Specs, rules and skills for AI agents: what an agent should know about a project, specs by aggregate, and a reconcile loop.
Spec-driven development with a reconcile loop: who changes the desired state and who brings the code to it, why green tests do not yet mean “correct”, and which six environment capabilities the agent needs to close the loop.
Spec-driven development without spec sprawl: how to keep specs in one aggregate dictionary so they do not multiply with every feature: requirement levels, the aggregate card and context boundaries.
Four kinds of persistent context for AI (AGENTS.md, CLAUDE.md, skills): the task spec, the project bible, rules and skills. What goes into each, when it enters the context, and what ChatGPT and Claude offer. Based on Anthropic, OpenAI, GitHub, Cursor and Cline docs.