/doctor Diagnostics with Auto-Fix / Claude Code v2.1.105

What

The /doctor command has been rewritten as a comprehensive diagnostic dashboard with a new keybinding to auto-fix detected issues.

Usage

/doctor            # open diagnostics screen
f                  # press f to ask Claude to fix the reported issues

Details

Displays installation info, ripgrep status, update channel, auto-update permissions
Aggregates warnings from multiple sources: CLAUDE.md context usage, agent parse errors, plugin errors, keybinding issues, MCP server health, unreachable permission rules, invalid settings, version locks
New tree-view UI with severity-colored messages and suggested fixes
"f to fix with Claude" sends the diagnostics output to a prompt: "Help me fix the issues reported by /doctor below"
Read-only checks run without confirmation; destructive fixes require explicit user approval

Evidence

Doctor command context (search for "doctor:fix") and fix prompt (search for "Help me fix the issues")

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

How sure we are

One source agreesOne thing we can check says the same as this entry.

Anthropic's release notes agreeImproved /doctor layout with status icons; press f to have Claude fix reported issues

See this entry in the whole of v2.1.105 →

The build it came inv2.1.105

13 Apr 2026 · 36 entries, this one is #2.

Either side of it

v2.1.104Older
v2.1.107Newer

Open the release →

Names in this entry

slash/doctor
Skill. Run a setup checkup that diagnoses issues and can fix them. Checks installation health, including duplicate or leftover installs, PATH problems, and unparseable settings files. Finds unused skills, MCP servers, and plugins versus their context cost, flags slow hooks, and checks for a newer version on your release channel. Deduplicates local CLAUDE.md files against checked-in ones, trims checked-in CLAUDE.md files by cutting content Claude could derive from the codebase, and migrates the always-loaded guidance that remains into skills and nested CLAUDE.md files that load on demand. Also offers to make auto mode your default and to pre-approve frequently denied read-only commands. Reports findings first and asks for confirmation before changing anything. From the terminal, claude doctor prints read-only installation diagnostics without starting a session. Alias: /checkup. Run /doctor prompt-audit to have Claude audit your CLAUDE.md files, skills, and other configuration for outdated or conflicting instructions instead of running the checkup. The prompt-audit subcommand requires Claude Code v2.1.283 or later. The CLAUDE.md trim check requires Claude Code v2.1.206 or later. Before v2.1.205, /doctor opened a read-only diagnostics screen and pressing f sent the report to Claude
clidoctor
claude doctor now lists each sandbox credential-masking problem separately with a specific fix.

Anthropic's note

Upstream's own release notes for v2.1.105 name something this entry names, so the two are probably about the same change. Probably: the pairing is made on a shared name rather than on the words around it.

Improved /doctor layout with status icons; press f to have Claude fix reported issues

Is this right?