Marian Ignev mignev

The Autonomous Agent Prompting Framework

This repository contains a disciplined, evidence-first prompting framework designed to elevate an Agentic AI from a simple command executor to an Autonomous Principal Engineer.

The philosophy is simple: Autonomy through discipline. Trust through verification.

This framework is not just a collection of prompts; it is a complete operational system for managing AI agents. It enforces a rigorous workflow of reconnaissance, planning, safe execution, and self-improvement, ensuring every action the agent takes is deliberate, verifiable, and aligned with senior engineering best practices.

I also have Claude Code prompting for your reference: https://gist.github.com/aashari/1c38e8c7766b5ba81c3a0d4d124a2f58

Golang Workers / Job Queue

A running example of the code from:

This gist creates a working example from blog post, and a alternate example using simple worker pool.

TLDR: if you want simple and controlled concurrency use a worker pool.

A few show tricks to find slow queries in mongodb

Enable profiling

First, you have to enable profiling

> db.setProfilingLevel(1)

Now let it run for a while. It collects the slow queries ( > 100ms) into a capped collections, so queries go in and if it's full, old queries go out, so don't be surprised that it's a moving target...

Smoke tests for the vault snap

(based on https://www.vaultproject.io/intro/index.html)

First, build and install the vault snap:

git clone https://github.com/elopio/vault
cd vault
git checkout snapcraft
sudo apt install snapcraft
snapcraft

Който се чувства комфортно да говори на езици като:

JavaScript (Client /React, Angular/ & Server side (Node))
Go (Docker, Kubernetes, Microservices)

Обича да си цапа ръцете със сървъри и се забавлява на тази картинка: https://scontent-frt3-1.xx.fbcdn.net/…/12605387_12291098337…

Да ми пише на лично или на мейл: [email protected] / [email protected]

Ние ... по въпросите ще го познаем :)))

Front-end Gagu

MediaHub си търси frontend човек за офиса си в София. Фокусът на компанията е разработка и интеграция на решения за разпространение и визуализиране на видео съдържание.

Много важно!

От особенна важност за позицията е добро познаване по: JavaScript, HTML5 и CSS3.

Ще се радваме ако:

В допълнение познаването на следните продукти и технологии е предимство:

Nodejs
MongoDB

	wget https://nodejs.org/dist/v4.5.0/node-v4.5.0-linux-armv6l.tar.gz
	sudo mv node-v4.5.0-linux-armv6l.tar.gz /opt

	cd /opt
	sudo tar -xzf node-v4.5.0-linux-armv6l.tar.gz
	sudo mv node-v4.5.0-linux-armv6l nodejs
	sudo rm node-v4.5.0-linux-armv6l.tar.gz

	sudo ln -s /opt/nodejs/bin/node /usr/bin/node
	sudo ln -s /opt/nodejs/bin/npm /usr/bin/npm

	<!DOCTYPE html>
	<html>
	<head>
	<title>Maintenance in progress. Please try again in few minutes</title>
	<link href='//fonts.googleapis.com/css?family=Ubuntu:300' rel='stylesheet' type='text/css'>
	<style type="text/css" />
	body {color: #666; text-align: center; font-family: "Ubuntu", "Helvetica Neue", Helvetica, Arial, sans-serif; sans-serif; margin:0; width: 800px; margin: auto; font-size: 14px; }
	h1 { font-size: 56px; line-height: 100px; font-weight: normal; color: #456; }
	h2 { font-size: 24px; color: #666; line-height: 1.5em; }
	h3 { color: #456; font-size: 20px; font-weight: normal; line-height: 28px; }

	require 'socket'

	# thanks to @mitio
	UNIXSocket.open('/tmp/fast.pid') do \|fastrails\|
	fastrails.write ARGV.join(' ')
	puts fastrails.read
	end

	=begin
	Jekyll tag to include Markdown text from _includes directory preprocessing with Liquid.
	Usage:
	{% markdown <filename> %}
	=end
	module Jekyll
	class MarkdownTag < Liquid::Tag
	def initialize(tag_name, text, tokens)
	super
	@text = text.strip