Claude Usage Tips

assetactive

Provenance: Ingested from C:\Users\mesha\Downloads\good-claude-tips-file.md (~5.5 KB) on 2026-03-28. Curated collection of Claude Code best practices from Boris Cherny (creator of Claude Code at Anthropic), shared via X threads and structured into a CLAUDE.md template, with community rebuttal commentary.

This CLAUDE.md file will make you 10x engineer

It combines all the best practices shared by Claude Code creator:

Boris Cherny (creator of Claude Code at Anthropic) shared on X internal best practices and workflows he and his team actually use with Claude Code daily. Someone turned those threads into a structured CLAUDE.md you can drop into any project.

It includes: • Workflow orchestration • Subagent strategy • Self-improvement loop • Verification before done • Autonomous bug fixing • Core principles

This is a compounding system. Every correction you make gets captured as a rule. Over time, Claude's mistake rate drops because it learns from your feedback.

If you build with AI daily, this will save you a lot of time.

Workflow Orchestration

1. Plan Mode Default

  • 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

2. Subagent Strategy 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 task per subagent for focused execution

3. Self-Improvement Loop

  • 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

6. Autonomous Bug Fixing

  • 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

Task Management

  1. Plan First: Write plan to 'tasks/todo.md' with checkable items
  2. Verify Plan: Check in before starting implementation
  3. Track Progress: Mark items complete as you go
  4. Explain Changes: High-level summary at each step
  5. Document Results: Add review to 'tasks/todo.md'
  6. Capture Lessons: Update 'tasks/lessons.md' after corrections

Core Principles

  • Simplicity First: Make every change as simple as possible. Impact minimal code.
  • No Laziness: Find root causes. No temporary fixes. Senior developer standards.
  • Minimal Impact: Changes should only touch what's necessary. Avoid introducing bugs.

Community Rebuttal

From Raphaël Hoogvliets (Principal Engineer | DX, Data, MLOps):

"This is not very useful... some feedback and points of caution:

  • there is nothing about real context management, a top skill to use CC well
  • subagents managed poorly is throwing massive compute at problems that need, again, topnotch context management + state management
  • autonomous bug fixing works for simple things, not bugs that need redesign
  • some massive token burner elements in here

There are many good workflow kits and workflow designs out there. You can't stuff all solutions in a single CLAUDE.md config file and expect your problems to be fixed... A lot of steps need specific framework instructions, you can't just say "verify everything"

CC builders didn't use one config file to make developing things run smoothly. Designing complex workflows is what actually matters."

From Eddy Ferreira (Web/Mobile/Software Engineer):

"Even if you craft the perfect Claude configuration today, it becomes outdated as soon as the codebase evolves. Without continuous self-healing, maintaining accuracy at the current pace of change is simply not sustainable."

Reference: https://www.work-3s.com/