Cate is an infinite, zoomable coding workspace that combines terminals, editors, and browsers while showing the status of multiple coding agents. It is for developers who run Claude Code, Codex, or other agent command-line tools in parallel and organize their branches with separate Git worktrees. The catalogue add-ons provide skills, agents, and instructions for using Cate.
Borrowing it
Nothing to install: this file belongs to 0-AI-UG/cate. 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/0-AI-UG/cate/main/AGENTS.mdgit clone --depth 1 https://github.com/0-AI-UG/cateWrote 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/0-ai-ug/cate/agents-md)<a href="https://agentmods.dev/instructions/0-ai-ug/cate/agents-md"><img src="https://agentmods.dev/badge/instructions/0-ai-ug/cate/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/0-ai-ug/cate/agents-md"><img src="https://agentmods.dev/badge/instructions/0-ai-ug/cate/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 | $0.03431 | $0.03431 |
| Opus 5.5 | $0.01372 | $0.01372 |
| Sonnet 5.5 | $0.00686 | $0.00686 |
| Haiku 4.5 | $0.00343 | $0.00343 |
Grade A, and why
cate 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 11d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- cate CLAUDE.md — 89% identical, 145 lines differ
How it starts
The opening of the file, as written. The whole thing — 259 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
This file provides guidance to Codex (Codex.ai/code) when working with code in this repository.
Before You Code
Read and follow the karpathy-guidelines skill (.Codex/skills/karpathy-guidelines) when writing, reviewing, or refactoring code here — surface assumptions, make surgical changes, keep it simple, and define verifiable success criteria.
Project Overview
Cate is a desktop application that provides an infinite zoomable canvas where terminal, editor, browser and review panels float spatially (similar to Figma/Miro, but for coding), next to classic docked layouts. Built with Electron + React + TypeScript, styled with Tailwind CSS.
Each open workspace is served by its own runtime daemon, which holds the
workspace's state and does all its work (files, git, terminals, agents,
the cate API). The desktop app is a client of those runtimes; other devices
(and later a phone) connect to the same runtime after pairing, and every
client sees one live workspace.
docs/architecture.md is the model: what every module is, where it lives,
what it owns and how the pieces talk. Read the sections for the area you touch
before changing it. Where the code disagrees with the document, the document
wins.
Build System
The Electron app lives at the project root. It uses electron-vite for the desktop shell and esbuild for the daemon and the CLI.
npm install # install dependencies
npm run dev # bundle the daemon, then start the app with hot reload
npm run build # production build of the desktop shell
npm run build:runtime # bundle the daemon to dist-runtime/runtime.cjs
npm run runtime:tarball # build the runtime tarball (daemon, Node, cate CLI, skills)
npm run typecheck # tsc --noEmit
npm run lint # eslint
npm run lint:deps # dependency-cruiser: layer, side and entry rules
npm test # vitest suite
npm run test:e2e # playwright e2e suite (e2e/)
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.
- 11d ago Changed · +122 lines · +1,681 tokens per session d9f2cec7d870
- 1mo ago Changed · -1 lines · -5 tokens per session fe34a1803edc
- 1mo ago Changed · +27 lines · +376 tokens per session 44cf11dfe9f9
- 1mo ago Changed · +2 tokens per session c9272f82c2f1
- 1mo ago Changed · -3 lines · -59 tokens per session 87e1faf6e9e0
- 2mo ago First seen · 114 lines · 1,436 tokens per session scan A ed0d1ca77d50
cate AGENTS.md is an instructions file published in the GitHub repository 0-AI-UG/cate (2,212 stars, last pushed yesterday), licensed MIT. It adds 3,431 tokens to every session, about $0.0137 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 instructions, from other repositories
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).
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.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
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.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
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.