Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add kevinlin/cowork-z --skill add-tauri-commandgit clone --depth 1 https://github.com/kevinlin/cowork-zWrote 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/kevinlin/cowork-z/add-tauri-command)<a href="https://agentmods.dev/skills/kevinlin/cowork-z/add-tauri-command"><img src="https://agentmods.dev/badge/skills/kevinlin/cowork-z/add-tauri-command/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/kevinlin/cowork-z/add-tauri-command"><img src="https://agentmods.dev/badge/skills/kevinlin/cowork-z/add-tauri-command.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 | $0.00069 | $0.00986 |
| Opus 5.5 | $0.00028 | $0.00394 |
| Sonnet 5.5 | $0.00014 | $0.00197 |
| Haiku 4.5 | $0.00007 | $0.00099 |
Grade A, and why
add-tauri-command 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 1mo 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.
How it starts
The opening of the file, as written. The whole thing — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Add a Tauri Command
A command is not usable until it exists in four places. Miss one and it fails at runtime, not at build time — generate_handler! takes any path that compiles, and invoke() takes any string.
The four edits
| Order | File | Edit |
|---|---|---|
| 1 | src-tauri/src/commands/<domain>.rs |
the #[tauri::command] fn |
| 2 | src-tauri/src/commands/mod.rs |
pub mod <domain>; — only when the file is new |
| 3 | src-tauri/src/lib.rs |
one line in tauri::generate_handler![], under the matching // Domain comment |
| 4 | src/lib/tauri-api.ts |
the typed invoke() wrapper |
Pick an existing domain file before creating one. There are 22; a new domain is rare.
Step 1 — the command
Copy templates/command.rs. Two shapes: plain, and path-taking.
Any command that accepts a caller-supplied path MUST go through path_guard. The renderer is untrusted — an agent will pass whatever path its model produced. Model it on the validate_path helper at the top of src-tauri/src/commands/files.rs, and validate before any fs:: call, never after.
Return Result<T, String>. T must be Serialize; shared shapes live in src-tauri/src/types.rs.
Step 2 — register
lib.rs groups the handler list by domain with // comments. Add the line to its group, not the end of the list.
Step 3 — the frontend wrapper
Copy templates/wrapper.ts.
Argument names cross the bridge as camelCase in TS, snake_case in Rust — Tauri converts them. invoke('add_workspace', { folderPath }) binds to folder_path: String. Get this wrong and the argument silently arrives empty.
The function name is camelCase; the invoke string is the exact Rust fn name.
New return types go in src/shared/ and must mirror the Rust struct's serde casing (rename_all = "camelCase" on the Rust side).
Step 4 — verify
cd src-tauri && cargo check # Rust compiles
pnpm typecheck # TS compiles
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.
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.
- 1mo ago First seen · 80 lines · 69 tokens per session scan A c31de6177fbe
add-tauri-command is a skill published in the GitHub repository kevinlin/cowork-z (13 stars, last pushed 10d ago), licensed MIT. It adds 69 tokens to every session and 986 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
claude-api
Build apps with the Claude API or Anthropic SDK. TRIGGER when: code imports anthropic/@anthropic-ai/sdk/claudeagentsdk, or user asks to use Claude API, Anthropic SDKs, or Agent SDK. DO NOT TRIGGER when: code imports openai/other AI SDK, general programming, or ML/data-science tasks.
mcp-builder
Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).
web-artifacts-builder
Suite of tools for creating elaborate, multi-component claude.ai HTML artifacts using modern frontend web technologies (React, Tailwind CSS, shadcn/ui). Use for complex artifacts requiring state management, routing, or shadcn/ui components - not for simple single-file HTML/JSX artifacts.
前端代码审查
A review checklist for browser-based front-end and React code. It covers security, accessibility, speed, React correctness, maintainability, and Forsion’s no-build environment rules.
React 组件与状态模式
A collection of patterns for building React components, hooks, and state management, where state means the data that controls what a page shows.
Forsion Connect AI SDK
Build web pages/apps that call Forsion's AI (LLM chat, server-managed agent conversations with web search, image generation) using the signed-in Forsion account — one script tag, no API keys. Use this whenever the user wants a website or HTML page with any AI feature (smart import/parsing, chatbot/assistant, AI…