Claude Code creator Boris Cherny shares CLAUDE.md practices that cut repeated errors
Roger_M_Taylor · x · 2026-10-05
Boris Cherny, creator of Claude Code at Anthropic, shared on X the best practices and workflows his team uses daily with Claude Code. Several can be baked into any project's CLAUDE.md:
- Workflow orchestration
- Sub-agent strategy
- Self-improvement loop
- Verification before finalizing
- Automatic error correction
- Fundamental principles
The interesting part: it works as a cumulative system. Every correction you make to Claude can be recorded as a rule for future tasks, so over time Claude learns from your feedback and repeatedly reduces the same errors. For daily AI-assisted coding, a well-structured CLAUDE.md saves significant time.
More from coding & agent
- Cloudflare Agents SDK adds Pi Durable harness for crash-resilient long-running agents — mitsuhiko · 2026-10-05
- Codex team pledges daily improvements for 28 days or a full reset — lxfater · 2026-10-05
- OpenAI Agents API in 10 steps: GPT-6.1 Sol nears GPT-6 Astra at one-fifth the price — Roger_M_Taylor · 2026-10-05
- Engineer 'fired herself' from the loop, runs 24/7 agent fleet in Grok Bot — the talk Musk reposted — Roger_M_Taylor · 2026-10-05
- DIGI-FUZE: a retro console where AI fuses any two game cartridges into a new game — Flomerboy · 2026-10-05
- One defaults write command unlocks forbidden targets for macOS Computer Use — GabGarrett · 2026-10-05