I've been using Claude Code and Cursor for several months on a real project. The tools are impressive, but I kept running into the same failure modes:1. Long sessions cause context drift — the AI gradually ignores the original design 2. The AI writes fake tests — empty assertions, mocking the thing being tested 3. No research phase — the AI guesses how a framework works instead of reading the docsOPC Workflow is my fix: three markdown files you put in your project and trigger as slash commands (/plan_sprint, /sprint, /audit).The core mechanic is isolated sessions: - Planning happens in session A, then you close it - Development happens in session B, then you close it - Auditing happens in session C with zero knowledge of session BThe audit is the part I'm most proud of. It runs mutation testing — deliberately breaking each core function to verify the tests actually catch it. In my project, it found a module that directly instantiated components, bypassing the agent registry entirely. S...