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 joao-aires/agent-skills-public --skill native-client-developmentgit clone --depth 1 https://github.com/joao-aires/agent-skills-publicWrote 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/joao-aires/agent-skills-public/native-client-development)<a href="https://agentmods.dev/skills/joao-aires/agent-skills-public/native-client-development"><img src="https://agentmods.dev/badge/skills/joao-aires/agent-skills-public/native-client-development/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/joao-aires/agent-skills-public/native-client-development"><img src="https://agentmods.dev/badge/skills/joao-aires/agent-skills-public/native-client-development.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 | $0.00052 | $0.00856 |
| Opus 5.5 | $0.00021 | $0.00342 |
| Sonnet 5.5 | $0.00010 | $0.00171 |
| Haiku 4.5 | $0.00005 | $0.00086 |
Grade A, and why
native-client-development 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 yesterday.
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 — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Build native clients
Apply the accepted platform choices
Preserve existing native stacks. For my new applications:
| Target | Starting candidate and conditions |
|---|---|
| Desktop | TypeScript with Tauri and a compatible SPA such as React/Vite. Keep Tauri's Rust shell and dependencies explicit. |
| TypeScript mobile | React Native + Expo when shared code fits the accepted product. Research unsupported native modules before promising parity. |
Consequential framework selection belongs to system design; this skill supplies compatibility evidence and implementation for the selected stack. Read platform selection when selecting or revisiting a framework.
A hosted backend remains a separate service with its accepted stack. Bundle a local sidecar only when an accepted offline/local requirement justifies its packaging, lifecycle and update costs.
Implement the platform experience
Use installed visual design expertise for product-derived visual direction/rendered review and interaction design expertise for behavior; otherwise retain explicit design intent, affected states and actual client verification. Native-client guidance complements these rather than replacing product/UX work.
- For React/Tauri DOM clients, use installed guidance for the accepted frontend stack for compatible shadcn/Tailwind implementation defaults; React Native uses native primitives.
- Reuse domain/API contracts and design tokens where suitable, while implementing platform-appropriate components and navigation. Web shadcn components are not React Native widgets.
- Account for keyboard, touch, safe areas, screen readers, Back/deep links, permission denial and platform lifecycle.
- Keep human drafts across errors and foreground/background transitions.
Define the client/backend boundary
Authenticate on the server and enforce ownership there.
- Store credentials/session material through platform-appropriate secure storage; avoid embedding backend/provider secrets or a production identity bypass.
- Fixture identities require explicit local/test opt-in, production rejection and tests for that boundary.
- Constrain Tauri commands/capabilities, IPC inputs, allowed origins and remote content.
- Use deterministic application authorization for all model-proposed client actions.
What ships with it
2 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.
- yesterday Changed · +28 lines 59a0dd8a9181
- 2d ago Changed · -1 lines 83eaaf224edc
- 5d ago First seen · 34 lines · 52 tokens per session scan A 670f6ae8c30f
native-client-development is a skill published in the GitHub repository joao-aires/agent-skills-public (2 stars, last pushed yesterday), licensed MIT. It adds 52 tokens to every session and 856 once invoked, about $0.0002 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 2026-10-17.
Other skills, from other repositories
orca-emulator-android
Android device and emulator control from inside Orca over adb, with the live device view in Orca's emulator pane. Use when driving an adb-connected emulator or phone on Windows, Linux, or macOS: booting AVDs, taps, swipes, typing, hardware buttons, rotation, app install and launch, runtime permissions, the…
glance-canonical-layouts
Use this skill to create home screen widgets using Jetpack Glance Canonical Layouts from the Android Platform Samples project, or when asked to implement standard widget layout patterns (including Check List, Image Grid, Snap Scrolling, and Standard Toolbar).
android-tombstone-symbolication
Symbolicate the .NET runtime frames in an Android tombstone file. Extracts BuildIds and PC offsets from the native backtrace, downloads debug symbols from the Microsoft symbol server, and runs llvm-symbolizer to produce function names with source file and line numbers. USE FOR triaging a .NET MAUI or Mono Android app…
dogfood
Systematically explore and test a mobile app on iOS/Android with agent-device to find bugs, UX issues, and other problems. Use when asked to dogfood, QA, exploratory test, find issues, bug hunt, or test this app on mobile.
winapp-maui
Package and sign .NET MAUI Windows apps with winapp: publish the Windows head first, then point packaging at the resolved resizetizer manifest. Use for a MAUI MSIX or signed unpackaged build, MAUI packaging in CI, or 'manifest contains unresolved placeholders' errors from winapp package.
apple-search-ads
When the user wants to set up, optimize, or scale Apple Search Ads (ASA) campaigns — including keyword bidding, match types, campaign structure, Creative Product Sets, CPP routing, and ROAS optimization. Use when the user mentions "Apple Search Ads", "ASA", "Search Ads", "Search tab ads", "Today tab ads", "CPT"…