Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/roedyrustam/vibes-plugnpx agentmods add skills/roedyrustam/vibes-plug/tauri-expertWrote 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/roedyrustam/vibes-plug/tauri-expert)<a href="https://agentmods.dev/skills/roedyrustam/vibes-plug/tauri-expert"><img src="https://agentmods.dev/badge/skills/roedyrustam/vibes-plug/tauri-expert/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/roedyrustam/vibes-plug/tauri-expert"><img src="https://agentmods.dev/badge/skills/roedyrustam/vibes-plug/tauri-expert.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 | $0.00073 | $0.04006 |
| Opus 5.5 | $0.00029 | $0.01602 |
| Sonnet 5.5 | $0.00015 | $0.00801 |
| Haiku 4.5 | $0.00007 | $0.00401 |
Grade A, and why
tauri-expert 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 2d 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 — 391 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Tauri Expert (Tauri 2.12+ Desktop & Mobile Architecture)
English
Orchestration & Integration
Connects and orchestrates with relevant domain skills:
rust-programming-expert— Writing memory-safe, asynchronous Rust commands, Tokio tasks, and state backends.senior-frontend— Building lightweight React 19 / Vite UI frontends for Tauri.design-system-architect— Desktop UI design systems, custom window titlebars, and native OS theming.ui-ux-pro-max— Desktop window ergonomics, system tray menus, and native keyboard shortcuts.visual-ui-auditor— Multimodal vision auditing of rendered desktop window frames and dialogs.anti-slop— Anti-slop desktop UI craft, zero fake browser window frames and zero placeholder commands.production-ready-hardener— Auditing binary sizes, code signing, and release pipeline hardening.
Description
Production-grade guidance for building cross-platform desktop (Windows 10/11, macOS, Linux) and mobile (iOS 16+, Android 10+) applications using Tauri 2.x (specifically v2.12+). Covers Rust 1.90+ MSRV requirements, tauri::ipc::Channel<T> for ordered bidirectional streaming, on_permission_request programmatic security gates, App-Bound Domain navigation limiting, portable application directory overrides (appDirectoriesOverride), Rust-side convert_file_src, and the fine-grained Capabilities & Permissions system.
Instructions & Best Practices
1. Architecture & Streaming IPC (tauri::ipc::Channel)
- Use
#[tauri::command]for discrete request-response commands. - For streaming long-running jobs (AI token generation, file download progress, database indexing), use
tauri::ipc::Channel<T>passed as a command argument:- Channels deliver messages strictly in order directly to the caller.
- Keeps the global event bus (
emit/listen) uncluttered and avoids global memory leaks.
- For raw binary streams without JSON serialization overhead, send
tauri::ipc::InvokeResponseBody::Raw(Vec<u8>).
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.
- 2d ago Changed · +241 lines · +73 tokens per session d3496998f4d2
- 3d ago Changed · +2 lines · -43 tokens per session 4d559cd7141c
- 5d ago Changed · +44 lines c5be7e65c217
- 6d ago Changed b502c1446f18
- 15d ago Changed d6b24cfff49b
- 20d ago Changed 828a1b52f542
- 21d ago Changed 371bdd2a2a93
- 23d ago Changed · -6 lines · +32 tokens per session d3697db71bb2
- 25d ago Changed · +6 lines · -32 tokens per session 5981fd953e7e
- 1mo ago First seen · 104 lines · 43 tokens per session scan A 886170359fd8
tauri-expert is a skill published in the GitHub repository roedyrustam/vibes-plug (113 stars, last pushed today), licensed MIT. It adds 73 tokens to every session and 4,006 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 2026-09-03.
Other skills, from other repositories
ios-development
Comprehensive iOS app development skill. Use this skill for ANY iOS-related task: writing Swift/SwiftUI/UIKit code, architecting apps, debugging crashes, setting up navigation, networking, data persistence, animations, performance optimization, App Store submission, Xcode configuration. Trigger when user mentions…
swiftui-patterns
SwiftUI architecture patterns, state management with @Observable, view composition, navigation, performance optimization, and modern iOS/macOS UI best practices.
android-clean-architecture
Clean Architecture patterns for Android and Kotlin Multiplatform projects — module structure, dependency rules, UseCases, Repositories, and data layer patterns.
compose-multiplatform-patterns
Compose Multiplatform and Jetpack Compose patterns for KMP projects — state management, navigation, theming, performance, and platform-specific UI.
android-jetpack-compose-expert
Expert guidance for building modern Android UIs with Jetpack Compose, covering state management, navigation, performance, and Material Design 3.
wear-compose-m3
Guidance for Wear OS Compose Material3 (Wear Compose Material 3 / Wear Compose Material3) watch and wearable apps. Covers creating, updating, and migrating projects (Material 2.5 and Horologist migration) using androidx.wear.compose.material3, androidx.wear.compose.foundation, and androidx.wear.compose.navigation3…