How do I run Claude Code `/doctor prompt-audit` on CLAUDE.md and skills?

Run `/doctor prompt-audit` (Claude Code 2.1.283+) to audit CLAUDE.md, skills, agents, and commands for outdated or conflicting instructions. Alias `/checkup prompt-audit`. Not `/skill-doctor`.

Run /doctor prompt-audit (alias /checkup prompt-audit) on Claude Code ≥ 2.1.283 to audit CLAUDE.md files, skills, and related config for outdated or conflicting instructions — CHANGELOG also names agents and commands, and patterns written for older models. Optional [path] is in the command signature. This is not /skill-doctor (skill context cost + usage) and not the default /doctor install checkup.

TL;DR: In a session on v2.1.283+, type /doctor prompt-audit or /checkup prompt-audit. Claude audits instruction files instead of running the setup checkup. Use /skill-doctor when you need unused-skill cost, not prompt-pattern audit. Support Labs KW claude code doctor volume 50 (no KD in Labs — [GAP]).

Prerequisites

Claude Code ≥ 2.1.283 — commands docs floor for the prompt-audit subcommand; CHANGELOG adds it under ## 2.1.283 (still visible under current 2.1.284 history). Check with claude --version.
Interactive session — slash /doctor … runs inside a session. From the terminal, bare claude doctor is a different surface: read-only install diagnostics without starting a session (commands docs).
Something worth auditing — project/user CLAUDE.md, skills, agents, or commands that may still teach older-model habits after a Sonnet/Opus upgrade.

Run `/doctor prompt-audit`

Start (or attach to) a Claude Code session in the terminal.
Type one of:

/doctor prompt-audit

/checkup prompt-audit

Optional path (signature only):

/doctor prompt-audit [path]

Deep path semantics beyond the documented [path] argument are [GAP] — cite the signature; do not invent path rules.

What it audits (official wording):

Source	Scope
Commands docs	`CLAUDE.md` files, skills, and other configuration for outdated or conflicting instructions — instead of the checkup
CHANGELOG 2.1.283	`CLAUDE.md` files, skills, agents and commands for prompting patterns written for older models

Report priorities (CHANGELOG improve under 2.1.283 history): stale paths, stale commands, and contradicting instruction files lead the report; thinking keywords that Claude Code documents are kept.

Contrast: plain /doctor / /checkup is a broader setup checkup that reports findings first and asks for confirmation before changing anything. Do not claim prompt-audit auto-rewrites files without a primary cite — interactive fix-apply UX for prompt-audit is [GAP].

`/doctor prompt-audit` vs `/skill-doctor` vs plain `/doctor`

Command	Job
`/doctor prompt-audit` / `/checkup prompt-audit`	Instruction-pattern / conflict audit (older-model prompting, stale paths/commands, contradicting files)
`/skill-doctor`	Skill context cost + usage → prune / turn off
`/doctor` / `/checkup` (no subcommand)	Setup checkup: install health, unused skills/MCP/plugins vs context cost, CLAUDE.md trim/migrate, and more

One-line boundary: /claude-api … prompt-audit is a different bundled-skill path (flags older-model instructions in API prompts / skills / tool descriptions; floor v2.1.221+) — out of scope for this Spec.

When to run it

After model upgrades when CLAUDE.md or skills still teach old thinking / tool_choice / computer-tool habits.
When skills, agents, or commands contradict each other or point at stale paths/commands.
When plain /doctor checkup is fine for install health, but you specifically need a prompt-pattern pass.

If permission / auto-mode defaults surprise you after a Claude Code bump, pair with How do I configure Claude Code permissions?. For sharing / nesting instruction files, see How should I share AGENTS.md / CLAUDE.md?.

Pitfalls

Unknown subcommand — upgrade past 2.1.283.
Wrong doctor — /skill-doctor does not audit prompt patterns; plain /doctor does not replace prompt-audit.
Invented flags — only documented behavior: /doctor [prompt-audit [path]]. No third-party blog flags.
Expecting Labs “prompt audit” volume — unmeasured; only thin support KW claude code doctor at volume 50 (KD [GAP]).
Confusing with /claude-api prompt-audit — API-skill path, different job.

FAQ

What version do I need?
Commands docs: prompt-audit requires Claude Code v2.1.283 or later. CHANGELOG adds /doctor prompt-audit (also /checkup prompt-audit) under 2.1.283.

Is /checkup prompt-audit the same?
Yes — /checkup is the documented alias of /doctor.

Does it replace /skill-doctor?
No. Skill-doctor is cost/usage prune; prompt-audit is instruction-pattern audit. Soft bridge: How do I use /skill-doctor?.

Does it edit files automatically?
[GAP] for prompt-audit apply UX. Plain /doctor reports first and asks confirmation before changes — do not invent the same for prompt-audit without a primary cite.

Can I pass a path?
Yes in the signature: /doctor [prompt-audit [path]]. Deep path rules [GAP] if not expanded in docs.

Sources (checked 2026-09-29)

Claude Code CHANGELOG.md — ## 2.1.283: add /doctor prompt-audit / /checkup prompt-audit; improve report lead (stale paths/commands, contradicting files; thinking keywords kept)
Commands reference — /doctor [prompt-audit [path]]; checkup alias; claude doctor read-only install diagnostics; version floor v2.1.283+
Live: /guides/how-do-i-use-claude-code-skill-doctor · /guides/how-do-i-configure-claude-code-permissions · /guides/how-should-i-share-agents-md-claude-md