News for hackers. Stuff that matters.

A comment on Show HN: We analyzed 1,573 Claude Code sessions to see how AI agents work.

Re:Show HN: We analyzed 1,573 Claude Code sessions to see ho... by dmix on Thursday March 12, 2026 @11:22AM (#47352050)
I've seen Claude ignore important parts of skills/agent files multiple times. I was running a clean up SKILL.md on a hundred markdown files, manually in small groups of 5, and about half the time it listened and ran the skill as written. The other half it would start trying to understand the codebase looking for markdown stuff for 2min, for no good reason, before reverting back to what the skill said.

LLMs are far from consistent.

[ Parent | on HN ]
Re:Show HN: We analyzed 1,573 Claude Code sessions to see ho... by cbg0 on Thursday March 12, 2026 @11:27AM (#47352142)
Try this: Keep your CLAUDE.md as simple as possible, disable skills, and request Opus to start a subagent for each of the files and process at most 10 at a time (so you don't get rate limited) and give it the instructions in the skill for whatever processing you're doing to the markdowns as a prompt, see if that helps.
[ Parent | on HN ]
Re:Show HN: We analyzed 1,573 Claude Code sessions to see ho... by keks0r on Thursday March 12, 2026 @11:25AM (#47352101)
yes we had to tune the claude.md and the skill trigger quite a bit, to get it much better. But to be honest also 4.6 did improve it quite a bit. Did you run into your issues under 4.5 or 4.6?
[ Parent | on HN ]
Re:Show HN: We analyzed 1,573 Claude Code sessions to see ho... by dmix on Thursday March 12, 2026 @11:43AM (#47352460)
I was using Sonnet 4.6 since it was a menial task
[ Parent | on HN ]
Re:Show HN: We analyzed 1,573 Claude Code sessions to see ho... by conception on Thursday March 12, 2026 @03:13PM (#47355691)
https://scottspence.com/posts/measuring-claude-code-skill-ac...

This works in my experience

[ Parent | on HN ]
Re:Show HN: We analyzed 1,573 Claude Code sessions to see ho... by stpedgwdgfhgdd on Thursday March 12, 2026 @04:39PM (#47356750)
Try the latest skill-creator, has a/b testing
[ Parent | on HN ]