os-clovy: Skill for Claude Code

.agents/skills/browser-test-tauri-fe/SKILL.md

browser-test-tauri-fe is a skill for Claude Code, Codex from open-software-network/os-clovy. It costs 96 tokens per session (2,233 once invoked), scanned A, original, MIT.

A method for testing a Tauri desktop interface or a Vite web interface in Chromium, with Playwright or Chrome DevTools. Tauri is a framework that packages web code as a desktop app; on macOS, this method tests its web frontend separately and fakes its connection to native code.

In plain words
What is it for?
Use it to run interaction tests, capture screenshots, investigate visual issues, and test Tauri frontend behavior through a development web server.
Why use it?
It lets you check clicks, screenshots, and rendering when the desktop window cannot be controlled by browser tools. It also avoids needing a native desktop build for frontend debugging.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents).

This is open-software-network/os-clovy's own configuration. It tells Claude Code and Codex how to work on os-clovy itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything os-clovy configures →

Reuse

Borrowing it

Nothing to install: this file belongs to open-software-network/os-clovy. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/open-software-network/os-clovy/main/.agents/skills/browser-test-tauri-fe/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/open-software-network/os-clovy

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 browser-test-tauri-fe

README.md
[![agentmods](https://agentmods.dev/badge/skills/open-software-network/os-clovy/browser-test-tauri-fe.svg)](https://agentmods.dev/skills/open-software-network/os-clovy/browser-test-tauri-fe)
Your own site
<a href="https://agentmods.dev/skills/open-software-network/os-clovy/browser-test-tauri-fe"><img src="https://agentmods.dev/badge/skills/open-software-network/os-clovy/browser-test-tauri-fe.svg" alt="Measured on agentmods" height="20"></a>
Per session 96 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,233 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00096 $0.02233
Opus 5 $0.00048 $0.01117
Sonnet 5 $0.00019 $0.00447
Haiku 4.5 $0.00010 $0.00223

Measured 6d ago against content hash a608917f10ff, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

browser-test-tauri-fe 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 6d ago.

The scan reads SKILL.md. This mod also ships 2 executable files (screenshot-harness.template.mjs, walkthrough-recorder.template.mjs), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

.agents/skills/browser-test-tauri-fe/SKILL.md · 120 lines

How it starts

The opening of the file, as written. The whole thing — 120 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Browser-testing a Tauri / Vite frontend

Drive a frontend in headless/real Chromium for screenshots, interaction tests, and UI debugging. Two tools, one strategy.

First decision: can you drive the real app?

  • Plain web app / Vite dev server → yes. Point Playwright or Chrome DevTools MCP at the dev URL and go.
  • Tauri app on macOS → NO. The window is WKWebView, which speaks no CDP, and tauri-driver doesn't support macOS. You cannot attach Playwright/DevTools to the real .app window. Instead, run the frontend's Vite dev server (pnpm dev / npm run dev) and drive that in Chromium. The catch: Tauri invoke()/listen() calls have no backend in a plain browser, so you must fake the IPC bridge (below).
  • Tauri on Windows → WebView2 is Chromium; tauri-driver + WebdriverIO works. On Linux, WebKitGTK + tauri-driver.

Faking the Tauri IPC bridge (the key technique)

@tauri-apps/api reads window.__TAURI_INTERNALS__ at load time. Define it before the app module loads and the React/Vue/etc. app can't tell it isn't in a webview — every invoke()/listen() resolves against your fake.

Recipe — a dev-only HTML entry (e.g. app-preview.html) NOT listed in vite.config rollupOptions.input (so it never ships):

<script type="module">
  // 1. install the bridge, 2. THEN import the app (dynamic import guarantees order)
  window.__TAURI_INTERNALS__ = {
    transformCallback(cb) { /* store cb, return id */ },
    unregisterCallback(id) { /* delete */ },
    convertFileSrc(p) { return p; },
    async invoke(cmd, args = {}) {
      switch (cmd) {
        case "plugin:event|listen":   /* register args.handler under args.event; return it */
        case "plugin:event|unlisten": return null;
        /* ...stub each command the app calls at boot, return realistic shapes... */
        default: return null;
      }
    },
  };
  // @tauri-apps/api >= v2.11: listener teardown uses a SEPARATE global.
  window.__TAURI_EVENT_PLUGIN_INTERNALS__ = {
    unregisterListener(event, eventId) { /* drop the handler */ },
  };
  await import("/src/main.tsx");
</script>

Read the full file on GitHub · 120 lines

Files

What ships with it

2 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. 6d ago First seen · 120 lines · 96 tokens per session scan A a608917f10ff

Subscribe to this mod's changes

browser-test-tauri-fe is a skill published in the GitHub repository open-software-network/os-clovy (357 stars, last pushed 5d ago), licensed MIT. It adds 96 tokens to every session and 2,233 once invoked, about $0.0005 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.