From claude-ecosystem
Audits .claude/rules/*.md files for quality, compliance, glob validity, naming, and structure using subagents. Use when creating, validating rules, or troubleshooting loading issues.
npx claudepluginhub melodic-software/claude-code-plugins --plugin claude-ecosystemThis skill is limited to using the following tools:
Audit Claude Code rule files (`.claude/rules/*.md`) for quality and compliance.
Evaluates Claude Code rules in .claude/rules/ directories, validating YAML frontmatter, glob patterns, content quality, organization, and token efficiency for quality audits.
Audits skills and memory files for docs-management delegation compliance in Claude Code projects. Detects hardcoded data like hook events and verifies delegation patterns with smart filtering.
Guides writing .claude/rules/ files Claude follows using golden format, positive framing, and enforceability tests. Use when creating, improving, or reviewing project rules.
Share bugs, ideas, or general feedback.
Audit Claude Code rule files (.claude/rules/*.md) for quality and compliance.
Before auditing, initialize the environment:
.claude/temp/) exists.The memory-management skill provides authoritative validation guidance for rules (auto-loaded when this command runs).
| Argument | Description |
|---|---|
| (none) | Audit all discoverable rule files |
--force | Audit regardless of modification status |
--skip-validation | Skip finding validation (faster, but may include false positives) |
Search for rule files in:
.claude/rules/*.md)~/.claude/rules/*.md)Build a list of discovered rule files with their scope (project or user) and full path.
If no rule files are found, report this and provide guidance on how to create one.
Check if the --force flag is present in the command arguments. Build the audit queue based on discovered files and the force flag.
Display audit mode (SMART or FORCE), rule files discovered, and list each with scope and last modified date.
For each rule file, spawn the memory-component-auditor subagent with the following context:
Run subagents in parallel when multiple rule files exist.
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.
Unless --skip-validation flag is present:
audit-finding-validator agent with:
project_root: The captured project root pathaudit_type: "rule"audit_files: List of .claude/temp/audit-*-rule-*.json file paths.claude/temp/audit-filtered-findings.jsonIf --skip-validation flag is present:
Report total rule files audited, results by scope, and details table. List frontmatter or glob pattern issues with remediation steps.
Include validation statistics (if validation was performed):
Rule files must have valid YAML frontmatter with description and optionally globs fields. The globs field controls which files the rule applies to.
| Location | Purpose |
|---|---|
.claude/rules/*.md | Project-specific rules |
~/.claude/rules/*.md | User-wide rules |
Rules can use glob patterns to apply only to specific files:
---
description: TypeScript coding standards
globs: ["**/*.ts", "**/*.tsx"]
---
All audit results are written to .claude/audit/rules.md.
Use /audit-log rules to view current audit status.
User: /audit-rules
Claude: Discovering rule files...
## Audit Plan
**Mode**: SMART
**Rule files discovered**: 3
1. [project] .claude/rules/typescript.md
2. [project] .claude/rules/security.md
3. [user] ~/.claude/rules/personal-style.md
[Spawns memory-component-auditor subagents]
## Audit Complete
| Scope | Rule File | Result | Score |
| --- | --- | --- | --- |
| project | typescript.md | PASS | 100/100 |
| project | security.md | PASS | 95/100 |
| user | personal-style.md | PASS WITH WARNINGS | 82/100 |
User: /audit-rules --force
Claude: Auditing all rule files (force mode)...