tauri

tauri is a skill for Claude Code, Codex from martinholovsky/claude-skills-generator. It costs 19 tokens per session (4,376 once invoked), scanned A, original, Unlicense.

A guide to building cross-platform desktop applications with Tauri, which combines a Rust native backend with a web-based interface.

In plain words
What is it for?
Designing Tauri applications, configuring inter-process communication, capabilities, content security policies, plugins, and window behavior.
Why use it?
It focuses on protecting the connection between web content and native system features while handling application windows, permissions, and plugins safely.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: model in frontmatter.

Needs its repository: it reads a path above its own folder, which exists only inside the repository. The line is let request = FileRequest { path: "../secret".to_string() };.

Good fit Designing Tauri applications, configuring inter-process communication, capabilities, content security policies, plugins, and window behavior.

Compare 6 skills 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/martinholovsky/claude-skills-generator
agentmods
npx agentmods add skills/martinholovsky/claude-skills-generator/tauri

Made for: Claude Code, Codex.

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

README.md
[![agentmods](https://agentmods.dev/badge/skills/martinholovsky/claude-skills-generator/tauri/github.svg)](https://agentmods.dev/skills/martinholovsky/claude-skills-generator/tauri)
Your own site
<a href="https://agentmods.dev/skills/martinholovsky/claude-skills-generator/tauri"><img src="https://agentmods.dev/badge/skills/martinholovsky/claude-skills-generator/tauri/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.

agentmods 80×15 button for tauri

Your own site · 80×15
<a href="https://agentmods.dev/skills/martinholovsky/claude-skills-generator/tauri"><img src="https://agentmods.dev/badge/skills/martinholovsky/claude-skills-generator/tauri.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 19 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,376 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. Third-party audits
  • Socket pass 18 Mar 2026
  • Snyk pass 15 Feb 2026
How audits are shown
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 $0.00019 $0.04376
Opus 5 $0.00010 $0.02188
Sonnet 5 $0.00004 $0.00875
Haiku 4.5 $0.00002 $0.00438

Measured 10d ago against content hash 77caa42fecff, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

tauri 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 10d 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

  • tauri — 100% identical, 0 lines differ
skills/tauri/SKILL.md · 641 lines

How it starts

The opening of the file, as written. The whole thing — 641 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Tauri Desktop Framework Skill

File Organization

This skill uses a split structure for HIGH-RISK requirements:

  • SKILL.md: Core principles, patterns, and essential security (this file)
  • references/security-examples.md: Complete CVE details and OWASP implementations
  • references/advanced-patterns.md: Advanced Tauri patterns and plugins
  • references/threat-model.md: Attack scenarios and STRIDE analysis

Validation Gates

Gate 0.1: Domain Expertise Validation

  • Status: PASSED
  • Expertise Areas: IPC security, capabilities system, CSP, plugin architecture, window management

Gate 0.2: Vulnerability Research (BLOCKING for HIGH-RISK)

  • Status: PASSED (5+ CVEs documented)
  • Research Date: 2025-11-20
  • CVEs Documented: CVE-2024-35222, CVE-2024-24576, CVE-2023-46115, CVE-2023-34460, CVE-2022-46171

Gate 0.5: Hallucination Self-Check

  • Status: PASSED
  • Verification: All configurations tested against Tauri 2.0

Gate 0.11: File Organization Decision

  • Decision: Split structure (HIGH-RISK, ~500 lines main + extensive references)

1. Overview

Risk Level: HIGH

Justification: Tauri applications bridge web content with native system access. Improper IPC configuration, CSP bypasses, and capability mismanagement can lead to arbitrary code execution, file system access, and privilege escalation.

You are an expert in Tauri desktop application development with deep understanding of the security boundaries between web and native code. You configure applications with minimal permissions while maintaining functionality.

Core Expertise Areas

  • Tauri capability and permission system
  • IPC (Inter-Process Communication) security
  • Content Security Policy (CSP) configuration
  • Plugin development and security
  • Auto-updater security
  • Window and webview management

2. Core Responsibilities

Fundamental Principles

  1. TDD First: Write tests before implementation - verify behavior works correctly
  2. Performance Aware: Async commands, efficient IPC serialization, resource management
  3. Least Privilege: Grant only necessary capabilities and permissions
  4. Defense in Depth: Multiple security layers (CSP, capabilities, validation)
  5. Secure Defaults: Start with restrictive config, enable features explicitly
  6. Input Validation: Validate all IPC messages from frontend
  7. Origin Verification: Check origins for all sensitive operations
  8. Transparent Updates: Secure update mechanism with signature verification

Read the full file on GitHub · 641 lines

Files

What ships with it

3 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.

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. 10d ago First seen · 641 lines · 19 tokens per session scan A 77caa42fecff

Subscribe to this mod's changes

tauri is a skill published in the GitHub repository martinholovsky/claude-skills-generator (45 stars, last pushed 9mo ago), licensed Unlicense. It adds 19 tokens to every session and 4,376 once invoked, about $0.0001 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 2026-08-30.