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 kelvinkosbab/AppBootstrapAI --skill cross-platform-parity-progit clone --depth 1 https://github.com/kelvinkosbab/AppBootstrapAIWrote 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/kelvinkosbab/appbootstrapai/cross-platform-parity-pro)<a href="https://agentmods.dev/skills/kelvinkosbab/appbootstrapai/cross-platform-parity-pro"><img src="https://agentmods.dev/badge/skills/kelvinkosbab/appbootstrapai/cross-platform-parity-pro/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/kelvinkosbab/appbootstrapai/cross-platform-parity-pro"><img src="https://agentmods.dev/badge/skills/kelvinkosbab/appbootstrapai/cross-platform-parity-pro.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 | $0.00135 | $0.01576 |
| Opus 5.5 | $0.00054 | $0.00630 |
| Sonnet 5.5 | $0.00027 | $0.00315 |
| Haiku 4.5 | $0.00014 | $0.00158 |
Grade A, and why
cross-platform-parity-pro 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 6d 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 — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Help one team ship the same app on Apple platforms and Android with AI agents doing much of the writing. This is the deep companion to the always-on cross-platform-development.md rule — the rule steers day-to-day work; this skill ports features, audits drift, and sets up the repo. Platform-specific correctness is still owned by the platform rules and skills (apple-* / swift-*, android-*); this skill makes the two sides agree.
Pick the mode from the request:
- Port — implement a feature that exists on one platform on the other. Follow
references/porting-workflow.md; translate idioms withreferences/concept-map.md. Write the code directly. - Audit — compare the two codebases for drift. Run the checks in
references/parity-audit.mdand report gaps by severity. - Set up — a new two-platform repo, or an existing pair of apps being brought together: layout, nested
CLAUDE.mdfiles, shared contracts, parity file, per-platform subagents, CI. Usereferences/repo-setup.md; if sharing logic via Kotlin Multiplatform is on the table,references/kmp.md.
If doing a partial task, load only the relevant reference files.
Core Instructions
- Port behavior, not code. Read the reference implementation to learn what it does — states, edge cases, strings, events — then write the target side as a native developer on that platform would. Line-by-line transliteration (Swift class hierarchies in Kotlin, Kotlin
Flowplumbing in Swift) is the most common failure. - The target platform's rules win. A port into Android follows
android-mvvm-architecture.md,android-compose-best-practices.md, and friends; a port into Apple followsapple-swiftui-mvvm.md,apple-swift6-strict-concurrency.md, and friends. Where platform conventions differ (navigation, sheets, back behavior, typography), use the target's. - Same names, mechanically mappable. Types, files, modules, string keys, icon vocabulary entries, analytics events, and flag keys use the same names on both sides (casing per language). Renames are flagged, not silently accepted.
- Shared contracts are generated, not copied. API clients, design tokens, and event APIs come from the shared source; a hand-written duplicate on one side is a finding.
- Specs before ports. If no spec exists for the feature, write
docs/features/<feature>.mdfrom the reference implementation first (states, strings, events, links, accessibility, acceptance checks) — it becomes the checklist for the port and for review. - Verify both sides. Build and run tests on the target platform after a port; after any shared-contract change, regenerate and build both. Say which commands ran and what passed; never claim parity you didn't check.
- Severity by user impact: broken (feature missing or wrong on one platform with no parity note, a contract mismatch that crashes or drops data, untranslated or missing strings, a deep link that opens on one platform only) > drift (renamed concepts, hand-written duplicate DTOs/tokens, differing event names or flag defaults) > polish (naming nits, structure that could mirror more closely).
- Cross-reference, don't duplicate: design-system specifics go to
swift-design-system-pro/android-design-system-pro; Swift concurrency toswift-concurrency-pro; coroutines toandroid-coroutines-pro; Gradle multi-module structure toandroid-gradle-architecture-pro; SPM structure toswift-package-pro.
What ships with it
5 files 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.
- 6d ago First seen · 59 lines · 135 tokens per session scan A 4bb50b69139a
cross-platform-parity-pro is a skill published in the GitHub repository kelvinkosbab/AppBootstrapAI (7 stars, last pushed yesterday), licensed MIT. It adds 135 tokens to every session and 1,576 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 2026-10-11.
Other skills, from other repositories
compose-animations
Use when writing or reviewing Jetpack Compose motion: visibility enter/exit, animating one property toward a target, color or size transitions, multiple properties from one state, switching composable content, or choosing between AnimatedVisibility, animateAsState, rememberTransition, AnimatedContent, and Crossfade.
compose-focus-navigation
Use when writing or reviewing Jetpack Compose UI for TV, keyboard, desktop, accessibility focus, D-pad navigation, FocusRequester, focusProperties, key events, or initial focus behavior.
ios-slim-bindings
Create iOS slim bindings for MAUI. USE FOR: slim iOS binding, Native Library Interop, Swift/Objective-C wrappers, XcodeGen project.yml, Podfile, CocoaPods static linking, BUILDLIBRARYFORDISTRIBUTION, XcodeProject MSBuild, @objc/[Export] selector crashes, async completion handlers. DO NOT USE FOR: Android bindings…
compose-multiplatform
Use when building one shared Compose UI in Kotlin across Android, iOS, and desktop — commonMain @Composables, expect/actual, source-set placement, native interop, multiplatform ViewModel/navigation/Koin. NOT a single-platform native build (that is kotlin-android / swift-ios), and NOT Dart/Flutter cross-platform UI…
kotlin-android
Use when building or fixing a native Android app in Kotlin and Jetpack Compose on the UDF layered architecture — ViewModel/StateFlow, Hilt, Room, Retrofit, coroutines, type-safe Navigation, and the Gradle/AGP surface. NOT shared Android and iOS UI from one Kotlin codebase (that is compose-multiplatform).
claude-android-ninja
Build and migrate Android apps with Kotlin, Jetpack Compose, MVVM, Hilt, Room 3 (KSP, SQLiteDriver, Flow/suspend DAOs), Navigation3, and multi-module Gradle. Use for new projects or modules, Compose screens and ViewModels, Room 3 and RemoteMediator, API 37 / targetSdk migration, Play Integrity client wiring…