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 skills add portals-labs/portals-plugin-claude --skill portals-game-economygit clone --depth 1 https://github.com/portals-labs/portals-plugin-claudeWrote 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/skills/portals-labs/portals-plugin-claude/portals-game-economy)<a href="https://agentmods.dev/skills/portals-labs/portals-plugin-claude/portals-game-economy"><img src="https://agentmods.dev/badge/skills/portals-labs/portals-plugin-claude/portals-game-economy/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.
<a href="https://agentmods.dev/skills/portals-labs/portals-plugin-claude/portals-game-economy"><img src="https://agentmods.dev/badge/skills/portals-labs/portals-plugin-claude/portals-game-economy.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00106 | $0.01632 |
| Opus 5 | $0.00053 | $0.00816 |
| Sonnet 5 | $0.00021 | $0.00326 |
| Haiku 4.5 | $0.00011 | $0.00163 |
Grade A, and why
portals-game-economy 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 12d 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 — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.
In-game purchases
Portals.economy is how a hosted game sells to its own players. The currency is Coins, which players already hold on Portals; the game never sees a card, a dollar price, or a wallet balance, and it never renders a payment form. Portals owns the confirmation UI and the money.
Read references/portals-game-economy.md for the full API, the catalog fields, every error code, and worked examples.
The catalog is not in the game's code
A game can only sell a SKU that exists in its catalog, authored per game and pinned to a release. purchase("anything_else") cannot invent a product. So the order of work is catalog first, code second:
list_web_games— resolve the game ID when it is not already known.get_game_economy_catalog— read what the game already sells, and itsdraft_revision.update_game_economy_catalog— draft a SKU (upsert), or withdraw one (retire).- Write game code against those exact SKU strings.
test_game_economy_purchase— run it against the owner's simulated wallet.
Portals review approval releases the exact approved draft: from that moment real-Coin purchases work in draft launches — the editor preview and the staging share link — before any publish. Publishing then captures the approved catalog into the immutable live release. Editing the draft closes draft selling until the next approval, and never changes what a live game charges today.
When the user asks to add microtransactions, call these tools yourself; do not send them to My Games for ordinary draft setup. If they did not specify every field, form a small coherent proposal from the requested game design and state the SKU/price/kind/grant/limit assumptions. Confirm a new SKU and its kind before its first upsert because both are permanent catalog identity choices; then perform the catalog writes yourself. Read before every write, preserve all intended fields because upsert replaces the whole product, and carry the returned revision into the next write. A permanent retirement still requires explicit intent.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 12d ago First seen · 84 lines · 106 tokens per session scan A 8239cd3b95df
portals-game-economy is a skill published in the GitHub repository portals-labs/portals-plugin-claude (4 stars, last pushed 3d ago), licensed ISC. It adds 106 tokens to every session and 1,632 once invoked, about $0.0005 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 skills, from other repositories
hz-store-submit
Guides end-to-end Meta Quest and Horizon OS app submission to the Meta Horizon Store — build validation, store-readiness checks, asset preparation, upload, and submission tracking. Use when preparing a Quest app for store publishing.
roblox-gamepasses
Rule-accurate Roblox monetization — game passes, developer products (ProcessReceipt), and subscriptions (GetUserSubscriptionStatusAsync, PromptSubscriptionPurchase). Covers the selling flow, server-authoritative granting on PlayerAdded and purchase completion, PolicyService gating (ArePaidRandomItemsRestricted…
implement-in-app-purchases
Implement, configure, and debug Unity In-App Purchases (IAP) — store connection, product catalog, consumable/non-consumable/subscription purchases, two-step pending-confirm flow, receipt validation, entitlement checking, restore transactions, Apple extensions (promotional purchases, Ask-to-Buy, code redemption), and…
roblox-monetization
Use when implementing Roblox GamePasses, Developer Products, subscriptions, private servers, Creator Rewards, or purchase policy checks.
ai-hive-animation-167-e6ff654
An AI-HIVE workflow for creating original 8-bit pixel-art animation or game-oriented content. It covers characters, settings, storyboards, key frames, animation clips, and checks for visual consistency and originality.
shop-setup
Orchestrator and entry point for building a complete Xsolla Headless Shop — an AI-assembled storefront from Login + Store API + Headless Checkout SDK. START HERE for any request to build a shop end-to-end: it scopes the integration and chains the domain skills — catalog-design, login-setup…