Rafał Araszkiewicz — Blog https://arasz.me/blog Engineering notes, project updates, and technical deep-dives from Rafał Araszkiewicz — Senior .NET / AWS / AI Engineer. en Sat, 01 Aug 2026 19:35:12 GMT https://arasz.me/favicon.svg Rafał Araszkiewicz — Blog https://arasz.me/blog https://arasz.me/favicon.svg https://arasz.me/og-image.png #00d4ff The Skills I Gave My Coding Agent https://arasz.me/blog/ai-badger-skills https://arasz.me/blog/ai-badger-skills Sat, 01 Aug 2026 08:30:00 GMT Rafał Araszkiewicz A tour of the skills my agent framework ships — what each one is for, what it actually does to your repo, and the situation that makes you reach for it. Starting with the one I open almost every day. A tour of the skills my agent framework ships — what each one is for, what it actually does to your repo, and the situation that makes you reach for it. Starting with the one I open almost every day.

]]> AI Agents ai-badger Claude Code Developer Tooling Skills The Bill Said Delegate. So I Made It the Default. https://arasz.me/blog/teaching-agents-to-delegate https://arasz.me/blog/teaching-agents-to-delegate Fri, 31 Jul 2026 14:00:00 GMT Rafał Araszkiewicz Part 2 measured a month of AI agent costs. This is what I changed because of it: my agent framework now picks the right model for each job, refuses hand-offs that name no model, and has a new team-lead role whose only job is routing work. Part 2 measured a month of AI agent costs. This is what I changed because of it: my agent framework now picks the right model for each job, refuses hand-offs that name no model, and has a new team-lead role whose only job is routing work.

]]> AI Agents ai-badger Cost Claude Code Delegation What AI Coding Agents Actually Cost, Part 2: A Full Month of Data https://arasz.me/blog/agent-cost-part-2 https://arasz.me/blog/agent-cost-part-2 Fri, 31 Jul 2026 08:30:00 GMT Rafał Araszkiewicz Part 1 compared three agents over two weeks. Part 2 reads 24 days of ccusage data off one machine — $10,453 in API-equivalent estimates, 97.81% cache reads, and the kinds of sessions that actually raise the bill. Part 1 compared three agents over two weeks. Part 2 reads 24 days of ccusage data off one machine — $10,453 in API-equivalent estimates, 97.81% cache reads, and the kinds of sessions that actually raise the bill.

]]> AI Claude Code Hermes Cost ccusage Agents Data ai-badger code-review-graph: When Your AI Agent Needs a Map of Your Codebase https://arasz.me/blog/code-review-graph-review https://arasz.me/blog/code-review-graph-review Sun, 26 Jul 2026 10:00:00 GMT Rafał Araszkiewicz A practical look at code-review-graph — how it builds a structural knowledge graph of your codebase, what it actually found in two real projects, and whether the token savings are real. A practical look at code-review-graph — how it builds a structural knowledge graph of your codebase, what it actually found in two real projects, and whether the token savings are real.

]]> AI Agents Code Review MCP Developer Tools Knowledge Graph Tree-sitter What AI Coding Agents Actually Cost: Real Usage Data Across 3 Agents https://arasz.me/blog/agent-cost-comparison https://arasz.me/blog/agent-cost-comparison Thu, 23 Jul 2026 09:00:00 GMT Rafał Araszkiewicz Data-driven comparison of Claude Code, Hermes Agent (via OpenRouter), and GitHub Copilot with real token usage, cost breakdowns, and the 80/20 strategy. Data-driven comparison of Claude Code, Hermes Agent (via OpenRouter), and GitHub Copilot with real token usage, cost breakdowns, and the 80/20 strategy.

]]> AI Claude Code Hermes OpenRouter Copilot Cost Agents Hermes Agent: A Developer-First AI Agent with Deep Integration Hooks https://arasz.me/blog/hermes-agent-review https://arasz.me/blog/hermes-agent-review Wed, 15 Jul 2026 08:30:00 GMT Rafał Araszkiewicz A practical review of Hermes Agent — how it compares to Claude Code, its hook system for prompt customization, token-friendly skill design, and why it pairs well with ai-badger. A practical review of Hermes Agent — how it compares to Claude Code, its hook system for prompt customization, token-friendly skill design, and why it pairs well with ai-badger.

]]> Hermes AI Agents Claude Code Developer Tools Introducing ai-badger: A Portable Agent Framework for the Multi-Agent Era https://arasz.me/blog/introducing-ai-badger https://arasz.me/blog/introducing-ai-badger Fri, 24 Jul 2026 08:30:00 GMT Rafał Araszkiewicz What ai-badger is, how the stack×feature catalog model works, and why portable agent knowledge matters when you run Claude Code, Hermes, Copilot, and Junie side by side. What ai-badger is, how the stack×feature catalog model works, and why portable agent knowledge matters when you run Claude Code, Hermes, Copilot, and Junie side by side.

]]> AI Agents Open Source Developer Tooling Claude Code Hermes Copilot