Amit Rawat sahajamit

GitHub Copilot CLI: Agentic & Loop-Engineering Features (vs. Claude Code)

Research note compiled 2026-06-16. Purpose: evaluate whether GitHub Copilot CLI can replace Claude Code for 24/7 autonomous / agentic engineering on a second machine. Every claim below was checked against official GitHub docs, the GitHub changelog, or the github/copilot-cli repo. Claims I could not verify are explicitly flagged.

TL;DR verdict

Copilot CLI has genuinely closed most of the gap with Claude Code on agentic workflows, and in one area (cloud delegation) it does something Claude Code's local /loop cannot: it offloads work to GitHub's servers so your laptop can sleep. The mental model is:

Local autonomous loop → --autopilot (+ --max-autopilot-continues) and --yolo
Local scheduling → /every and /after (experimental)

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.

Prompt for Migrating a Java/Selenium/RestAssured Framework to Playwright/TypeScript

I have a Java-based automation framework using Selenium for UI testing and RestAssured for API testing. The framework's structure and test cases are contained within a directory named [Source Directory Name] at the root level of this project. Please migrate this entire framework to use Playwright with TypeScript for both UI and API testing. The new framework should be placed in a new directory named [Destination Directory Name] at the root level.

The current framework includes:

UI Tests: Implemented using Selenium, likely with a Page Object Model (POM) or similar design pattern. These tests cover various user interactions with the web application.
API Tests: Implemented using RestAssured, covering the testing of RESTful APIs. These tests verify API functionality, data integrity, and response codes.
Test Framework: Likely using JUnit or TestNG for test execution, reporting, and assertion.

You are Claude Dev, a highly skilled software developer with extensive knowledge in many programming languages, frameworks, design patterns, and best practices.

====

CAPABILITIES

You can read and analyze code in various programming languages, and can write clean, efficient, and well-documented code.
You can debug complex issues and providing detailed explanations, offering architectural insights and design patterns.
You have access to tools that let you execute CLI commands on the user's computer, list files in a directory (top level or recursively), extract source code definitions, read and write files, and ask follow-up questions. These tools help you effectively accomplish a wide range of tasks, such as writing code, making edits or improvements to existing files, understanding the current state of a project, performing system operations, and much more.
When the user initially gives you a task, a recursive list of all filepaths in the current working directory ('/Users/amit/Desktop/claude-dev')

	{
	"model": "qwen3:8b",
	"temperature": 0,
	"user": "google-oauth2\|user_",
	"messages": [
	{
	"role": "system",
	"content": "You are an AI coding assistant, powered by qwen3:8b. You operate in Cursor.\n\nYou are pair programming with a USER to solve their coding task. Each time the USER sends a message, we may automatically attach some information about their current state, such as what files they have open, where their cursor is, recently viewed files, edit history in their session so far, linter errors, and more. This information may or may not be relevant to the coding task, it is up for you to decide.\n\nYour main goal is to follow the USER's instructions at each message, denoted by the <user_query> tag.\n\n<communication>\nWhen using markdown in assistant messages, use backticks to format file, directory, function, and class names. Use \\( and \\) for inline math, \\[ and \\] for block math.\n</communication>\n\n\n<tool_calling>\nYou have tools at your disposal to

	FROM centos:centos7
	ARG JAVA_VERSION="1.8.0"
	LABEL maintainer="sahajamit@gmail.com"
	WORKDIR /app
	RUN chmod 666 /etc/passwd && chown root:root /etc/passwd
	RUN yum install -y java-$JAVA_VERSION-openjdk-devel unzip && mkdir -p /opt/lib

	package main

	import (
	"context"
	"flag"
	"fmt"
	"math/rand"
	"os"
	"time"

	https://github.com/kubernetes/client-go/blob/master/examples/out-of-cluster-client-configuration/main.go

	https://github.com/kubernetes/client-go/blob/master/tools/clientcmd/client_config.go

	https://github.com/kubernetes/client-go/tree/master/examples/create-update-delete-deployment

	https://stackoverflow.com/questions/53891862/patching-deployments-via-kubernetes-client-go

	https://stackoverflow.com/questions/32554893/how-can-i-create-a-simple-client-app-with-the-kubernetes-go-library

	apiVersion: v1
	kind: Pod
	metadata:
	name: demo-pod
	spec:
	containers:
	- name: busybox-demo
	image: busybox
	args:
	[

	Highcharts.chart('container', {
	chart: {
	type: 'columnrange',
	inverted: true
	},
	title: {
	text: 'Different MicroServices Timings in a Waterfall Chart'
	},
	subtitle: {
	text: 'Time taken by each microservice'