emreyildirim

Claude Config Auditor — Development skill for Claude Code

Development community

Non-destructive linter and cost auditor for Claude Code's .claude/ and CLAUDE.md — measures token cost, audits agent/skill quality.

How to install Claude Config Auditor

This entry records only its repository, not the path inside it, so there is no exact command to give. Open emreyildirim/claude-config-auditor and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

What Claude Config Auditor does

Non-destructive linter and cost auditor for Claude Code's .claude/ and CLAUDE.md — measures token cost, audits agent/skill quality.

Alternatives in Development

Benjamin Plus Skill — Benjamin-Plus: a measured token-efficiency skill for coding agents (−17.9% cost median, quality unchanged) 272 ★
Full Diagnostic — Full health sweep chaining token, naming, component, drift, docs-coverage and system-health audits into one re 194 ★
Decant — Local-first analysis of Claude Code and Codex sessions: token spend, context windows, files touched, and cost 59 ★

README

claude-config-auditor

[![PyPI](https://img.shields.io/pypi/v/claude-config-auditor.svg)](https://pypi.org/project/claude-config-auditor/) [![Python](https://img.shields.io/pypi/pyversions/claude-config-auditor.svg)](https://pypi.org/project/claude-config-auditor/) [![tests](https://github.com/emreyildirim/claude-config-auditor/actions/workflows/tests.yml/badge.svg)](https://github.com/emreyildirim/claude-config-auditor/actions/workflows/tests.yml) [![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)

A **non-destructive** linter and cost auditor for `.claude/` and `CLAUDE.md` — *we annotate, we don't rewrite*. Measures the **token cost** your Claude Code config pays on every session, and audits **agent / skill quality** (missing descriptions, overlapping routes, broken YAML).

Think of it as ESLint for your context window.

Why this exists

Claude Code loads `CLAUDE.md`, every `.claude/agents/*.md`, and every skill's `SKILL.md` into the context window on every session start. That's a **fixed per-session tax** — and most projects don't know how big theirs is.

The ecosystem has a lot of "session handoff" and "state management" tools. It doesn't have a linter for the config itself. This is that linter.

"How many tokens does my CLAUDE.md actually cost?"
"Are two of my agents describing the same job?" (Anthropic's docs say agents are selected based on their description; the exact ranking algorithm isn't published, but overlapping descriptions create routing ambiguity in practice.)
"Is my SKILL.md description too vague for Claude to ever invoke it?"