What is cowork-z CLAUDE.md?

Project instructions for Cowork-Z, a desktop app that gives AI agents a controlled workspace. They document its Rust, React, TypeScript, Node.js, SQLite, and testing setup.

Use them when developing, checking types, running tests, formatting, or building the Cowork-Z desktop app and its Node.js sidecar.

They give the agent the project's architecture, commands, path aliases, and rules so it can make changes that fit the existing codebase.

How kevinlin/cowork-z configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to kevinlin/cowork-z. 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/kevinlin/cowork-z/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/kevinlin/cowork-z

Made for: Claude Code.

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/kevinlin/cowork-z/claude-md/github.svg)](https://agentmods.dev/instructions/kevinlin/cowork-z/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/kevinlin/cowork-z/claude-md"><img src="https://agentmods.dev/badge/instructions/kevinlin/cowork-z/claude-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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/kevinlin/cowork-z/claude-md"><img src="https://agentmods.dev/badge/instructions/kevinlin/cowork-z/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 2,868 This file is loaded in full into every session.

When invoked 2,868 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.02868	$0.02868
Opus 5	$0.01434	$0.01434
Sonnet 5	$0.00574	$0.00574
Haiku 4.5	$0.00287	$0.00287

Measured 10d ago against content hash 73e7a612619c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

cowork-z CLAUDE.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 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.

CLAUDE.md · 151 lines

How it starts

The opening of the file, as written. The whole thing — 151 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

Project Overview

Cowork-Z is a cross-platform Tauri 2.x desktop app that gives autonomous AI agents a sandboxed environment. It drives OpenCode via a Node.js sidecar.

Stack: Tauri 2.x (Rust) + React 19 / TypeScript 5.8 · Radix UI + shadcn/ui · Tailwind 3.4 · Zustand 5 · Vite 7 · pnpm · SQLite (rusqlite) · OS Keychain (keyring)

Path aliases (mirrored in tsconfig.json, vite.config.ts, vitest.config.ts; all three must agree): @ → src/ · @shared → src/shared/ · @sidecar → src-tauri/sidecar-opencode/src/

Commands

pnpm tauri dev                # full stack (builds sidecar binary first, then Vite + Tauri)
pnpm dev                      # frontend only, no Tauri window

pnpm typecheck                # tsc --noEmit
pnpm test --run               # Vitest, single run
pnpm test path/to/file        # single test file
pnpm ultracite:fix            # format + lint

cd src-tauri && cargo check && cargo test
cd src-tauri/sidecar-opencode && pnpm test          # Jest
cd src-tauri/sidecar-opencode && pnpm build:binary  # see package.json for other targets

Rust changes need an app restart; frontend hot-reloads.

Before reporting completion: TypeScript edits → pnpm typecheck. Rust edits → cargo check. Do not claim success until compilation passes.

Three independent test suites. A change to the IPC protocol usually needs all three.

Frontend (Vitest + jsdom): __tests__/ next to the code, *.{test,spec}.{ts,tsx}. src/test/setup.ts mocks matchMedia and ResizeObserver.
Sidecar (Jest) and Rust (cargo test) run from their own directories.

Architecture

Multi-Process Overview

Tauri (Rust) ↔ stdin/stdout JSON-line ↔ Node.js Sidecar ↔ HTTP/SSE ↔ opencode serve
  src-tauri/src/                         src-tauri/sidecar-opencode/
  - sidecar.rs (process mgmt)           - opencode-client.ts (REST)
  - lib.rs (Tauri commands)             - event-stream.ts (SSE)
                                        - session-manager.ts

Read the full file on GitHub · 151 lines

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.

10d ago First seen · 151 lines · 2,868 tokens per session scan A 73e7a612619c

Subscribe to this mod's changes

cowork-z CLAUDE.md is an instructions file published in the GitHub repository kevinlin/cowork-z (13 stars, last pushed 5d ago), licensed MIT. It adds 2,868 tokens to every session, about $0.0143 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.

agent-skills ai-agent desktop-app local-first mcp opencode

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.

vercel/next.js · 7,296 tokens

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.

openai/codex · 5,153 tokens

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).

microsoft/vscode · 6,785 tokens

cowork-z: Instructions file for Claude Code