Join me on a journey where every post brings a fresh perspective. This blog is for those who are driven by curiosity and a desire to learn.
A follow-up to the real cost of AI coding agents: how to turn usage-based billing, AI credits, model mix, and engineering outcomes into a practical KPI scorecard.
A follow-up to the real cost of AI coding agents: how to turn usage-based billing, AI credits, model mix, and engineering outcomes into a practical KPI scorecard.
Spec-Kit and OpenSpec are two prominent spec-driven workflows for AI coding agents. They look similar on the surface and diverge sharply once you actually use them. Here's how they compare on workflow, philosophy, brownfield support, and customization.
A quick chat costs about $0.0015. A heavy agent session costs $5. GitHub just admitted flat-rate pricing can't survive this gap. Here's what AI coding agents actually cost at team scale, with real numbers from official sources.
Five customization files, one .NET Aspire repo, one complete agent setup. How AGENTS.md, .instructions.md, SKILL.md, .prompt.md, and .agent.md work together in practice.
The difference between AGENTS.md and .agent.md, how GitHub Copilot uses both, and when to write repo instructions versus a custom agent persona.
Why GitHub Copilot skills live in plural folders but singular SKILL.md files, how they load, and when supporting files are pulled in on demand.
