Borrowing it
Nothing to install: this file belongs to yusufkaraaslan/tote. 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/yusufkaraaslan/tote/main/CLAUDE.mdgit clone --depth 1 https://github.com/yusufkaraaslan/toteWrote 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/yusufkaraaslan/tote/claude-md)<a href="https://agentmods.dev/instructions/yusufkaraaslan/tote/claude-md"><img src="https://agentmods.dev/badge/instructions/yusufkaraaslan/tote/claude-md.svg" alt="Measured on agentmods" 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 | $0.08448 | $0.08448 |
| Opus 5 | $0.04224 | $0.04224 |
| Sonnet 5 | $0.01690 | $0.01690 |
| Haiku 4.5 | $0.00845 | $0.00845 |
Grade A, and why
tote CLAUDE.md scanned grade A with 1 finding 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 today.
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.
Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
- `sshfix.js` — **pure**: shell quoting, every command sent to a remote shell, remote path containment, the tree/stat/probe parsers, and the ssh/Tailscale output detectors. No fs, no child_process, no electron. How it starts
The opening of the file, as written. The whole thing — 89 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.
What this is
Tote is an Electron desktop app: web LLM tabs (Kimi, Claude, ChatGPT, …) + a shared workspace folder pane + docked CLI-agent terminals (Claude Code, Kimi CLI, Codex, …). The organizing idea is spaces: one Global workspace plus project workspaces. The active space is the routing context for everything — web-tab downloads land in <space>/inbox/<provider>/, native-app downloads are bridged into <space>/inbox/_desktop/, and every new terminal spawns with cwd = <space>. A space may also be remote — a project on another machine reached over ssh (typically Tailscale SSH) — and then its files pane, doc panes and agent terminals all run there.
The project was renamed from OmniHub to Tote; migrateFromOmniHub() in main.js moves the old userData folder, renames omnihub-* partition dirs and installer.js upgrades the omnihub-workspace MCP key — keep that migration until users have moved. Plain JavaScript everywhere (CommonJS in main, vanilla browser JS in renderer). No bundler, no TypeScript, no linter. The only tests are npm test → scripts/test-layout.js (the pure tiling engine), scripts/test-scratch.js (temp-space naming, the delete guard, promote, sweep), scripts/test-doc.js (the markdown parser and the extension→kind map), scripts/test-npmfix.js (the wizard's npm-output detectors and prefix-fix guards) and scripts/test-remote.js (remote spaces: shell quoting, the commands sent over ssh, remote path containment, the tree parser, and the ssh/Tailscale output detectors), all dependency-free; everything else is verified by running the app. AGENTS.md and README.md also describe the project, and archlens.model.yaml is a tracked component/method model of src/ — keep all four in sync when changing architecture.
Commands
npm install # postinstall runs scripts/copy-vendor.js: vendors xterm assets + chmod +x node-pty's spawn-helper
npm start # electron .
npm test # test-layout.js (tiling engine, 60) + test-scratch.js (temp spaces, 42) + test-doc.js (markdown, 54) + test-npmfix.js (wizard installs, 20) + test-remote.js (remote spaces, 126)
npm rebuild node-pty # if terminals are disabled ("node-pty unavailable" toast); needs a C++ toolchain
./scripts/install.sh # prereq checks + npm install + npm start
npm run install:mac # test + build + install to /Applications (see below)
npm run pack # electron-builder --dir (unpacked build, fast smoke test)
npm run dist # installer for current platform → dist/
npm run dist:linux | dist:mac | dist:win
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.
- today Changed · +14 lines · +2,867 tokens per session 0bc0b7fed4f3
- 4d ago Changed · +1 lines · +306 tokens per session f790c87267d5
- 8d ago First seen · 74 lines · 5,275 tokens per session scan A ee14d78a1f4c
tote CLAUDE.md is an instructions file published in the GitHub repository yusufkaraaslan/tote (5 stars, last pushed today), licensed MIT. It adds 8,448 tokens to every session, about $0.0422 per session on Opus 5. A static security scan graded it A with 1 finding (runs shell commands). 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.
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.