Rules

Build a **single TypeScript codebase** that runs interactive apps on **MCP Apps and ChatGPT** via a shared tool + UI model. Optimize for **strict type-safety**, **clean public APIs**, and **backwards-compatible changes** across packages.

_An overview of the current repository and its related projects, generated by [AgentPrimer](https://github.com/deanthecoder/AgentPrimer)._

This project uses **bd (beads)** for issue tracking. Run `bd prime` for workflow context, or install hooks (`bd hooks install`) for auto-injection. For full workflow details: `bd prime`

This document provides guidance for any AI agent working with code in this repository. Agents are expected to contribute to the project effectively and safely, based on the information provided below.

These instructions are for AI assistants working in this project. Always open `@/openspec/AGENTS.md` when the request: Use `@/openspec/AGENTS.md` to learn: Keep this managed block so 'openspec update' can refresh the instructions.

⛔ **STOP**: Do not start any work before choosing a subagent. Do not directly work on the task. No task is too trivial to not use an agent. The project has subagents with clear instructions to handle any task.

**Organization patterns and templates for AI coding agents**

Kanmail is a desktop email client that functions like a kanban board, built with Wails v3 (Go backend + React frontend). It supports Mac, Windows, and Linux.

This document is here to make you generate code that humans will like a little bit more than completely hate it. Some simple rules to follow: Some additional notes: After you finish your task, verify that your code follow the guidelines

OpenCV prints to stderr which corrupts MCP stdio. Always suppress stderr at fd level BEFORE importing cv2 (see `_suppress_opencv_stderr()` in src/optic_mcp/server.py).

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

This is **Finance Guru™** - a private AI-powered family office system built on BMAD-CORE™ v6 architecture. This repository serves as the operational center for a multi-agent financial intelligence system that provides research, quantitative analysis, strategic planning, and compliance oversight.

This document provides guidance for AI agents working with the kube-state-logs codebase.

acon (Atlassian Confluence) is a CLI tool for managing Confluence pages and spaces from the terminal. It provides bidirectional Markdown conversion (Markdown ↔ Confluence storage format), enabling a local-first documentation workflow.

A file for [guiding coding agents](https://agents.md/).

3.2  Validate a New Feature

Current version is 0.1 This document provides critical context for AI agents working on this codebase. Read this file completely before making changes.

1. **Read & Analyze**: Read puzzle description from `data/puzzles/<day>.md` 2. **Add Example Input**: Copy example from puzzle into `data/examples/<day>.txt` 3. **Implement Part 1**: 4. **Test & Submit Part 1**:

AI coding agent instructions for project conventions and guidelines.

This repository is a Go publish/subscribe bus built on PostgreSQL. Use this file to orient automated agents to the build, test, and style conventions used here.

AI coding agent instructions for project conventions and guidelines.

**gian.cool** — Gianfranco's personal blog, a statically generated site.