Skill v1.0.0

name: audit description: Audit this Claude Code setup for settings that waste tokens or silently do nothing. disable-model-invocation: true allowed-tools: Bash(tokendoctor-audit *) argument-hint: [project-dir] metadata: version: "1.0.0"

Audit the Claude Code configuration for the current project (or $ARGUMENTS if given).

1. Run tokendoctor-audit --json (add --project <dir> when an argument was given). It is read-only

and reports the Claude Code version, what it found, and a list of findings, each with a severity, an explanation and a documentation link.

1. Present the findings grouped by severity: errors first (settings that are wrong or ignored),

then warnings, then info. For each, give one or two sentences in plain words and the doc link. Do not restate the whole detail text.

1. Be honest about limits: the audit checks configuration against documented behaviour. It does

not measure savings, so state no percentages. Point to /usage (usage breakdown and recommendations) and /context (what is loaded now) for measuring.

1. Say which findings have an automatic fix (those with a fixes list) and offer

/tokendoctor fix <finding-id> for them. Never edit files from this skill.

1. If facts.version is null, say the Claude Code version could not be read and that rules which

depend on a minimum version were still applied.