Borrowing it
Nothing to install: this file belongs to xiaolai/vmark. 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/xiaolai/vmark/main/.claude/skills/tauri-mcp-testing/SKILL.mdgit clone --depth 1 https://github.com/xiaolai/vmarkWrote 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/xiaolai/vmark/tauri-mcp-testing)<a href="https://agentmods.dev/skills/xiaolai/vmark/tauri-mcp-testing"><img src="https://agentmods.dev/badge/skills/xiaolai/vmark/tauri-mcp-testing/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/xiaolai/vmark/tauri-mcp-testing"><img src="https://agentmods.dev/badge/skills/xiaolai/vmark/tauri-mcp-testing.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 | $0.00077 | $0.03086 |
| Opus 5.5 | $0.00031 | $0.01234 |
| Sonnet 5.5 | $0.00015 | $0.00617 |
| Haiku 4.5 | $0.00008 | $0.00309 |
Grade A, and why
tauri-mcp-testing 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 yesterday.
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 — 409 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Tauri MCP E2E Testing (VMark)
CRITICAL: VMark is a Tauri app. Drive it with the Tauri MCP tools
(mcp__tauri__driver_session, mcp__tauri__webview_screenshot, …; this skill
writes them without the mcp__tauri__ prefix). NEVER use Chrome DevTools MCP.
Which server tests what
| What is under test | Drive it through |
|---|---|
| Non-AI UI and plumbing: tabs, modes, toolbar, settings, save, find bar | Tauri MCP (127.0.0.1:9323, debug builds only) |
| AI features and anything an MCP client does | VMark MCP (mcp__vmark__session, document, selection, workspace, workflow, browser, browser_read, coherence) |
pnpm tauri:dev runs as app.vmark.dev, with its own settings and mcp-port;
point a VMark MCP client at it with VMARK_APP_IDENTIFIER=app.vmark.dev. The
VMark MCP port is dynamic (read from mcp-port). The scripted journeys
(pnpm e2e:journeys) and their guide are in e2e/README.md.
Running a flow
- Confirm
pnpm tauri:devis running; if not, ask the user to start it. driver_session({ action: 'start', port: 9323 }), thenmanage_window({ action: 'list' })and pick the target window.- Run the flow. VMark MCP calls:
session.get_stateto orient,document.readbeforedocument.write(passrevisionback asexpected_revision),selection.get/selection.setfor targeted edits. - Verify with a screenshot,
webview_find_elementordocument.read; readread_logson failure. Stop the session when done. - Report each flow as passed or failed, with errors and repro steps.
Common flows: app startup (main window visible); open recent and open from the picker; WYSIWYG ↔ Source toggle (F7); format toolbar (Ctrl+E); change a setting and confirm it persists; edit, save, and confirm the dirty flag clears.
Quick Reference
| Task | MCP Tool |
|---|---|
| Connect to app | driver_session |
| Take screenshot | webview_screenshot |
| Find elements | webview_find_element |
| Click/scroll/swipe | webview_interact |
| Type text | webview_keyboard |
| Wait for element | webview_wait_for |
| Execute JS | webview_execute_js |
| Get CSS styles | webview_execute_js with getComputedStyle |
| Test IPC commands | ipc_execute_command |
| Monitor IPC calls | ipc_monitor |
| Read console logs | read_logs |
| Manage windows | manage_window |
What ships with it
4 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.
- yesterday Changed · +22 lines · +15 tokens per session cf6f59822661
- 2mo ago First seen · 387 lines · 62 tokens per session scan A a7848ee85875
tauri-mcp-testing is a skill published in the GitHub repository xiaolai/vmark (878 stars, last pushed yesterday), licensed ISC. It adds 77 tokens to every session and 3,086 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 2026-08-30.
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.
critique
Adversarial design critique of the current work. Render it, look at it, and argue for rejection. Run after the gates are green, never instead of them.