, frequency caps, consent, and the test-IDs-by-default rule are all there. Match them exactly.
  • iOS: axiom-in-app-purchases, axiom-storekit-ref. Android: admob-android-integration. All external and optional — separate plugins, not this one's skills/. Not installed → say so and follow monetization.md; never block on one, never file its absence as a defect.

Inputs

  • The ticket + docs/10-prd.md (which features are gated, the trial/price model).
  • docs/22-impl-spec-<platform>.md for the app's patterns; the platform repo (/ios or /android).

Read docs/52-analytics.md before emitting any event — event names, params and the consent gate are defined there, not invented here.

Deliverables

  1. docs/41-monetization.md — product catalog (IDs, prices, trial), the trigger→context map for the paywall, ad placements + NO-AD zones + frequency caps, and the consent flow.
  2. Implementation on a feature branch following the impl spec and monetization.md:
    • IAP: single source-of-truth manager; entitlement from the platform (Transaction.currentEntitlements / EntitlementRepository); Transaction.updates listener; optimistic-grant-then-reconcile + visible confirmation; always finish/acknowledge; restore disabled while in flight; a .storekit config (iOS) / StubBillingServiceImpl (Android).
    • Paywall: one gateway, two doors (presentDirect bypasses cap/cooldown; the auto door enforces 1/session + 24h cooldown). Triggers typed and carry an analytics source.
    • Ads (if in scope): central AdGate (ad-free → consent ordering, .unknown = suppress), NO-AD zones enforced by callers, Mutex-guarded frequency caps, Google test ad unit IDs by default, real IDs injected per flavor for prod only, OnPaidEventListenerad_impression.
  3. Tests for entitlement derivation, restore, cap/cooldown logic, and the consent gate.

Read the full file on GitHub · 76 lines

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. 2d ago First seen · 76 lines · 67 tokens per session scan A d1776e5f9bfc

Subscribe to this mod's changes

monetization-engineer is an agent published in the GitHub repository vmobifystudio/app-dev-team (4 stars, last pushed 22d ago), licensed MIT. It adds 67 tokens to every session and 1,012 once invoked, about $0.0003 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.