Source Intelligence
Follow Discord

DisclaimerUnofficial, and not affiliated with Anthropic. Nearly all of this is read straight out of what ships: npm bundles, captured prompts, published docs. Anthropic's own notes go in verbatim, marked as theirs. The rest is my reading, and every entry carries the strings behind it. If one looks wrong, vote it down and say why.

← All of v2.1.30 Home All releases ←olderv2.1.29 v2.1.31newer→
Claude Code v2.1.30

/insights Command

What

Generate an interactive HTML report analyzing your Claude Code usage patterns across sessions.

Usage
/insights
Details
  • Analyzes session transcripts to produce a multi-faceted usage report
  • Generates an "At a Glance" summary with sections: Big Wins, What's Working, What's Hindering You, Quick Wins, and Ambitious Workflows
  • Identifies project areas, friction categories, usage patterns, and features to try
  • Includes a "Multi-Clauding (Parallel Sessions)" analysis section
  • Produces an HTML report with interactive checkboxes for selecting CLAUDE.md suggestions to copy
  • Uses AI-powered facet extraction to categorize sessions by outcome types (e.g., "Correct Code Edits", "Good Debugging", "Edit Failed", "Wrong Approach")
Evidence

Insights prompt handler (search for "insights" in the prompt name definition, and "Generate a report analyzing your Claude Code sessions")

Strings lifted out of the shipped bundle, so the claim above can be checked against them.

Related

Other releases about the same thing. Found by shared names or similar wording; neither means one caused the other.

See this entry in the whole of v2.1.30 →