Skip to main content
skill CX Codex

audit · localixai — Claude Code skill: settings audit

audit is a Claude Code skill that checks project settings for options that waste tokens or have no effect. It also reviews project instructions and builds a token-usage report.

MIT ★ 171 updated 2026-11-17

Install into Claude Code · Plugin marketplace All methods and platforms ↓
/plugin marketplace add localixai/tokendoctor
/plugin install tokendoctor@tokendoctor
Open on GitHub

What audit does

audit runs tokendoctor-audit --json and sorts findings by severity. It reads project memory and instruction files, flags conflicting or unsafe directions, cites file paths and line numbers, and suggests replacement wording. It does not edit files.

The skill then runs tokendoctor-dashboard --open to create a local HTML report from transcripts on the machine. It uses usage figures, not message text, and makes no network requests. To inspect what actually loaded, it can run tokendoctor-selfcheck after the user agrees; that command starts claude -p on Haiku for one request. The audit compares configuration with the docs; it does not measure token savings.

What it helps with

  • find Claude Code settings that are ignored or waste tokens
  • spot conflicts across project memory and instruction files
  • break down token usage across local transcripts
  • check which hooks and skill tier actually loaded

Example prompts for the agent

  • Audit the Claude Code settings in this project.
  • Find conflicting directions in the project memory and instruction files.
  • Build a token-usage report and relate its figures to the findings.

How to install audit

1Plugin marketplace

/plugin marketplace add localixai/tokendoctor
/plugin install tokendoctor@tokendoctor

This installs the whole tokendoctor plugin with all its skills

2Skills CLI (Vercel)

npx skills add localixai/tokendoctor --skill audit -a claude-code

3Manually: put the files in place

~/.claude/skills/audit/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/audit/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about audit

How do I install audit in Claude Code?

Add the marketplace with /plugin marketplace add localixai/tokendoctor, then install the plugin with /plugin install tokendoctor@tokendoctor.

What does audit do?

It checks Claude Code configuration against the documentation, reviews project instructions, and creates a local token-usage report. It does not modify project files.

What is needed to check which settings actually loaded?

Running tokendoctor-selfcheck requires consent. It makes one request by starting claude -p on Haiku. An existing log can instead be read with tokendoctor-selfcheck --log <file>.

Source text

SKILL.md · MIT
---
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 *), Bash(tokendoctor-dashboard *), Bash(tokendoctor-selfcheck --log *), WebFetch(domain:code.claude.com), Read, Glob
argument-hint: [project-dir]
---

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.
2. 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.
3. 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.
4. 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.
5. Review what Claude is told to do, not only how it is configured: read this project's memory
   (`~/.claude/projects/<project path with / as ->/memory/`, its `MEMORY.md` and the files it
   lists) and the instruction files (`~/.claude/CLAUDE.md`, `~/.claude/rules/`, the project's
   `CLAUDE.md` and `.claude/rules/`). Use your own judgment: point out anything there that makes
   Claude spend more than the work needs, contradicts the settings or another instruction, is stale,
   or is unsafe to keep. Quote `file:line` and say how to rewrite it. Where an instruction is
   plainly the person's own choice, show what it costs and leave the choice to them.
6. **Read the docs as they are today.** The audit checked every settings key and `env` variable
   against Claude Code's current settings reference and variable list (`facts.docs` says when they
   were read; null means offline with no copy, so those checks were skipped: say so). To explain a
   finding beyond its detail, or to answer a question about a setting, read its `doc` link: every
   page is served as Markdown at that URL (`…/docs/en/<page>.md`), and
   `https://code.claude.com/docs/llms.txt` indexes them all. Prefer this to memory or to a mirror
   such as context7: it is the text of the current release, while mirrors re-index on their own
   schedule.
7. **See what really loaded.** Findings from a debug log (`facts.debugLog` gives its time) come from a
   `claude --debug` run of the last day. To check now, offer `tokendoctor-selfcheck`: it starts
   `claude -p` once in this project on Haiku, with no saved session and no MCP servers (one small request,
   a few cents at most), and reports which copy of tokendoctor loaded and in which tier, whether the
   built-in guard was seated, mods hooking compaction ahead of it, skipped hooks, the window Claude
   Code really compacts at, and a skill listing over its budget. Run it only after the person says
   yes; `tokendoctor-selfcheck --log <file>` reads a log they already have, at no cost.
8. 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.
9. Build the usage dashboard: run `tokendoctor-dashboard --open`. It reads every transcript on this
   machine (usage figures only, never message text), writes one HTML file with no network use, and
   opens it: spend by day, by kind of token, model, reasoning effort, main thread and each subagent
   type, context size, project, hour of the week, and the largest sessions, with filters. Give the
   path it prints, and tie one or two of its numbers to the findings above (for example the share of
   spend that was the conversation re-read from the cache, or above 200K tokens of context).

© rsaryev · MIT · localixai/tokendoctor

Similar skills

SKILL.md skills catalog →

audit by other authors comes first.

audit jsmastery-pro audit scans codebases to generate and gap fill AGENTS.md context files. Helps bootstrap shared rules for AI assistants on greenfield or legacy repos. CX Codex +1 5,100installs audit educlopez Runs a technical UI audit across accessibility, performance and responsiveness, then hands back a prioritized findings table. CX Codex +1 1,100installs audit calm-north The audit skill walks a site through five layers of SEO review: technical foundation, on-page work, content quality, link profile and competitive position. CX Codex +1 6,400installs audit adobe Audits a website for design, SEO, technical health and AI-search visibility, then turns the findings into a scored report. CX Codex +1 301installs audit aladicf audit runs code-level checks on accessibility, performance, theming, responsive design and anti-patterns. Returns a scored report with a fix plan. CX Codex +1 729installs minimal-run-and-audit lllllllama minimal-run-and-audit is a Claude Code skill that captures and standardizes evidence from deep learning reproduction runs, including inference, evaluation, and smoke tests. CX Codex +1 502,400installs seo-audit coreyhaines31 A skill for Claude Code, Codex, and Cursor that guides technical SEO audits. Diagnoses traffic drops, indexing issues, canonical tags, and multilingual setups. CX Codex +1 257,200installs browser-fingerprint-audit liarjsdev browser-fingerprint-audit audits browser fingerprints for internal contradictions using the liarjs CLI. It spots mismatches between browser JavaScript APIs and edge network data. CX Codex +1 132,900installs security-audit cloudflare security-audit reviews codebases and APIs for vulnerabilities using safe sandboxing. Fits pre-release security reviews, pen-test triage, and architecture checks. CX Codex +1 116,100installs audit-website squirrelscan audit-website is a Claude Code skill that audits a site and helps fix findings in its code. Start it to inspect a website or web app and work through the reported issues. CX Codex +1 75,200installs ponytail-audit DietrichGebert ponytail-audit is a Claude Code skill that audits a repository and ranks bugs, risks, and redundant code in a one-shot report without changing files. CX Codex +1 62,700installs

From the same set6

Project sponsors

Companies that keep this analytics open