Click any tag below to further narrow down your results
Links
@Raytar on X
A post from @raytar says a friend on Andrej Karpathy's team at Anthropic shared the CLAUDE.md file he uses, and that it makes Claude follow instructions far better from the first message. The post is a short pitch with no technical detail, so the file itself is the real content, and it is linked as an article rather than shown inline.
- The author says a CLAUDE.md file from a colleague of Andrej Karpathy, who joined Anthropic five weeks ago, changed how Claude behaves for them.
- The claimed benefit is that Claude stops resisting their requests and works the way they need from the first message.
- The post itself gives no specifics on what the file contains, so the claims are unverified.
@Jmoon_174 on X
The author says CLAUDE.md solves the instruction side of working with Claude, but the other half is tracking how much context you have left before you hit the limit. They built Headroom, a one-line install that puts a percentage readout in your statusline.
- CLAUDE.md handles persistent instructions for Claude, which is only half the problem.
- The other half is knowing your remaining context budget before you run out.
- Headroom installs in one line and displays context usage as a percentage in your statusline.