Stats
Links
Categories
Claude Code Auditor
Tells you why your Claude Code setup isn't working as well as it should. Scores any Claude Code markdown file — CLAUDE.md, .claude/rules/*.md, SKILL.md, agents/*.md, .claude/commands/*.md, MEMORY.md, .claude/output-styles/*.md, and context files — against Anthropic best practices. Gives you an A–F grade, exact fixes, and a standard shields.io Score Badge for your README.
Most plugin quality improvements are based on intuition ("I feel this is better"). This plugin makes quality measurable with a consistent 100-point scoring rubric derived from Anthropic's official documentation and established community standards.
Installation
You can install this plugin either directly within Claude Code or via your standard terminal.
1. Inside Claude Code (Recommended)
/plugin marketplace add https://github.com/ordinary9843/claude-code-auditor.git
/plugin install code-auditor@claude-code-auditor
2. Via Standard Terminal
claude plugin marketplace add https://github.com/ordinary9843/claude-code-auditor.git
claude plugin install code-auditor@claude-code-auditor
Note: Please restart Claude Code after installation to ensure the plugin loads correctly.
How It Works
The plugin provides two primary commands that auto-detect the target file type. There is no need to manually specify what kind of file you are evaluating:
/code-auditor:review [path] → score a file or directory (read-only)
/code-auditor:fix [path] → review + apply improvements (confirms before writing)
If no path argument is provided, it defaults to the current working directory.
Two precision tiers are available:
- Fast Review (default): Scores using the criteria files in
skills/review/references/. Best for quick feedback on a single file. - Deep Audit: Activated automatically for directory-level audits, or when you ask for a "deep audit" or "detailed review". Handled by the
auditoragent for full reference criteria with cross-file consistency checks.
Supported File Types & Components
| Target | Description |
|---|---|
| Directory | Performs a full weighted audit |
CLAUDE.md | Assesses context file quality (actionability, commands, architecture layout, size limit). |
.claude/rules/*.md | Evaluates rule actionability, scope focus, path targeting, and cross-rule consistency. |
.claude/commands/*.md | Evaluates custom slash command quality (frontmatter, $ARGUMENTS usage, prompt clarity). |
SKILL.md | Evaluates skill rubrics (frontmatter, content, progressive disclosure, structure). |
agents/*.md | Evaluates agent rubrics (frontmatter, role definition, behavioral guidelines). |
MEMORY.md & topic files | Evaluates auto-memory quality (200-line limit, actionability, topic file structure). |
Output styles (.claude/output-styles/*.md) | Evaluates custom output style quality (frontmatter, persona, behavioral rules). |
Context files (template.md, examples/*.md) | Evaluates supporting prompt files (formatting, placeholders, input/output clarity). |
Commands, rules, skills, and output styles must be under
.claude/(project-level) or~/.claude/(global). CLAUDE.md can be placed at the project root or any subdirectory.
Background Hooks
The plugin also includes background hooks that fire automatically to assist your development flow:
- PostToolUse: When you write or edit any Claude Code artifact, this hook suggests running the relevant review/fix command.
- SessionStart: When a Claude Code session begins in a plugin project, it displays available commands.
Both hooks are advisory only (exit 0) and will never block your operations.
Usage Examples
1. Run a Full Plugin Audit
/code-auditor:review .
Example Output:
## Plugin Audit: Project Overall: 64/100 — Grade D
Badge: `[](https://github.com/ordinary9843/claude-code-auditor)`