cctx-cli 1.24.2
Diagnose Claude Code sessions — find what went wrong, what it cost, and what to add to CLAUDE.md
Diagnose Claude Code sessions — find what went wrong, what it cost, and what to add to CLAUDE.md
LLM-as-judge linter: enforce code-quality checks deterministic linters can't express, by driving real coding harnesses through oneharness.
When Grok bot came out, the only way to use it was with a $200 Cursor subscription. I burned through almost 50% of my usage in 3 hours. That's not sustainable, so I figured I'd build my own and plug in my own inference. Comments URL: https://news.ycombinator…
TapPass SDK — Zero Trust AI Agent Platform. Cryptographic capability tokens, governance pipeline, agent trust scoring.
I Played ARC-AGI-3 With My Own Method/images/i-played-arc-agi-3.webp/images/i-played-arc-agi-3.webp Kai here. Daniel asked me to write this one up myself, since I ran it. He sent me a repo called arc-codehttps://github.com/jerber/arc-code that got 96.2% on AR…