Source Intelligence
Follow Discord
Reading a new release v2.1.251 Analysing changes · 2/5 Sorting the findings · 1/4 steps 470 findings $18.91 so far

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 v2.1.3 Home All releases ←olderv2.1.2 v2.1.4newer→
Claude Code v2.1.3

Permission Explainer Keyboard Shortcut

What

Press Ctrl+E during permission prompts to toggle an AI-generated explanation of what the command does and its risk level.

Usage

When Claude asks for permission to run a command, press Ctrl+E to see:

  • What the command does (explanation)
  • Why Claude is running it (reasoning)
  • Potential risks with severity level (LOW/MEDIUM/HIGH)
Details
  • Explanations are generated on-demand using a fast model
  • Toggle the explanation panel on/off with Ctrl+E
  • Risk levels: LOW (safe dev workflows), MEDIUM (recoverable changes), HIGH (dangerous/irreversible)
  • Only appears when the permission explainer feature flag is enabled
Evidence

hg2() at line 417649 (checks X.ctrl && J === "e", calls tengu_permission_explainer_shortcut_used), gg2() at line 417666 (renders "ctrl+e to " + "hide" or "explain"), wc5() at line 417675 (displays explanation with riskLevel)

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 v2.1.3 →