cd /news/developer-tools/claude-codeun-arkasindaki-ekipten-pa… · home topics developer-tools article
[ARTICLE · art-6552] src=gist.github.com ↗ pub= topic=developer-tools verified=true sentiment=· neutral

Claude Code’un arkasındaki ekipten paylaşılan gerçek kullanım alışkanlıkları bir araya getirilmiş ve tek bir dosyada toplanmış: CLAUDE.md

A set of real-world usage habits compiled by the team behind Claude Code, which have been consolidated into a single file called `CLAUDE.md`. The file outlines a structured workflow for AI-assisted coding, emphasizing plan mode for complex tasks, the liberal use of subagents to maintain context, and a self-improvement loop for learning from mistakes. It also includes principles for task management, verification, elegant problem-solving, and autonomous bug fixing to maintain high development standards.

read2 min views16 publishedFeb 22, 2026

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 #

  • 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 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: 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

  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 section to tasks/todo.md
  6. 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.
  • Minimal Impact: Changes should only touch what's necessary. Avoid introducing bugs.
── more in #developer-tools 4 stories · sorted by recency
── more on @claude code 3 stories trending now
sponsored brought to you by zahid.host 4,200+ EU-deployed projects
reading about agents? ship yours in a single git push.

Run your AI side-project on zahid.host

EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain — perfect for shipping the agent you just read about.

$git push zahid main
Live at https://your-agent.zahid.host
Get free account → Pricing
from €0/mo · no card required
LIVE [news/claude-codeun-arkasi…] indexed:0 read:2min 2026-02-22 ·