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 v2.1.81 Home All releases olderv2.1.80 v2.1.83newer
Claude Code v2.1.81

Auto Mode Rule Critique CLI

What

New claude auto-mode critique subcommand that sends your custom auto mode rules to an AI reviewer that evaluates them for clarity, completeness, conflicts, and actionability.

Usage
claude auto-mode critique
claude auto-mode critique --model opus
claude auto-mode defaults   # view the default rules for reference
Details
  • Reads your custom rules from autoMode.{allow, soft_deny, environment} in settings
  • Shows the full classifier system prompt alongside your custom rules for context
  • AI reviewer comments only on rules that could be improved
  • If no custom rules are found, prompts you to add them and use claude auto-mode defaults to see defaults
Evidence

Auto mode rule critique command (search for "Analyzing your auto mode rules" and "auto_mode_critique")

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 v2.1.81 →