Shawn Cicoria cicorias

Install Cache Break Notifier

Install this plugin directly from its GitHub Gist:

copilot plugin install https://gist.github.com/burkeholland/647ad0e579c06a43346ce6a373261eba.git

Start Copilot CLI to load the plugin:

LLM Wiki

A pattern for building personal knowledge bases using LLMs.

This is an idea file, it is designed to be copy pasted to your own LLM Agent (e.g. OpenAI Codex, Claude Code, OpenCode / Pi, or etc.). Its goal is to communicate the high level idea, but your agent will build out the specifics in collaboration with you.

The core idea

Most people's experience with LLMs and documents looks like RAG: you upload a collection of files, the LLM retrieves relevant chunks at query time, and generates an answer. This works, but the LLM is rediscovering knowledge from scratch on every question. There's no accumulation. Ask a subtle question that requires synthesizing five documents, and the LLM has to find and piece together the relevant fragments every time. Nothing is built up. NotebookLM, ChatGPT file uploads, and most RAG systems work this way.

quick guide to improve and make faster your Claude Code file suggestion

from https://x.com/thayto_dev/status/2009401734213554494?s=43

before all you have to install ripgrep, jq, fzf

Add this to your ~/.claude/settings.json

"fileSuggestion": {
    "type": "command",

⠀⠀⠀⠀⠀⠀⣀⣤⣶⡶⢛⠟⡿⠻⢻⢿⢶⢦⣄⡀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀
⠀⠀⠀⢀⣠⡾⡫⢊⠌⡐⢡⠊⢰⠁⡎⠘⡄⢢⠙⡛⡷⢤⡀⠀⠀⠀⠀⠀⠀⠀
⠀⠀⢠⢪⢋⡞⢠⠃⡜⠀⠎⠀⠉⠀⠃⠀⠃⠀⠃⠙⠘⠊⢻⠦⠀⠀⠀⠀⠀⠀
⠀⠀⢇⡇⡜⠀⠜⠀⠁⠀⢀⠔⠉⠉⠑⠄⠀⠀⡰⠊⠉⠑⡄⡇⠀⠀⠀⠀⠀⠀
⠀⠀⡸⠧⠄⠀⠀⠀⠀⠀⠘⡀⠾⠀⠀⣸⠀⠀⢧⠀⠛⠀⠌⡇⠀⠀⠀⠀⠀⠀
⠀⠘⡇⠀⠀⠀⠀⠀⠀⠀⠀⠙⠒⠒⠚⠁⠈⠉⠲⡍⠒⠈⠀⡇⠀⠀⠀⠀⠀⠀
⠀⠀⠈⠲⣆⠀⠀⠀⠀⠀⠀⠀⠀⣠⠖⠉⡹⠤⠶⠁⠀⠀⠀⠈⢦⠀⠀⠀⠀⠀
⠀⠀⠀⠀⠈⣦⡀⠀⠀⠀⠀⠧⣴⠁⠀⠘⠓⢲⣄⣀⣀⣀⡤⠔⠃⠀⠀⠀⠀⠀
⠀⠀⠀⠀⣜⠀⠈⠓⠦⢄⣀⣀⣸⠀⠀⠀⠀⠁⢈⢇⣼⡁⠀⠀⠀⠀⠀⠀⠀⠀

	// cache-drop-notifier
	//
	// In one line: every turn this tells you how many tokens were reused from the prompt
	// cache, and warns you when that number suddenly collapses.
	//
	// Why it matters: every time you send a message, Copilot re-sends your entire
	// conversation plus a large block of setup text (its instructions, every tool
	// definition, your enabled skills, and so on). That is tens of thousands of tokens
	// before you have typed a word. The model provider caches the front of that payload
	// so it does not reprocess it each turn. You keep that discount only while the front

	"""
	The most atomic way to train and inference a GPT in pure, dependency-free Python.
	This file is the complete algorithm.
	Everything else is just efficiency.

	@karpathy
	"""

	import os # os.path.exists
	import math # math.log, math.exp

	#!/bin/bash

	# Script to fetch and pull git repositories listed in gitrepos.txt
	# Usage: ./git-pull-all.sh [path-to-gitrepos.txt]

	REPO_FILE="${1:-gitrepos.txt}"
	BASE_DIR="$(pwd)"

	# Check if the repo file exists
	if [[ ! -f "$REPO_FILE" ]]; then

	#!/usr/bin/env bash

	# use this after a 'yay -S aur/visual-studio-code-bin' on omarchy / arch linux
	# add to /etc/pacman.conf a "IgnorePkg = visual-studio-code-bin" as wel

	set -euo pipefail

	PKG="visual-studio-code-bin"

	current_ver() {

	LOCATION=westus3
	WORKLOAD_PROFILE_TYPE="Consumption-GPU-NC24-A100"
	WORKLOAD_PROFILE_NAME="nc24-a100-profile"

Shawn Cicoria cicorias

Install Cache Break Notifier

LLM Wiki

The core idea

🧩 Some Agentic Patterns Places