mannewalis

My Claude Code Setup

I work on multiple git worktrees of the same repo simultaneously, so I keep my Claude config in a parent directory and symlink it into each worktree. One place to update settings, policies, skills - they all stay in sync.

I use a policy MCP server that serves my coding standards as markdown files. I reference them with a § notation and they get pulled into context automatically. The server recursively resolves references, so if one policy points to another (like general code rules pointing to C++ specific rules), it follows the chain and pulls in everything needed. I have general rules, code quality rules, and C++ specific style all defined once and injected when needed.

I've set up a few skills to streamline things. The engineer skill loads the relevant policies before any code gets written. The continue/restart skills let me save session state to a continuation plan and pick up where I left off later.

Checkmate handles linting validation - different rules for different parts of the codebase (C++ engine code vs TypeScript cloud workers vs shell scripts).

Basically: policies keep the code consistent, skills keep the workflow consistent, and the shared config keeps everything in sync across worktrees.

(edited for formatting)

Seems like an ad for Incogni.

Minus points for redirect trapping.

Plenty of people will be working, just not everyone will make the jump to a post-AI society, especially older folks I imagine.

ok I looked it up and have a better understanding now.

But OpenAI's model isn't open source, how would they distill knowledge without direct access to the model?

lol

Hmmm who owns Hacker News?

You are neither. People are not thoughts, whether ones own or not.

Just tried the demo, this had zero effect on my brightness.

you can kiss this all goodbye Jan 20th 2025.

But but inner dialog?

Lol this isn't about helping users, this is about creating training data for MS to use to train their models.

Incoming cease and desist in...3...2...1

Lol no!