Boris Cherny’s CLAUDE.md

This article outlines a structured workflow methodology for AI coding agents, emphasizing the use of "plan mode" for complex tasks, strict verification before task completion, and continuous learning through a lessons log. It instructs the agent to demand elegant solutions, fix bugs independently without user hand-holding, and maintain a clean context window by offloading work to subagents. The core principles include planning first, tracking progress, documenting results, and ruthlessly iterating on mistakes to achieve senior developer standards.

CLAUDE.md - Enter plan mode for ANY non-trivial task 3+ steps or architectural decisions - If something goes sideways, STOP and re-plan immediately - don't keep pushing - Use plan mode for verification steps, not just building - Write detailed specs upfront to reduce ambiguity - Use subagents liberally to keep main context window clean - Offload research, exploration, and parallel analysis to subagents - For complex problems, throw more compute at it via subagents - One tack per subagent for focused execution - After ANY correction from the user: update tasks/lessons.md with the pattern - Write rules for yourself that prevent the same mistake - Ruthlessly iterate on these lessons until mistake rate drops - Review lessons at session start for relevant project 4. Verification Before Done - Never mark a task complete without proving it works - Diff behavior between main and your changes when relevant - Ask yourself: "Would a staff engineer approve this?" - Run tests, check logs, demonstrate correctness 5. Demand Elegance Balanced - For non-trivial changes: pause and ask "is there a more elegant way?" - If a fix feels hacky: "Knowing everything I know now, implement the elegant solution" - Skip this for simple, obvious fixes - don't over-engineer - Challenge your own work before presenting it - When given a bug report: just fix it. Don't ask for hand-holding - Point at logs, errors, failing tests - then resolve them - Zero context switching required from the user - Go fix failing CI tests without being told how - Plan First: Write plan to tasks/todo.md with checkable items - Verify Plan: Check in before starting implementation - Track Progress: Mark items complete as you go - Explain Changes: High-level summary at each step - Document Results: Add review section to tasks/todo.md - Capture Lessons: Update tasks/lessons.md after corrections - Simplicity First: Make every change as simple as possible. Impact minimal code. - No Laziness: Find root causes. No temporary fixes. Senior developer standards. - Minimat Impact: Changes should only touch what's necessary. Avoid introducing bugs.