tauri-v2-expert

tauri-v2-expert is an agent for Claude Code from nodnarbnitram/claude-code-extensions. It costs 79 tokens per session (4,132 once invoked), scanned A, original, MIT.

An expert guide for building Tauri v2 desktop and mobile applications with Rust backends and web frontends. It covers communication between the interface and backend, permissions, and plugins.

In plain words
What is it for?
Use it when building or troubleshooting Tauri commands, events, state, permissions, plugins, or desktop and mobile builds.
Why use it?
It helps developers work through the cross-platform parts of Tauri, including security settings and backend-to-frontend communication.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: names the TodoWrite tool.

Needs its repository: it reads a path above its own folder, which exists only inside the repository. The line is **⚠️ DEPRECATED / LEGACY**: This agent is preserved for backward compatibility but is no longer the primary interface for Tauri v2 work. Use the [`tauri-v2` ski.

Part of the cce-tauri plugin — 1 agent shipped together

Good fit Use it when building or troubleshooting Tauri commands, events, state, permissions, plugins, or desktop and mobile builds.

Compare 6 agents from other repositories ↓
Install

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.

Clone the repo
git clone --depth 1 https://github.com/nodnarbnitram/claude-code-extensions
agentmods
npx agentmods add agents/nodnarbnitram/claude-code-extensions/tauri-v2-expert

Made for: Claude Code.

Or install cce-tauri, the plugin that ships this one along with the rest of its 1 agent.

Wrote 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.

agentmods badge for tauri-v2-expert

README.md
[![agentmods](https://agentmods.dev/badge/agents/nodnarbnitram/claude-code-extensions/tauri-v2-expert.svg)](https://agentmods.dev/agents/nodnarbnitram/claude-code-extensions/tauri-v2-expert)
Your own site
<a href="https://agentmods.dev/agents/nodnarbnitram/claude-code-extensions/tauri-v2-expert"><img src="https://agentmods.dev/badge/agents/nodnarbnitram/claude-code-extensions/tauri-v2-expert.svg" alt="Measured on agentmods" height="20"></a>
Per session 79 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 4,132 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00079 $0.04132
Opus 5 $0.00039 $0.02066
Sonnet 5 $0.00016 $0.00826
Haiku 4.5 $0.00008 $0.00413

Measured 3d ago against content hash 7b23070711c0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

tauri-v2-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 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.

plugins/cce-tauri/agents/tauri-v2-expert.md · 595 lines

How it starts

The opening of the file, as written. The whole thing — 595 lines — stays where its author put it; the contents beside it link to each section on GitHub.

⚠️ DEPRECATED / LEGACY: This agent is preserved for backward compatibility but is no longer the primary interface for Tauri v2 work. Use the tauri-v2 skill instead — it is the actively maintained, layered reference with exhaustive plugin, security, IPC, updater, and runtime coverage.

Purpose

You are a Tauri v2+ expert specializing in building secure, performant cross-platform desktop and mobile applications using Rust backends with web frontends. Your expertise spans the complete Tauri ecosystem including command implementation, IPC patterns, security configuration, plugin development, and deployment across all supported platforms.

Core Expertise Areas

  1. Rust Backend Command Implementation - Type-safe commands with #[tauri::command], async patterns, state management
  2. IPC Patterns - invoke, events, channels for frontend-backend communication
  3. Security Model - Capabilities, permissions, Content Security Policy (CSP), runtime authority
  4. Cross-Platform Deployment - macOS, Windows, Linux, iOS, Android builds and distribution
  5. Plugin Development - Creating and integrating Tauri plugins
  6. Frontend Integration - Vite, React, TanStack Router, and other web frameworks

Instructions

When invoked for Tauri v2+ tasks, follow these steps:

1. Project Analysis

  1. Identify the project structure by locating:

    • src-tauri/ directory (Rust backend)
    • src-tauri/tauri.conf.json (configuration)
    • src-tauri/capabilities/ (security capabilities)
    • Frontend framework (Vite, React, etc.)
  2. Check Tauri version in src-tauri/Cargo.toml:

    [dependencies]
    tauri = { version = "2.x", features = [...] }
    
  3. Review existing commands in src-tauri/src/lib.rs or command modules

2. Command Implementation

When implementing Rust commands:

  1. Define the command with #[tauri::command]:
    #[tauri::command]
    fn my_command(arg: String) -> Result<String, String> {
        Ok(format!("Received: {}", arg))
    }
    

Read the full file on GitHub · 595 lines

Changes

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.

  1. 3d ago First seen · 595 lines · 79 tokens per session scan A 7b23070711c0

Subscribe to this mod's changes

tauri-v2-expert is an agent published in the GitHub repository nodnarbnitram/claude-code-extensions (16 stars, last pushed 4mo ago), licensed MIT. It adds 79 tokens to every session and 4,132 once invoked, about $0.0004 per session on Opus 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.

Related

Other agents, from other repositories

backend_integration_agent

An agent for planning how an iPhone app connects to online services. It covers APIs, login, data synchronization, file transfers, notifications, caching, errors, retries, and development environments.

BingHanOfUESTC/open_agent_team · 48 tokens

network-impl

Network layer implementation specialist. Creates API clients, DTOs, request/response models, and error handling with platform detection. Android: Ktor + kotlinx.serialization. iOS: URLSession + async/await + Codable. KMP: shared Ktor in commonMain.

ahmed3elshaer/everything-claude-code-mobile · 58 tokens

api-integrator

API integration specialist. Implements REST/GraphQL API clients, designs authentication (OAuth, JWT), caching, offline support, and error handling. Optimizes the data flow between server and app.

revfactory/harness-100 · 42 tokens

flutter-backend-specialist

Use this agent when working with APIs, networking, data persistence, backend integration, ServerPod, REST/GraphQL clients, local storage, caching strategies, or implementing the data layer of your Flutter application.

aaronbassett/agent-foundry · 47 tokens

api-designer

Designs the contract between mobile clients and servers. Picks between REST, GraphQL, and gRPC; defines versioning, error envelopes, idempotency, pagination, ETags, and the rules for breaking vs non-breaking changes. Engage at the start of any feature that crosses the network.

cenconq25/claude-code-app-studio · 63 tokens

firebase-specialist

Owns Firebase/Google Cloud usage on mobile: Auth, Firestore, FCM, Remote Config, App Check, Crashlytics, Analytics, and Cloud Functions. Engage when integrating Firebase, when security rules need designing, or when the bill is unexpectedly high.

cenconq25/claude-code-app-studio · 57 tokens