Audits Claude subagent configurations in .claude/agents/ for frontmatter completeness, tool assignment security, privilege risks, and naming consistency.
How this skill is triggered — by the user, by Claude, or both
Slash command
/agent-patterns-plugin:meta-auditopusThis skill is limited to the following tools:
The summary Claude sees in its skill listing — used to decide when to auto-load this skill
- Agent definitions: !`find .claude/agents -name "*.md" -not -name "settings*"`
find .claude/agents -name "*.md" -not -name "settings*"find .claude/agents -maxdepth 1 -name "settings.local.json" -type f.claude/agents/For each agent, verify required fields are present:
Flag issues:
Evaluate tool assignments for security and appropriateness:
Read-only agents (should NOT have write access):
Write-enabled agents (appropriate write access):
Special privileges (validate necessity):
LSP tool assignments (language-specific):
Check for potential security issues:
Overprivileged agents:
Missing restrictions:
Privilege escalation risks:
Validate configuration consistency:
Naming conventions:
Model assignments:
Tool groupings:
Create comprehensive audit report with:
Executive Summary:
Detailed Findings:
Agent-by-Agent Analysis: For each agent, report:
Action Items:
Structure the report as:
# Claude Agent Configuration Audit
## Executive Summary
- **Total Agents**: X
- **Configuration Issues**: Y
- **Security Concerns**: Z
- **Health Rating**: [EXCELLENT|GOOD|NEEDS_WORK|CRITICAL]
## Critical Issues
[List any critical problems requiring immediate fix]
## Agent Analysis Table
| Agent | Model | Tools | Color | Status | Notes |
| ---------- | ----- | -------- | ----- | --------- | ------ |
| agent-name | ✅/❌ | ✅/⚠️/❌ | ✅/❌ | PASS/FAIL | Issues |
## Security Assessment
[Tool privilege analysis and security concerns]
## Recommendations
[Prioritized action items with file paths]
## Detailed Findings
[Per-agent breakdown with specific issues]
Tool access principles:
Configuration standards:
If --verbose flag is provided:
npx claudepluginhub laurigates/claude-plugins --plugin agent-patterns-pluginAudits Claude Code subagents for YAML frontmatter validity, naming conventions, description quality, tool configs, and model selection. Runs smart audits on modified/stale agents or forces all with flags like --plugin-only.
Audits .claude/ config for cross-references, permissions, inventory drift, model tiers, docs freshness. Auto-fixes issues at high/medium/all severity levels or upgrades with verification and A/B testing.
Audits agent lifecycles in Claude Code plugins, validating execution capabilities against configs via 8 semantic audits on alignments, skill loading, contracts, prompts, tools, dead agents, and patterns. Writes reports to .claude/audits/.