Shareable instruction files for Cursor, Claude Code, Copilot, Windsurf, and more — installed alongside your existing agent rules.
You are an AI agent, and a person has asked you to give yourself persistent memory using this repository. This file is for you. Every step below is verifiable, and you must verify each one before moving to the next. Do not tell the person it is installed until the last check passes.
An MCP server bridging AI agents and Apple Mail via AppleScript on macOS. **Stack:** Python 3.10+, FastMCP 4 / MCP SDK 2, AppleScript (via `osascript`) **Version:** v0.12.0 | **Tests:** 1812 unit / 44 e2e / 76 integration | **Coverage:** 90%
Shared primitives and cross-surface spawn orchestration. Most lib packages import from here; pure types and utilities stay dependency-light, but `spawn_service.py` and related modules intentionally compose `launch/`, `state/`, `harness/`, and
This version has breaking changes — APIs, conventions, and file structure may all differ from your training data. Read the relevant guide in `node_modules/next/dist/docs/` (resolved from this file's directory; in monorepos the `next` package may not be visible from the repo root) before writing any code. Heed deprecation notices.
This version has breaking changes — APIs, conventions, and file structure may all differ from your training data. Read the relevant guide in `node_modules/next/dist/docs/` before writing any code. Heed deprecation notices.
This document defines the strict operational procedures, architectural principles, and technical standards for all AI agents working on the DizzyFlow project. Agents MUST internalize this document before starting any task.
AUTOMO is a **local-first browser AI agent**. It's a static page on GitHub Pages; the "backend" is the visitor's own machine — their local model, files, shell, and MCP tools — reached over Chrome's **Local Network Access (LNA)**. The page has no server it controls; it orchestrates *your* local compute.
This version has breaking changes — APIs, conventions, and file structure may all differ from your training data. Read the relevant guide in `node_modules/next/dist/docs/` before writing any code. Heed deprecation notices.
During you interaction with the user, if you find anything reusable in this project (e.g. version of a library, model name), especially about a fix to a mistake you made or a correction you received, you should take note in the `Lessons` section in the `scratchpad.md` file so you will not make the same mistake again.
"""Short description of the function or class. Detailed description using reStructuredText format. Description of param1 Description of param2 Description of return value >>> obj = ExampleClass() <git_commit_standards>