Borrowing it
Nothing to install: this file belongs to webdriverio/desktop-mobile. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/webdriverio/desktop-mobile/main/.claude/skills/add-native-service/SKILL.mdgit clone --depth 1 https://github.com/webdriverio/desktop-mobileWrote 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/webdriverio/desktop-mobile/add-native-service)<a href="https://agentmods.dev/skills/webdriverio/desktop-mobile/add-native-service"><img src="https://agentmods.dev/badge/skills/webdriverio/desktop-mobile/add-native-service/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/webdriverio/desktop-mobile/add-native-service"><img src="https://agentmods.dev/badge/skills/webdriverio/desktop-mobile/add-native-service.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- 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 | $0.00153 | $0.16899 |
| Opus 5.5 | $0.00061 | $0.06760 |
| Sonnet 5.5 | $0.00031 | $0.03380 |
| Haiku 4.5 | $0.00015 | $0.01690 |
Grade A, and why
add-native-service 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 3d 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 — 492 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Add Native Service
A runbook for bootstrapping a new WebdriverIO service package in this monorepo. It abstracts over the architectures already shipped here so the same process can ship any of them:
Desktop:
- Electron (
@wdio/electron-service) — CDP attach, no driver process, no Rust. - Tauri (
@wdio/tauri-service) — Wry webview, external WebDriver driver + Tauri plugin crate. - Dioxus (
@wdio/dioxus-service) — Wry webview, in-process embedded WebDriver server + bridge crate.
Mobile:
- React Native (
@wdio/react-native-service) — Appium-driven native UI (UiAutomator2/XCUITest);execute/mockover a Hermes/Metro JS-realm CDP channel. No driver process, no Rust.
If you follow this skill against any of those frameworks you should land in the same place the shipped package already is, and the same process bootstraps the next framework. See ROADMAP.md for what's planned (Flutter and Capacitor are the next mobile frameworks).
The single most important step is Step 0: identify which integration archetype your framework falls into — first desktop or mobile, then the axis within. It decides whether Phase 2 builds Rust crates, attaches over CDP, forks a driver, or composes with Appium — and which existing service you clone.
Scope: this skill covers desktop (CDP, Wry/WebDriver) and mobile (Appium) frameworks. Mobile is a third transport family with patterns desktop has no analogue for — device-pool allocation, Appium capability mutation, contexts-as-windows, a per-platform E2E split — all captured in plumbing-mobile.md and flagged inline below.
When to use
- A new desktop or mobile framework (e.g. Flutter, Capacitor) is being added per
ROADMAP.md. - An existing pre-1.0 service is being promoted from a Phase 0 spike to its first MVP package.
- You're validating that a framework can be automated before committing to a service implementation.
- You're refactoring one of the shipped services and want to keep it aligned with the shared pattern.
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.
- 3d ago Changed 7db23ff21e68
- 4d ago Changed 3e0ae678fb2f
- 5d ago Changed · +1 lines ea9c5e03a659
- 6d ago Changed 69751ee3d700
- 8d ago Changed bfff81db9164
- 25d ago Changed · +1 lines 848ee337a95d
- 2mo ago First seen · 490 lines · 153 tokens per session scan A 52ad5a7f8503
add-native-service is a skill published in the GitHub repository webdriverio/desktop-mobile (20 stars, last pushed today), licensed MIT. It adds 153 tokens to every session and 16,899 once invoked, about $0.0006 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
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…
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.
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.
test-warp-ui
Guides testing Warp UI features and changes using the computer use tool. Use this skill only when computer-use testing was requested (explicit request or accepted offer) and the computeruse tool is available to the agent. Covers launching Warp and verifying UI behavior.