agentmods.dev

purchasely-review

purchasely-review is a skill for Claude Code from Purchasely/Purchasely-AI-Plugin. It costs 52 tokens per session (13,780 once invoked), scanned A, original, MIT.

A review workflow for Purchasely SDK integrations, where Purchasely is a service for adding subscription purchases to mobile apps. It checks integrations on iOS, Android, React Native, Flutter, and Cordova.

In plain words
What is it for?
It is for reviewing SDK setup, paywall display, purchase actions, deep links, user management, and how the app works with other subscription systems.
Why use it?
It finds common integration mistakes and checks whether subscription and purchase flows are ready for production.

Skill for Claude Code

Written for Claude Code: $ARGUMENTS substitution. Also seen: mentions subagents; mentions Claude Code.

Part of the purchasely plugin — 5 skills, 4 commands, 1 agent, 1 hook shipped together

not rated 2repo 7d ago A scan 52 tokens original MIT

Good fit It is for reviewing SDK setup, paywall display, purchase actions, deep links, user management, and how the app works with other subscription systems.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/purchasely/purchasely-ai-plugin/purchasely-review
View source ↗ Purchasely/Purchasely-AI-Plugin
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.

Any agent
npx skills add Purchasely/Purchasely-AI-Plugin --skill purchasely-review
Clone the repo
git clone --depth 1 https://github.com/Purchasely/Purchasely-AI-Plugin

Made for: Claude Code.

Or install purchasely, the plugin that ships this one along with the rest of its 5 skills, 4 commands, 1 agent, 1 hook.

Wrote 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.

agentmods badge for purchasely-review

README.md
[![agentmods](https://agentmods.dev/badge/skills/purchasely/purchasely-ai-plugin/purchasely-review/github.svg)](https://agentmods.dev/skills/purchasely/purchasely-ai-plugin/purchasely-review)
Your own site
<a href="https://agentmods.dev/skills/purchasely/purchasely-ai-plugin/purchasely-review"><img src="https://agentmods.dev/badge/skills/purchasely/purchasely-ai-plugin/purchasely-review/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.

agentmods 80×15 button for purchasely-review

Your own site · 80×15
<a href="https://agentmods.dev/skills/purchasely/purchasely-ai-plugin/purchasely-review"><img src="https://agentmods.dev/badge/skills/purchasely/purchasely-ai-plugin/purchasely-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 52 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 13,780 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00052 $0.13780
Opus 5 $0.00026 $0.06890
Sonnet 5 $0.00010 $0.02756
Haiku 4.5 $0.00005 $0.01378

Measured 10d ago against content hash d5831b4f4b8b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

purchasely-review 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 10d 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.

purchasely/skills/purchasely-review/SKILL.md · 339 lines

How it starts

The opening of the file, as written. The whole thing — 339 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Purchasely Integration Review

You are an expert reviewer of Purchasely SDK integrations. Your job is to systematically audit the user's codebase for correctness, best practices, and common mistakes.

Before reviewing, read ../../references/purchasely-architecture.md to ground yourself in the end-to-end platform and resilience guarantees — this helps you spot anti-patterns such as putting the customer's backend on the critical purchase path. If the project also handles web subscriptions (Stripe / another subscription platform / in-house), load ../../references/cross-platform-subscriptions.md to know what cross-store coexistence patterns are expected vs. broken.

The bundled references are intentionally curated, not a full copy of the public docs. If a review finding depends on an exact SDK signature, current Console behavior, or a detail missing from ../../references/, verify it against the official Purchasely documentation at https://docs.purchasely.com/ before flagging or fixing it.

When the review uncovers a deeper issue, route to the troubleshooting docs:

  • ../../references/troubleshooting/common-issues.md — symptom→cause table, log reading, full event taxonomy (use when a check fails and you're not sure why)
  • ../../references/troubleshooting/screen-issue-report.md — when the audit points at a Screen Composer bug (layout, missing component, wrong offer), package the escalation with this template instead of recommending app-code changes

Universal SDK concept references (apply to every platform — load as needed during the review):

  • ../../references/concepts/running-modes.md — Full vs Observer modes, log levels
  • ../../references/concepts/paywall-actions.md — interceptor rules + every code path must return/resolve an intercept result
  • ../../references/concepts/presentation-types.md — NORMAL / FALLBACK / DEACTIVATED / CLIENT guard
  • ../../references/concepts/presentation-cache.md — preload pattern + when to invalidate
  • ../../references/concepts/observer-mode-post-purchase.md — intercept-result → dismiss ordering
  • ../../references/concepts/programmatic-purchases.md — exact app-side purchase APIs by platform
  • ../../references/concepts/user-attributes-targeting.md — attributes for audiences
  • ../../references/concepts/privacy-settings.md — revokeDataProcessingConsent, privacy purposes, essential/optional processing
  • ../../references/concepts/user-identity.md — userLogin / userLogout timing, anonymous→logged-in merge, foreground resync
  • ../../references/concepts/subscription-checks.md — gating + restore purchases
  • ../../references/concepts/subscription-management.md — native Manage Subscription entry point (App Store / Play)
  • ../../references/concepts/promotional-offers.md — offers eligibility responsibility + implementation
  • ../../references/concepts/campaigns.md — deeplink/campaign display flags (allowDeeplink / allowCampaigns on v6; allowDeeplink defaults to true on every v6 platform including React Native — the RN builder just omits the key when unset; allowCampaigns defaults to true in v6 on iOS/Android/Flutter, was false in v5) + SDK ≥ 5.1.0
  • ../../references/concepts/lottie-animations.md — Lottie bridge/dependency checks for Screens with animations
  • ../../references/concepts/analytics-integration.md — events forwarding + analytics wrapper recommendation
  • ../../references/sdk-versions.md — latest stable versions (flag outdated pins)
  • ../../references/troubleshooting/error-codes.md — PLYError reference (errors silently ignored is a FAIL)
  • ../../references/troubleshooting/debug-mode.md — verify LogLevel.DEBUG gating

If $ARGUMENTS specifies a particular area (e.g., "interceptor", "deeplinks", "initialization"), focus the review on that section only. Otherwise, run the full checklist.

Read the full file on GitHub · 339 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. 10d ago First seen · 339 lines · 52 tokens per session scan A d5831b4f4b8b

Subscribe to this mod's changes

purchasely-review is a skill published in the GitHub repository Purchasely/Purchasely-AI-Plugin (2 stars, last pushed 7d ago), licensed MIT. It adds 52 tokens to every session and 13,780 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.

Mobile
Related

Other skills, from other repositories

orca-emulator-android

Android device and emulator control from inside Orca over adb, with the live device view in Orca's emulator pane. Use when driving an adb-connected emulator or phone on Windows, Linux, or macOS: booting AVDs, taps, swipes, typing, hardware buttons, rotation, app install and launch, runtime permissions, the…

stablyai/orca · 102 tokens

android-tombstone-symbolication

Symbolicate the .NET runtime frames in an Android tombstone file. Extracts BuildIds and PC offsets from the native backtrace, downloads debug symbols from the Microsoft symbol server, and runs llvm-symbolizer to produce function names with source file and line numbers. USE FOR triaging a .NET MAUI or Mono Android app…

dotnet/skills · 176 tokens

dogfood

Systematically explore and test a mobile app on iOS/Android with agent-device to find bugs, UX issues, and other problems. Use when asked to dogfood, QA, exploratory test, find issues, bug hunt, or test this app on mobile.

callstack/agent-device · 55 tokens

winapp-maui

Package and sign .NET MAUI Windows apps with winapp, resolving the resizetizer manifest dependency. Use when packaging or signing a .NET MAUI Windows app, building a MAUI MSIX or signed unpackaged build in CI, or fixing 'manifest contains unresolved placeholders ($placeholder$)' errors from winapp package.

microsoft/winappCli · 71 tokens

react-native-ease-refactor

Scan for Animated/Reanimated code and migrate to EaseView.

appandflow/react-native-ease · 18 tokens

apple-search-ads

When the user wants to set up, optimize, or scale Apple Search Ads (ASA) campaigns — including keyword bidding, match types, campaign structure, Creative Product Sets, CPP routing, and ROAS optimization. Use when the user mentions "Apple Search Ads", "ASA", "Search Ads", "Search tab ads", "Today tab ads", "CPT"…

Eronred/aso-skills · 127 tokens