Borrowing it
Nothing to install: this file belongs to Radek44/mcp-tauri-automation. 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/Radek44/mcp-tauri-automation/main/AGENTS.mdgit clone --depth 1 https://github.com/Radek44/mcp-tauri-automationWrote 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/instructions/radek44/mcp-tauri-automation/agents-md)<a href="https://agentmods.dev/instructions/radek44/mcp-tauri-automation/agents-md"><img src="https://agentmods.dev/badge/instructions/radek44/mcp-tauri-automation/agents-md/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/instructions/radek44/mcp-tauri-automation/agents-md"><img src="https://agentmods.dev/badge/instructions/radek44/mcp-tauri-automation/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00594 | $0.00594 |
| Opus 5 | $0.00297 | $0.00297 |
| Sonnet 5 | $0.00119 | $0.00119 |
| Haiku 4.5 | $0.00059 | $0.00059 |
Grade A, and why
mcp-tauri-automation AGENTS.md 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 — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MCP Tauri Automation
Mission
This repository provides a stdio MCP server for launching and automating built
Tauri desktop applications through tauri-driver and WebDriver. Keep the MCP
protocol surface predictable, failures actionable, and platform behavior
portable across supported desktop environments.
Layout
src/index.ts— stdio entry point, configuration, and shutdown.src/server.ts— validated MCP tool schemas, bounded queue, and dispatch.src/tauri-driver.ts— WebDriver session and Tauri process lifecycle.src/ui-snapshot.ts— fixed, read-only, bounded DOM diagnostic.test/— Node tests with local fake WebDriver servers and real MCP transports.src/types.ts— shared configuration, parameter, state, and response types.dist/— generated TypeScript output; never edit or commit it.
Verification
npm ci
npm run verify
The full gate builds, tests, audits runtime dependencies, and dry-runs packaging. Use targeted tests while iterating and run the full gate on final source before publication. Native smoke requires a built Tauri test app and either embedded WebDriver or tauri-driver. Report unavailable native platforms as untested. Create sessions only on loopback, serialize calls, never automatically replay mutations, and delete only sessions owned by this server. Embedded app processes remain owned by their launcher. Keep snapshots bounded and omit form values.
Model Routing
- Use hosted subscription roles only:
opusfor architecture or MCP contract changes,sonnetfor ordinary implementation, andhaikufor bounded mechanical work. - Do not use local LLMs for repository work. Do not delegate generic work to DGX Spark; Spark is not a cheap or default agent lane.
- Native subagents inherit the current model unless a delegation receipt proves a different hosted profile. Never claim a lower-tier route from prose alone.
Boundaries
- Preserve stdio for MCP protocol messages; diagnostics must not corrupt the protocol stream.
- Validate untrusted tool inputs and return structured errors. Do not expose credentials, environment values, arbitrary local files, or auth state.
- Keep process and WebDriver cleanup reliable on normal exit and signals.
- Do not edit generated
dist/, dependency contents, or lockfile data by hand. - Screenshots and other runtime output remain local and ignored.
- Changes to tool names, schemas, response shapes, environment variables, or process lifecycle are public-contract changes and require explicit review.
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 · +2 lines · +53 tokens per session 2a473ca81b32
- 9d ago First seen · 61 lines · 541 tokens per session scan A 8283c136aace
mcp-tauri-automation AGENTS.md is an instructions file published in the GitHub repository Radek44/mcp-tauri-automation (7 stars, last pushed yesterday), licensed MIT. It adds 594 tokens to every session, about $0.0030 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 2026-08-31.
Other instructions, from other repositories
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.