What's hiding in your Claude Code config files? I mined mine-found 22 patterns
The author analyzed their Claude Code configuration files and discovered 22 distinct patterns, revealing hidden conventions, workflows, and automation rules embedded within the configs that shape how AI coding assistants behave on their projects.
Background
- Claude Code is an AI coding assistant by Anthropic (the makers of Claude AI). Users configure it via config files (like `~/.claude/config.json` or project-level `.claude.json`) to control model behavior, set custom instructions, define tools, etc.
- The author "mined" (analyzed) their own config files—likely using scripts to extract and categorize settings—and found 22 distinct patterns, meaning recurring configurations for different use cases (e.g., code review style, documentation generation, framework-specific rules).
- This matters because config files are under-discussed: most users copy-paste snippets without understanding what's available or how to structure them effectively. The patterns the author discovered serve as a reference for power users looking to optimize their own setups.
Newer Claude models sometimes invent extra keys in tool call arguments, breaking validation in Pi's edit tool. The author suspects post-training for Claude Code's forgiving harness makes alternative schemas fail. This suggests closed RL training can degrade general tool-use reliability.
The article argues that Claude for Mac is an Electron app because its lead developer, Felix Rieseberg, is a former Microsoft engineer known for porting Slack to Electron and has a professional history strongly tied to the Electron framework.
Simon Willison released llm-coding-agent 0.1a0, an experimental coding agent built on his LLM library. The agent provides tools for reading, editing, searching files and executing commands, and ships with a Python API and CLI. It was developed using Claude Code (Fable 5) via TDD with a spec-first approach, and is available as a slop-alpha on PyPI.
Truth Social remains an outlet primarily for Trump's own posts, while other administration officials continue using X. The platform functions as a blog-like channel for Trump's messages rather than a genuine social network competitor.