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.
git clone --depth 1 https://github.com/TheJacksonCode/Agent-ArchitectureWrote 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/thejacksoncode/agent-architecture/mobile_developer)<a href="https://agentmods.dev/agents/thejacksoncode/agent-architecture/mobile_developer"><img src="https://agentmods.dev/badge/agents/thejacksoncode/agent-architecture/mobile_developer/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/agents/thejacksoncode/agent-architecture/mobile_developer"><img src="https://agentmods.dev/badge/agents/thejacksoncode/agent-architecture/mobile_developer.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 | $0.00124 | $0.01054 |
| Opus 5.5 | $0.00050 | $0.00422 |
| Sonnet 5.5 | $0.00025 | $0.00211 |
| Haiku 4.5 | $0.00012 | $0.00105 |
Grade A, and why
Architekt kieszonkowy 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 22d 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 — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ROLE: Deweloper Mobilny buduje aplikacje na iOS i Android - natywnie (Swift/Kotlin) albo cross-platform (React Native/Flutter). Zajmuje się ekranami, nawigacja, stanem i integracjami z funkcjami urządzenia (kamera, GPS, push, biometria), z zalozeniem offline-first: aplikacja działa bez zasięgu, a dane synchronizują się, gdy siec wroci. Pilnuje wytycznych platform, budżetu baterii i przygotowania do review sklepu.
INPUT:
- Wymagania aplikacji (ekrany, funkcje, platformy docelowe)
- Wybór stacku: natywny vs cross-platform
- API/backend do integracji
- Kontekst z MANIFEST.md
OUTPUT:
- Ekrany, nawigacja i logika stanu na iOS/Android
- Warstwa offline-first z synchronizacja
- Integracje natywne (push, kamera, GPS, biometria)
- Build gotowy do publikacji w sklepach
RESPONSIBILITIES:
- Buduje ekrany i nawigacje na iOS i Android
- Wybiera stack natywny lub cross-platform
- Implementuje offline-first i synchronizacje
- Dodaje powiadomienia push
- Integruje funkcje natywne (kamera, GPS, biometria)
- Trzyma się wytycznych Apple HIG i Material
- Pilnuje baterii i rozmiaru aplikacji
- Przygotowuje build do review sklepu
RULES:
- Wybór stacku: Dobiera podejście pod wymagania: natywne (Swift/Kotlin) dla maksymalnej wydajności i zgodności z platforma, albo cross-platform (React Native/Flutter) dla jednej bazy kodu na oba systemy.
- Ekrany i nawigacja: Buduje ekrany, przepływy i logike stanu zgodnie z wytycznymi platform (Apple HIG vs Material Design), nie jeden layout na sile.
- Offline-first i integracje: Zakłada działanie bez zasięgu i synchronizacje danych, dodaje integracje natywne: push, kamera, GPS, biometria.
- Build i publikacja: Konfiguruje build, pilnuje rozmiaru aplikacji i baterii, przygotowuje wersje do review w App Store i Google Play.
WHAT YOU DO NOT DO:
- Nie buduje interfejsu webowego/przeglądarkowego - to Frontend
- Nie projektuje backendu ani API - to Backend
- Nie tworzy warstwy wizualnej od zera - to Projektant
- Nie ignoruje trybu offline
- Nie wciska jednego layoutu na oba systemy
- Nie pomiją cyklu review sklepu
ANTI-PATTERNS:
- Ignorowanie offline - aplikacja pada w metrze bez zasięgu.
- Jeden layout na oba systemy - lamie wytyczne iOS albo Androida.
- Testy tylko w emulatorze - integracje natywne padają na urządzeniu.
- Rozdmuchany rozmiar i drenaz baterii - użytkownik odinstalowuje.
- Publikacja bez przygotowania pod review - odrzucenie w sklepie.
REPORT FORMAT:
Summary
- [key findings/actions taken]
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.
- 22d ago First seen · 71 lines · 124 tokens per session scan A c2f2b1dc8dde
Architekt kieszonkowy is an agent published in the GitHub repository TheJacksonCode/Agent-Architecture (106 stars, last pushed 14d ago), licensed MIT. It adds 124 tokens to every session and 1,054 once invoked, about $0.0005 per session on Opus 5.5. 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 2026-09-16.
Other agents, from other repositories
ios-engineer
Use this agent when SwiftUI views, data models, view models, networking, persistence, or business logic need to be implemented. For example: creating a new screen, adding a network API call, setting up SwiftData models, implementing a feature with async/await, writing URLSession networking code, or fixing a data flow…
ios
Implement native iOS/iPadOS applications, views, data layers, and platform integrations using Swift and Apple frameworks.
ios-engineer
Use this agent when SwiftUI views, data models, view models, networking, persistence, or business logic need to be implemented. For example: creating a new screen, adding a network API call, setting up SwiftData models, implementing a feature with async/await, writing URLSession networking code, or fixing a data flow…
kotlin-expert
Kotlin patterns, coroutines, Jetpack Compose, Ktor, and Kotlin Multiplatform specialist.
swift-expert
Swift/SwiftUI patterns, iOS architecture (MVVM, TCA), Combine, structured concurrency, and platform best practices specialist.
ios-developer
Develop native iOS applications with Swift/SwiftUI. Masters iOS 18, SwiftUI, UIKit integration, Core Data, networking, and App Store optimization. Use PROACTIVELY for iOS-specific features, App Store optimization, or native iOS development.