Thread

1. perganomoly · 1789783761 · focus · HN ↗

   The fact that it took this long to add such a basic feature is a disgrace. I’m not even remotely satisfied. Bailed on Claude ages ago. Rolling Codex, Gemini, and Qwen3.8 30B. The only way I’m going back to Anthropic is if they drop and Culture Series mind.

   1. chrisandchris · 1789798788 · focus · HN ↗

      We have a CLAUDE.md file whose only content is "please read .agents/agents.md"

      1. yjftsjthsd-h · 1789798923 · focus · HN ↗

         Wouldn't symlinking it be faster and use fewer tokens?

         1. ffsm8 · 1789801989 · focus · HN ↗

            I did that but not necessarily.

            When prompted to write to it, it will always try to write into the Claude.md and error out with that approach.. It eventually figures it out, but it's a ymmv situation I think

         2. tstrimple · 1789875050 · focus · HN ↗

            It also works more reliably. I've tested this quite a bit. Instructions in files referenced via CLAUDE.md are more likely to fall out of context or to be ignored. Raw project level CLAUDE.md instructions are the second most durable available as far as I know. I used to have a "well organized" hierarchy of rules and instructions. Collapsing all of that into CLAUDE.md + skills made things far more predictable and "as instructed".

Unofficial Hacker News client; not affiliated with Y Combinator.