CLAUDE.md
Anthropic convention for project instructions in Markdown
Episodes
-
#6050: Codex vs Claude Code: What the Numbers Actually CountCodex has more users, Claude Code has more revenue — both can be true. The difference is what each number is counting. -
#4832: Your AI Memory Should Be Markdown FilesWhy your AI project memory should live in Git-tracked Markdown files, not a proprietary platform. -
#4825: Russian Dolls: Skills, MCPs, and PluginsWhen to use a skill vs MCP vs plugin in Claude Code — and when to keep it simple. -
#4786: Markdown vs Vectors for Agent MemoryWhy coding agents need two kinds of memory — and why mixing them creates a sync nightmare. -
#4701: Why Claude Code Re-Introduces Itself to Your RepoClaude Code remembers your preferences but not your codebase. We explore why that's by design and how to work around it. -
#4445: AI Agents Keep Undoing Each Other's WorkWhy AI coding agents silently revert each other's fixes — and three memory strategies that prevent it. -
#2790: Git Hygiene for AI Coding AgentsHow to keep your git repo clean when Claude is blazing through tasks — plus a recovery playbook for when things go sideways.