Native SDK is a toolkit for building desktop applications with native rendering instead of a browser, WebView, or JavaScript runtime bundled into the application. Developers author interfaces in `.native` markup and write application logic in TypeScript or Zig, which the toolkit compiles and renders in real operating-system windows. The catalogue entries provide skills and instructions for working with Native SDK.
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 vercel-labs/native --skill automationgit clone --depth 1 https://github.com/vercel-labs/nativeWrote 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/vercel-labs/native/automation)<a href="https://agentmods.dev/skills/vercel-labs/native/automation"><img src="https://agentmods.dev/badge/skills/vercel-labs/native/automation/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/vercel-labs/native/automation"><img src="https://agentmods.dev/badge/skills/vercel-labs/native/automation.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Snyk pass
- NVIDIA SkillSpector pass
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 | $0.00069 | $0.04141 |
| Opus 5.5 | $0.00028 | $0.01656 |
| Sonnet 5.5 | $0.00014 | $0.00828 |
| Haiku 4.5 | $0.00007 | $0.00414 |
Grade A, and why
automation 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 1mo 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 — 253 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Automate Native SDK apps
Every Native SDK app embeds an automation server — native-rendered apps and WebView-shell apps alike. It works through file-based IPC in .zig-cache/native-sdk-automation/ and is intended for smoke tests, CI checks with a GUI session, and quick runtime inspection: accessibility snapshots, widget driving through the real input paths, deterministic reference-renderer screenshots, readiness/state assertions, and bridge round-trips.
Automation is not browser DOM automation. It reports runtime/window/widget state, drives retained-canvas widgets, and can ask the runtime to reload or dispatch bridge requests. For DOM testing of the optional WebView path, use the frontend framework's tests or a browser automation tool against the dev server.
What automation can verify
- An automation-enabled app started and published
ready=true. - The runtime loaded the expected app name, source kind, and window metadata.
- The main window exists and is focused/open.
- The JavaScript-to-Zig bridge can round-trip a request through
native automate bridge. - Builtin window/WebView commands work when exercised by a smoke test.
- Reload requests are accepted by the runtime.
- Real pixels of retained-canvas (
gpu_surface) views:native automate screenshot <view-label>renders the view's current canvas frame through the deterministic CPU reference renderer and writes a PNG artifact. Two captures of an unchanged scene are byte-identical, so screenshots can back golden-image or "did the UI change" checks.
What automation cannot verify
- Screenshots of WebView content.
screenshotcoversgpu_surfacecanvas views only; there is no DOM/WebView pixel capture. - Arbitrary DOM queries and clicks.
- Browser network assertions.
Prerequisites
Build/run an app with automation enabled. Generated examples usually expose -Dautomation=true:
zig build run -Dplatform=macos -Dautomation=true
Repository examples may have specialized steps:
zig build run-webview -Dplatform=macos -Dautomation=true
zig build test-webview-smoke -Dplatform=macos
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.
- 1mo ago First seen · 253 lines · 69 tokens per session scan A 8274dbc992fc
automation is a skill published in the GitHub repository vercel-labs/native (7,804 stars, last pushed yesterday), licensed Apache-2.0. It adds 69 tokens to every session and 4,141 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
eval-dataset-design
A guide to creating reliable test sets for AI agents. Each evaluation task includes the request, the simulated user's behaviour, a reset starting state, and a success check that can be independently verified.
verify-omnigent
Drive Omnigent the way a user does and prove a behavior with recorded evidence, using an isolated server, runner, and mock model plus a feature map of every user entry point. Load before reproducing a user-facing bug, before claiming a fix works, or when reviewing whether a change covered every surface (session vs.…
test-master
Generates test files, creates mocking strategies, analyzes code coverage, designs test architectures, and produces test plans and defect reports across functional, performance, and security testing disciplines. Use when writing unit tests, integration tests, or E2E tests; creating test strategies or automation…
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.
cua-driver
Use Cua Driver for desktop or browser tasks that are awkward or unavailable through Bash/APIs, or when the user explicitly wants GUI interaction: app testing, visual bug reproduction, form filling, calendar entry, screenshots, and demo recording. Also covers Cua setup; not OpenAI Codex Computer Use or web research.
critique
Adversarial design critique of the current work — render it, look at it, and argue for rejection. Run after the gates are green, never instead of them.