Source Intelligence

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 v2.1.6 Home All releases olderv2.1.5 v2.1.7newer
Claude Code v2.1.6

Command Explanation Tool Refactoring

The shell command explanation system has been refactored from structured outputs to a tool-based approach.

Details
  • Now uses explain_command tool with explicit JSON schema
  • Cleaner separation between explanation, reasoning, and risk assessment
  • Simplified system prompt: "Analyze shell commands and explain what they do, why you're running them, and potential risks."
Evidence

zE5 at line 2256 (tool definition, contains "explain_command")

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

See this entry in the whole of v2.1.6 →