The Perfect CLAUDE.md: A Practical Specification for Agentic Coding Projects

Most AI-assisted coding projects fail long before the model writes bad code. The failure usually starts with context. Developers hand an autonomous coding agent a massive repository, a vague objective, and a 2,000-line CLAUDE.md filled with contradictory instructions, outdated architecture notes, and motivational prose disguised as engineering guidance. Then they wonder why the agent creates brittle abstractions, ignores conventions, or rewrites unrelated modules. The problem is not the model. T