Audit Output Styles Command

Audit Claude Code output styles for quality, compliance, and usability.

Initialization

Before auditing, initialize the environment:

1. Get the current UTC date for audit timestamps.
2. Capture the project root path for subagent communication.
3. Ensure the temp directory (.claude/temp/) exists.
4. Clean up any stale audit files if the user confirms.

The output-customization skill provides authoritative validation guidance (auto-loaded when this command runs).

What Gets Audited

• Markdown file format (must be .md, not .json)
• YAML frontmatter (name, description, keep-coding-instructions)
• Content structure and clarity
• File naming conventions
• Style switching compatibility

Command Arguments

Argument	Description
(none)	Audit all discoverable output styles
plugin	Only audit plugin output styles
project	Only audit .claude/output-styles/*.md
user	Only audit ~/.claude/output-styles/*.md
all	Audit all scopes explicitly
--force	Audit regardless of modification status

Step 1: Discover Output Styles

Check plugin directories (plugins/*/output-styles/*.md), project directory (.claude/output-styles/*.md), and user directory (~/.claude/output-styles/*.md on Unix, %USERPROFILE%\.claude\output-styles\ on Windows).

Warn about any .json files found (wrong format - output styles must be markdown).

Step 2: Parse Arguments

Parse the scope selector (plugin, project, user, all) and --force flag from command arguments. Filter discovered styles to match the requested scope.

Step 3: Present Audit Plan

Display mode (SMART or FORCE), styles discovered, plugins with styles, and file list with scope.

Step 4: Execute Audits

For each style, spawn the output-style-auditor subagent with the following context:

• Scope (plugin, project, or user)
• Full path to the style file
• Style name (derived from filename)
• Last audit date or "Never audited"
• Current audit date
• Project root path

Run subagents in parallel batches of 3-5.

Subagents write findings to .claude/temp/ as both JSON (for recovery/aggregation) and markdown (for human review). The main conversation thread collects results and updates audit logs using its Write/Edit tools.

Step 5: Final Summary

Report total audited by scope, results, and details table. List format warnings for .json files with remediation (convert to .md).

Important Notes

Frontmatter Requirements

Output styles require YAML frontmatter with name, description, and optionally keep-coding-instructions.

File Naming

Use kebab-case with .md extension (e.g., my-style.md).

Cross-Platform Paths

Platform	User Styles
Unix	~/.claude/output-styles/
Windows	%USERPROFILE%\.claude\output-styles\

Audit Log Location

All audit results are written to .claude/audit/output-styles.md.

Use /audit-log output-styles to view current audit status.

Example Usage

Example 1: Audit All Output Styles

User: /audit-output-styles

Claude: Discovering output styles...

## Audit Plan
**Mode**: SMART
**Styles discovered**: 3
**Plugins with styles**: 2

1. [plugin:claude-ecosystem] concise-coder.md
2. [plugin:soft-skills] code-review-comment.md
3. [project] custom-style.md

[Spawns output-style-auditor subagents]

## Audit Complete
| Scope | Style | Result | Score |
| --- | --- | --- | --- |
| plugin | concise-coder | PASS | 100/100 |
| project | custom-style | PASS | 98/100 |

Example 2: Audit Plugin Styles Only

User: /audit-output-styles plugin
Claude: Auditing plugin output styles only...