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 agentmods add skills/vmobifystudio/app-dev-team/architecture-buildernpx skills add vmobifystudio/app-dev-team --skill architecture-buildergit clone --depth 1 https://github.com/vmobifystudio/app-dev-teamWrote 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/vmobifystudio/app-dev-team/architecture-builder)<a href="https://agentmods.dev/skills/vmobifystudio/app-dev-team/architecture-builder"><img src="https://agentmods.dev/badge/skills/vmobifystudio/app-dev-team/architecture-builder.svg" alt="Measured on agentmods" 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 | $0.00046 | $0.00890 |
| Opus 5 | $0.00023 | $0.00445 |
| Sonnet 5 | $0.00009 | $0.00178 |
| Haiku 4.5 | $0.00005 | $0.00089 |
Grade A, and why
architecture-builder 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 today.
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 — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Architecture builder
Produce docs/20-architecture.md and docs/21-engineering-principles.md from docs/00-vision.md + docs/10-prd.md.
docs/20-architecture.md sections
- Platform decision — iOS / Android / both, with order if sequential.
- iOS stack —
- Swift version (latest stable)
- Minimum iOS target — resolve
knowledge/stack-defaults.md's relative rule (flagship = latest major minus one) to a concrete number here, and record how you resolved it - UI: SwiftUI by default; UIKit only if PRD demands something SwiftUI struggles with
- State:
@Observable+@MainActoron ViewModels only (Combine /@Published/ObservableObjectare forbidden —knowledge/ios-conventions.md) - Networking: URLSession + async/await, or a named lib
- Persistence: SwiftData (content apps) or GRDB+SQLite/FTS5 (camera/media) — pick by PRD complexity
- DI: lightweight — protocol + initializer injection
- Testing: Swift Testing (
@Test/@Suite) for unit and domain tests, not XCTest. UI automation stays XCUITest — it is XCTest-based, has no Swift Testing equivalent, andruntime-gateruns it, so a blanket "never XCTest" would ban the suite the release gate expects. Name the snapshot lib. State the coverage floor for the pure-Swift domain engine package (knowledge/stack-defaults.md)
- Android stack —
- Kotlin version
- minSdk / targetSdk (set based on PRD users)
- UI: Jetpack Compose
- Architecture: MVVM or MVI, picked once
- Networking: Retrofit + OkHttp + Kotlinx Serialization (or named alternative)
- Persistence: Room (or named alternative)
- DI: Hilt (flagship) or Koin (utility tier)
- Async: Coroutines + Flow
- Testing: JUnit, Turbine, MockK, Paparazzi (screenshot), Compose UI test
- Shared concerns — auth, analytics, crash reporting, feature flags, remote config, push.
- Backend interface — sketch the APIs the apps need. If backend is in scope, name the service shape.
- Repository layout —
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.
- today First seen · 69 lines · 46 tokens per session scan A 70994a3939a6
architecture-builder is a skill published in the GitHub repository vmobifystudio/app-dev-team (4 stars, last pushed 24d ago), licensed MIT. It adds 46 tokens to every session and 890 once invoked, about $0.0002 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 2026-09-03.
Other skills, from other repositories
execute-task
Implement one task (or a cohesion bundle) from a signed-off spec (Ready or Active): recompute the execution freshness gate, write the verifying test first, implement to green, run the project's full CI with adaptive retry, converge via the configured reviewsequence (default /polish --nested), then open a draft PR…
builder
Detect a project's stack and recommend or apply the universal mechanical quality guards from planwright's core catalog (formatter, linters, type-checker, test runner, secret scan, commit hooks, CI gate), plus the growable breadth dimensions. Escalates stake-bearing decisions (auth, data modeling, security posture…
spec-walkthrough
Render a spec bundle (or a chosen slice) into a plain-language, didactic comprehension artifact a human reads and judges for themselves: an unaided cold read before kickoff, re-orientation mid-execution, or onboarding to a finished or abandoned spec. Standalone and strictly read-only: it renders any status, never…
drain
Run the on-demand drain pass over every spec bundle's Gate deferral entries: evaluate structured GATE(when:) conditions, surface date and free-text gates, report malformed ones, inventory each live bundle's [manual] test-spec entries, and surface the observations log's unmined state. Read-only; nothing is…
cloudx-integrate
Integrate the CloudX SDK into a publisher app on any supported platform (Android, iOS, React Native, Flutter, Unity). Use when asked to integrate, add, install, or set up CloudX, CloudX ads, or CloudX mediation in an app, including alongside or replacing an existing mediation stack such as AppLovin MAX, LevelPlay, or…
review-mobile-pr
Expert Android & iOS PR review. Defaults to saving findings as a PENDING (draft) GitHub review — invisible until manually submitted — but will post them live instead if the user asks or says so when prompted. Use whenever the user asks to review, audit, or give feedback on a pull request touching Android (Kotlin…