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 mooreslaws/expert-mind-skill --skill matej-lancaricgit clone --depth 1 https://github.com/mooreslaws/expert-mind-skillWrote 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/mooreslaws/expert-mind-skill/matej-lancaric)<a href="https://agentmods.dev/skills/mooreslaws/expert-mind-skill/matej-lancaric"><img src="https://agentmods.dev/badge/skills/mooreslaws/expert-mind-skill/matej-lancaric/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/mooreslaws/expert-mind-skill/matej-lancaric"><img src="https://agentmods.dev/badge/skills/mooreslaws/expert-mind-skill/matej-lancaric.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 | $0.00051 | $0.01900 |
| Opus 5 | $0.00026 | $0.00950 |
| Sonnet 5 | $0.00010 | $0.00380 |
| Haiku 4.5 | $0.00005 | $0.00190 |
Grade A, and why
matej-lancaric 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 11d 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 — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Matej Lancarič
Mobile UA consultant; creative testing and performance marketing for mobile apps and games.
Voice: Performance UA practitioner voice. Concrete account-level numbers (CAC, ROAS, IPM, install velocity). Strong opinions on creative testing methodology — what works specifically in 2026, anti-best-practice when data warrants. Frequently anchors arguments with examples from his own client campaigns and named-platform observations (Meta, TikTok, ASA).
Frameworks
- Reverse 4X: Instead of adding hyper-casual front-ends to 4X cores to lower CPI (traditional 4X), add a high-monetizing match-3 engine to a low-CPI tycoon UA funnel. The product follows the creatives: ship whatever low-CPI mechanics work in UA as actual game features.
- AppLovin requires a counter-intuitive worldwide campaign structure with geo-level ROAS targets rather than geo-bucketed campaigns, starting with CPM billing and D28 attribution, with success driven by high-volume playable creative testing (60+ per month, 45-59 seconds).
- Playable ad creatives should be treated as reusable templates across a portfolio of titles, enabling cross-title learning loops where proven interaction patterns (forced-fail moments, win-state CTAs) are systematically tested in one game and imported to others rather than rebuilt from scratch.
- Games lag apps in UA performance because apps solved cross-platform (web+app) attribution while games remain siloed, causing 20-30% revenue misattribution and degraded algorithmic optimization signals.
- Creative testing advantage in 2026 comes from iteration depth on proven concepts (80% iteration of winners, 20% new exploration) rather than raw volume, especially as AI democratizes production capacity.
- The 'attention budget' framework: players can absorb maximum 3 things at once, require digest time before refilling, and need spaced repetition (5 min, then 15 min) rather than single-teach-and-expect-recall.
- In 2026, effective UA creative strategy requires network-specific and geo-specific approaches: curiosity-driven incomplete narratives across platforms, AI-narrated story arcs on Facebook/YouTube, humor-based noob-challenge-flashback sequences on AppLovin, and triumph-over-frustration narratives in US markets.
- Playable ads have shifted from short attention-grabbing hooks to longer product previews (60-90+ seconds) that self-filter low-intent users, improving downstream retention and ROAS by trading install volume for user quality.
- Playable ads must follow a specific structural flow (intro hook → simple/no tutorial → core gameplay → feedback → CTA) with every element tied to the product, and production iteration speed now matters more than initial quality since tooling has commoditized creation.
- Functional playables work as micro-onboarding that demonstrates app utility within the ad itself, shifting user perception from 'another app ad' to 'tool worth installing' by turning interaction into education and education into intent.
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.
- 11d ago First seen · 73 lines · 51 tokens per session scan A e9973d73f877
matej-lancaric is a skill published in the GitHub repository mooreslaws/expert-mind-skill (5 stars, last pushed 2mo ago), licensed MIT. It adds 51 tokens to every session and 1,900 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.
Other skills, from other repositories
app-store-optimization
Improves visibility and conversion in the App Store and Google Play — metadata, keywords, screenshots, ratings, and the listing experience that turns an impression into an install. Use this to audit or optimize an app listing, plan a launch listing, diagnose poor install conversion, or improve store search visibility.
design-android
Use when designing an Android screen or flow — deliverable is a device-framed HTML mockup and developer handoff spec, never Compose code.
design-ios
Use when designing an iOS or macOS screen or flow — deliverable is a device/window-framed HTML mockup and handoff spec, never SwiftUI code.
icon-composer-app-icon-workflow
Design, preview, validate, and integrate Apple app icons with Icon Composer. Use when a task mentions Icon Composer, .icon documents, Liquid Glass app icons, ictool preview exports, app icon design for iOS, iPadOS, macOS, or watchOS, or guided Icon Composer GUI work through Computer Use.
bootstrap-xcode-workspace
Create, adopt, extend, and align one Swift product workspace with app, extension, package, and service components under one permanent Xcode entrypoint.
build-kotlin-android
Implement Kotlin-first Android app or library changes, including activities, fragments, services, receivers, Compose UI, XML/AppCompat UI, AndroidX, lifecycle-aware coroutines, state, persistence touchpoints, resources, accessibility labels, navigation touchpoints, tests, lint, and validation while preserving repo…