Claudetop – htop for Claude Code sessions (see your AI spend in real-time)(github.com)

30 points by liorwn 7 months ago | 13 comments

1940s Irish sci-fi novel features early mecha and gravity assists(github.com)

70 points by donohoe 8 months ago | 26 comments

Claude Code plugin that plays a Mr. Meeseeks voice line whene Claude is waiting(github.com)

112 points by patrickwiseman 3 months ago | 48 comments

Show HN: enveil – hide your .env secrets from prAIng eyes(github.com)

181 points by parkaboy 8 months ago | 117 comments

Show HN: Claudoro, Pomodoro timer embedded in the Claude Code statusline(github.com)

39 points by emson 3 months ago | 28 comments

Show HN: Bithoven – A high-level, imperative language for Bitcoin Smart Contract(github.com)

15 points by hyunhum 10 months ago | 3 comments

Claude Code can debug low-level cryptography(words.filippo.io)

446 points by Bogdanp 11 months ago | 199 comments

Filippo Valsorda's blog post on using Claude Code to debug his new Go implementation of the ML-DSA post-quantum signature algorithm.

Issue: Claude Code is unusable for complex engineering tasks with Feb updates(github.com)

1252 points by StanAngeloff 6 months ago | 686 comments

GitHub issue on anthropics/claude-code reporting that Claude Code became unusable for complex engineering tasks after the February model updates.

Gheist campaign plants secret-dumping workflows using stolen GitHub tokens(wiz.io)

44 points by acossta 1 day ago | 0 comments

Wiz Research blog post analyzing Gheist, a campaign using stolen GitHub tokens to plant workflows that dump repository secrets, with IOCs and response guidance.

Claude's system prompt is over 24k tokens with tools(github.com)

584 points by mike210 1 year ago | 308 comments

A GitHub file in a repository of leaked LLM system prompts containing what is claimed to be Claude's full system prompt including tool definitions.

Once: Cache CLI commands(github.com)

85 points by baquero 17 days ago | 37 comments

GitHub repository for once, a Go CLI tool that runs a command once and reuses its cached output for a period of time.

I never authorized an integration that scans my secrets(github.com)

202 points by trvrprkr 10 days ago | 155 comments

A closed GitHub issue on the home-assistant.io repo in which a user complains that an integration scanning their secrets was enabled without authorization, calling it a privacy invasion.