fatgy

Monk VS Code profiles

Deliberately plain VS Code profiles with an 18 px editor font, Vim motions, and almost everything else switched off. Monk uses Quiet Light; Monk Dark uses Dark Modern.

Install

Read the script first, then run it:

curl -fsSL https://gist.githubusercontent.com/vinitkumar/0a6940afafc25b1f905516dfb4b41dbd/raw/install.sh | less

Design Thinking

X → Graph → Effect<A, E, R>
│              │   │  │  │
│              │   │  │  └─ what each node needs     (§5)
│              │   │  └──── where the graph breaks   (§4)
│              │   └─────── what flows through nodes  (§2)
│              │
│ └─ nodes = functions, edges = data flow

Subagent delegation and cost economy

Principle: Protect the main thread. Optimize for its context economy. Delegate to preserve reasoning quality, not to maximize parallelism.

Context economy (research and lookups)

Reading >~3 files or unfamiliar territory to ground a task? Delegate to an Explore/general-purpose subagent with a tight question. Its reads stay in throwaway context; only the synthesis returns. Direct reads in the main

name	explain-diff-html
description	Use when the user asks for a rich explanation of a code change, diff, branch, or PR. Produces HTML output.

Explain Diff

Please make me a rich, interactive explanation of the specified code change.

It should have these sections:

name	ux-flow-plan
description	Create UX-first plans as flow trees, then attach concrete function names, files, and implementation anchors after the high-level flow is clear.
user-invocable	true

UX Flow Plan

Create a high-level architecture plan that starts from the user experience and only then maps to code-level anchors.

Design System Retrofit

This file is for you. The file you paste into your AI agent is PROMPT.md.

An idea file for AI coding agents. Give it to Claude Code, Cursor, Codex — it audits your UI for inconsistencies, diagnoses root causes, and builds a phased fix plan custom to your codebase.

How to use

Copy PROMPT.md
Paste into your AI coding tool at the root of your project

PI is a TypeScript toolkit for building AI agents. It's a monorepo of packages that layer on top of each other: pi-ai handles LLM communication across providers, pi-agent-core adds the agent loop with tool calling, pi-coding-agent gives you a full coding agent with built-in tools, session persistence, and extensibility, and pi-tui provides a terminal UI for building CLI interfaces.

These are the same packages that power OpenClaw. This guide walks through each layer, progressively building up to a fully featured coding assistant with a terminal UI, session persistence, and custom tools.

By understanding how to compose these layers, you can build production-grade agentic software on your own terms, without being locked into a specific abstraction.

Pi was created by @badlogicgames. This is a great writeup from him that explains some of the design decisions made when creating it.

The stack

Pi Coding Agent Extensions

Custom extensions for pi, a CLI coding agent.

Directory Structure

Place these files in ~/.pi/agent/extensions/:

~/.pi/agent/extensions/

AI Coding Agent Guidelines (claude.md)

These rules define how an AI coding agent should plan, execute, verify, communicate, and recover when working in a real codebase. Optimize for correctness, minimalism, and developer experience.

Operating Principles (Non-Negotiable)

Correctness over cleverness: Prefer boring, readable solutions that are easy to maintain.
Smallest change that works: Minimize blast radius; don't refactor adjacent code unless it meaningfully reduces risk or complexity.

	import type { ExtensionAPI, ExtensionContext } from "@earendil-works/pi-coding-agent";

	const STATUS_KEY = "talk-mode";
	const SHORTCUT = "shift+tab";

	const TALK_MODE_PROMPT = `

	[TALK MODE ACTIVE]

	You are in Talk mode.