ALAdam Lewis·3d ago32A spec the agent can't run isn't a spec yetWhat's working for us with spec-driven development is treating acceptance criteria as checks the agent can run, not paragraphs it has to interpret. Small TOC example in the latest post on the pricklesSSuny and 1 more commented
EMEnmanuel Magallanes·May 1429Stop Agent roaming all your codebaseWhat it is: agent-harness-kit (ahk) is a thin CLI + library you drop into any repo to give your AI agents structure. It scaffolds a 4-role workflow (Lead → Explorer → Builder → Reviewer), a local SQLiKKeesan and 8 more commented
EMEnmanuel Magallanes·May 1400I built agent-harness-kit — scaffolding for multi-agent AI workflowsWhat it is: agent-harness-kit (ahk) is a thin CLI + library you drop into any repo to give your AI agents structure. It scaffolds a 4-role workflow (Lead → Explorer → Builder → Reviewer), a local SQLiJoin discussion
BBarbara·Apr 2404In today's context, buy or build software?It seems this question has come up quite often in the community, but today it’s more relevant than ever. I’m specifically referring to the pace of AI development and its use in coding, testing, designFJPhr and 3 more commented
JSJohn Smith·Mar 2620Your Claude Code skill "works." But is it actually doing anything?Three things that actually tell me something's wrong: Trigger drift — the skill stops firing on inputs it used to handle Zero delta — same result with or without the skill active My correction log Join discussion
LMLeena Malhotra·Mar 2510Claude Opus 4.6 vs GPT-5 on Multi-Step Reasoning.What are your thoughts?Join discussion
