Karpathy on Programming

1. claude-code-system-prompts

   1 10 12,307 9.7 JavaScript

   All parts of Claude Code's system prompt, 27 builtin tool descriptions, sub agent prompts (Plan/Explore/Task), utility prompts (CLAUDE.md, compact, statusline, magic docs, WebFetch, Bash cmd, security review, agent creation). Updated for each Claude Code version.

   

   That refers to the sandbox "escape hatch" [1], running a command without a sandbox is a separate approval so you get another prompt even if that command has been pre-approved. Their system prompt [2] is too vague about what kinds of failures the sandbox can cause, in my experience the agent always jumps straight to disabling the sandbox if a command fails. Probably best to disable the escape hatch and deal with failures manually.

   [1] https://code.claude.com/docs/en/sandboxing#configure-sandbox...

   [2] https://github.com/Piebald-AI/claude-code-system-prompts/blo...

2. SaaSHub

   www.saashub.com sponsored

   SaaSHub - Software Alternatives and Reviews. SaaSHub helps you find the best software and product alternatives

   

3. monorepo

   2 11 125 10.0 TypeScript

   Monorepo for all of my projects (by shepherdjerred)

   

   3. Provide an interface for easily switching between your active worktrees/containers.

   For credentials, I have an HTTP/HTTPS mitm [1] that runs on the host with creds, so there are zero secrets in the container.

   The end goal is to be able to manage, say, 5-10 Claude instances at a time. I want something like Claude Code for Web.

   [0]: https://github.com/shepherdjerred/monorepo/tree/main/package...

4. nitter

   3 966 13,437 9.1 Nim

   Alternative Twitter front-end

   

5. claude-code-transcripts

   4 6 1,665 8.7 Python

   Tools for publishing transcripts for Claude Code sessions

   

   If the complexity grows beyond what it makes sense to do without React I'll have the LLM rewrite it all in React!

   I did that with an HTML generation project to switch from Python strings to Jinja templates just the other day: https://github.com/simonw/claude-code-transcripts/pull/2

6. micro-javascript

   5 8 30 9.1 Python

   Python port of MicroQuickJS

   

7. datasette-turnstile

   6 1 2 5.6 Python

   Configurable CAPTCHAs for Datasette paths using Cloudflare Turnstile

   

8. Vibe-Prolog

   7 7 56 9.9 Python

   Vibe 🎶 Coding 💻 Prolog 🐪

   

   Ironically this doesn't really prove that the current frontier models are better because large amounts of code were written with non-frontier models (You can sort of get an idea of what models were used with the labels on https://github.com/nlothian/Vibe-Prolog/pulls?q=is%3Apr+is%3...)

   But - importantly - this project is what convinced me that the frontier models are much better than the previous generation. There were numerous times I tried the same thing in a non-Frontier model which couldn't do it, and then I'd try it in Claude, Codex or Gemini and it would succeed.

Suggest a related project