RSSAmplifier

Blog

Hammad Haqqani - Blog

Exploring the frontiers of cloud engineering, DevOps, AI infrastructure, and modern operations.

hammadhaqqani.comRSS feed ↗42 posts

Latest posts

Context Engineering Is Cloud Cost Optimization for Your AI Agent

Run /context in your next Claude Code session before you type anything. Look at the breakdown: system prompt, tool definitions, MCP schemas, CLAUDE.md, memory files. That's your idle spend. You're...

MCP Servers vs. Agent Skills: When to Use Each (And Why the Answer Is Usually Both)

Open a fresh Claude Code session in one of my client repos and run /context. Before I type a single word, tens of thousands of tokens are already spent. Most of that is MCP tool definitions: a GitHub...

Awesome DevOps AI Crossed 219 Tools and a Few Thousand Stars. Here's What Changed in 60 Days.

In March I shipped Awesome DevOps AI, a curated list of AI tools, agents, and resources built for DevOps, SRE, and Platform Engineering. The first version had 100 entries. Sixty days later it has...

The $47K AWS Bill My Claude Code Hook Caught at 2 AM

A client called me at 11:47 PM on a Tuesday. Their staging environment was on fire. Not literally. A Lambda was retrying a request to a third-party API on every cold start, the API was rate-limiting...

How a Claude Code Agent Burned $3,400 Overnight (And the Math to Predict It Before It Happens)

A founder I know left a Claude Code agent running on a refactoring task at 11 PM. The task was a 22-file cross-cutting rename. Nothing exotic. He went to sleep. At 7 AM he woke up to a $3,412 token...

The 7 Claude Code Hooks Every Production Team Should Be Running

A Claude Code agent without hooks is an intern with sudo. It will not be malicious. It will be confidently wrong about rm -rf, git push --force, or terraform destroy. You will find out at 2 AM. Hooks...

Stop Squinting at Cron: A Field Guide for 2026

Cron expressions are the most ubiquitous and least readable string in DevOps. Three decades of muscle memory and most engineers still pause for 10 seconds when they see 0 9 1 1-5. This guide is for...

Your GitHub Actions Bill Is Hiding 30% Waste. Here's the Math.

GitHub Actions billing has four moving parts most teams underestimate: minutes, OS multipliers, matrix expansion, and artifact storage. They compound. The bill arrives at the end of the month and...

How to Write a CLAUDE.md That Doubles Your Agent's Output

CLAUDE.md is the agent's onboarding doc. It is the difference between an agent that asks where db.ts lives every session and an agent that opens it and reads it. I have been writing these for 14...

Your First MCP Server in 12 Minutes (And the Three Configs That Brick Half the Setups I Audit)

MCP (Model Context Protocol) is the standard that lets Claude Code and Claude Desktop talk to external tools, databases, browsers, and APIs. The protocol is good. The config files are where teams...

Migrating from OpenAI to Anthropic in 2026: The Honest Playbook

Half my consulting calls this quarter started the same way: "We have been on the OpenAI SDK for two years. Leadership wants to evaluate Anthropic. What does the migration actually look like?" This is...

Why Your AWS NAT Gateway Bill Is 10x What You Think (And How to Cut It)

NAT Gateway is the single largest hidden line item on most AWS bills under 50K a month. It is not because the per-unit pricing is bad. It is because the pricing has two components that compound and...

The Missing Index Pattern Killing 80% of Postgres Apps (And How to Find Yours in 5 Minutes)

A Postgres database that performs well in development and falls over in production is almost always missing an index. The same five-mistake list shows up in every audit. They are easy to find, easy...

Why the Same Prompt Costs 30% Less on Claude Than on GPT-5: A Tokenizer Story

Every API price comparison you read uses a price-per-million-tokens number. That number is correct, and it is also misleading. Because the same prompt does not become the same number of tokens across...

GPT-5 Code vs Claude Opus 4.7: The 30-Task Production Benchmark Nobody Wanted to Publish

I ran the same 30 production-shaped tasks through GPT-5 (via Codex CLI) and Claude Opus 4.7 (via Claude Code, 1M context, native plan mode). Same prompts. Same repos. Same machine. Same network. Same...

I Audited 12 AI Coding Setups This Spring. Every Single One Was Leaking 5 Figures.

In the last 90 days I sat down with 12 engineering teams who had rolled out Claude Code, Cursor, or both at company scale. Series A through public, four to two hundred engineers, US and EMEA. The...

30 Days of Claude Code in Production: The Receipts Across 7 Projects

Over the last 30 days I ran Claude Code as the primary pair-programmer across seven concurrent projects spanning consumer mobile, backend services, trading automation, personal web, networking,...

I Now Have 75 Free AI Tools Running in Your Browser, Here Are the 4 New Ones Everyone's Asking For

Two months ago I published a post about the 71 free browser-based AI and DevOps tools I built. It got way more attention than I expected. Thousands of developers started using them daily. The most...

BMAD Method: The Framework That Turns Claude Code Into a Complete Agile Development Team

What if Claude Code wasn't just a coding assistant, but an entire agile team? An analyst who gathers requirements. A product manager who writes PRDs. An architect who designs systems. A scrum master...

Superpowers Is the Most Important Open Source Plugin for Claude Code, Here's Why

There are hundreds of Claude Code plugins now. Most of them add a few slash commands and call it a day. Superpowers is different. It's a complete software development methodology that turns Claude...

The Ultimate Vibe Coding Prompt Library: 50 Battle-Tested Prompts for Claude Code, Cursor, and Windsurf

Vibe coding changed how I build software. Instead of typing every line, I describe what I want and an AI agent writes it. But here's the thing nobody talks about: the quality of your prompt...

What Leaked AI System Prompts Reveal About How Claude, ChatGPT, and Gemini Actually Think

In the last few months, system prompts from every major AI tool have leaked onto GitHub. Claude Code, ChatGPT, Gemini, Cursor, Windsurf, Devin, Replit, Lovable, v0, all of them. Repositories like...

How to Use AI Coding Assistants for Infrastructure as Code Without Breaking Production

You've probably tried using ChatGPT or Claude to write Terraform. Maybe you pasted an error message and got back confident-looking code that made things worse. Or you asked it to "create an AWS VPC"...

I Curated 219 AI Tools for DevOps Engineers (And You Can Use Them All for Free)

Over the past 6 months, I've watched the DevOps AI landscape explode from a handful of experimental tools to an overwhelming ecosystem of 500+ products, agents, and frameworks. Every week there's a...

Fine-Tuning vs RAG: The Decision Framework (When to Use Each)

"Should I fine-tune or use RAG?" I've been asked this question 47 times in the past 3 months. Every time, the person asking thinks they need fine-tuning. About 90% of the time, they actually need...

LLM Context Windows and Token Limits: The Complete Guide (2026)

You're halfway through pasting your 50-page architecture document into ChatGPT when it stops responding. Or Claude gives you an error: "Your message exceeds the maximum context length." Or you get...

Prompt Injection Attacks: What They Are and How to Stop Them (2026 Guide)

Last month, a Fortune 500 company's internal AI chatbot started leaking employee salary data. The cause? A simple prompt injection attack that took 8 seconds to execute. The attack looked like this:...

I Built 71 Free AI and DevOps Tools That Run Entirely in Your Browser

Every week I watch developers paste production secrets into random websites to decode a JWT, estimate token costs by doing math in a spreadsheet, and pay $20/month for a prompt testing tool that...

How to Set Up OpenClaw on macOS and Windows: Your Personal AI Assistant

OpenClaw is an open-source personal AI assistant with over 224,000 GitHub stars. It runs on your own machine, connects to any LLM provider (OpenAI, Anthropic, Google Gemini, Groq, Mistral, Ollama,...

The AI Singularity Is Closer Than You Think: Why 2026 Changed Everything

I've spent over a decade building and scaling systems, leading engineering teams, and staying ahead of every technological shift this industry has thrown at us. Cloud computing, DevOps, Kubernetes,...

The Definitive Guide to Setting Up Claude Code on Windows and macOS

I have been using Claude Code every day for over a year to build infrastructure, write Terraform, debug Kubernetes manifests, and ship production code faster than I ever thought possible. This is the...

The Hardcore DevOps Checklist: 2026 Edition

DevOps in 2026 is unrecognizable from five years ago. CI/CD pipelines are self-healing. AI agents are writing and reviewing Terraform. Platform engineering is a real discipline, not a rebranded ops...

How Claude Code and Codex Are Revolutionizing Cloud Infrastructure Engineering

The intersection of artificial intelligence and cloud infrastructure is no longer a futuristic concept -- it's the new reality of DevOps engineering. As someone who has spent over a decade building...

Automating AWS Operations Controls with Claude Code and Infrastructure as Code

Operations controls are the backbone of any secure, well-governed AWS environment. But manually writing Service Control Policies (SCPs), IAM policies, Config rules, and compliance checks across...

Building Self-Healing Infrastructure: Claude Code + CloudWatch + Lambda

What if your infrastructure could detect problems, diagnose root causes, and fix itself -- all before an engineer even gets paged? This isn't science fiction. It's what I've been building using...

Prompt Engineering for Cloud Engineers: Getting the Best from Claude Code

You've started using Claude Code for infrastructure work. You know it can generate Terraform, write CI/CD pipelines, and debug Kubernetes manifests. But are you getting the best output? The...

How to Ace Your Next Technical Interview

Technical interviews follow patterns. Once you understand the structure, you can prepare systematically instead of hoping for the best. Here's what I've learned from both sides of the interview...

AWS CLI Setup Guide: From Installation to Your First Commands

The AWS CLI is the foundation of any cloud engineer's toolkit. It lets you manage AWS resources from your terminal, automate tasks with scripts, and integrate AWS operations into CI/CD pipelines....

RAG Explained: How Retrieve and Generate Technology Works with Cloud Services

Retrieval Augmented Generation (RAG) is one of the most practical AI patterns for real-world applications. It combines the knowledge-retrieval capabilities of search systems with the natural language...

AIOps: A Practical Guide to AI-Powered IT Operations

AIOps -- Artificial Intelligence for IT Operations -- applies machine learning to the massive volumes of data generated by modern infrastructure. The goal: automate detection, diagnosis, and...

Free Resources to Learn Coding and Web Development in 2024

A curated list of the best free platforms for learning programming languages, frameworks, and development tools. Bookmark this and work through them at your own pace. Frontend HTML -- html.com...

Navigating the Cloud: Lessons from a Decade of Public Cloud Engineering

After 10+ years of building on AWS and Azure across financial services, government, and enterprise, here are the real lessons I've learned about cloud transformation -- what works, what doesn't, and...