Skip to content
Development
Command

/audit-deps

Run comprehensive dependency audit

From plugin
safe-agentic-workflow
39524 skills11 agents24 commands
Install
$ npx -y skills add bybren-llc/safe-agentic-workflow --agent claude-code

How it fires

How this command gets triggered: by you, by Claude, or both.

  • Fires itselfClaude auto-loads it when your prompt matches the work.
  • You can call itInvoke it directly when you want it.
  • Slash command/audit-deps

Context preview

What this command does when you run it.

Run comprehensive dependency audit

Command definition

audit-deps.md
description: Run comprehensive dependency audit
allowed-tools: [Read, Write, Edit, Bash, Grep, Glob]

> **๐Ÿ“‹ TEMPLATE**: This command is a template. See "Customization Guide" below to adapt for your infrastructure.

Execute dependency audit to identify optimization opportunities and security issues.

Audit Workflow

1. Security Audit

Check for vulnerabilities:

yarn audit

Report:

  • Critical/High severity issues
  • Packages with known vulnerabilities
  • Recommended upgrades

2. Bundle Analysis

Run bundle analyzer:

ANALYZE=true yarn build

Identify:

  • Largest packages
  • Duplicate dependencies
  • Unused code opportunities

3. Unused Dependencies

Run depcheck:

npx depcheck

Find:

  • Unused dependencies (can remove)
  • Missing dependencies (should add)
  • Dependencies only in devDependencies

4. Outdated Packages

Check for updates:

yarn outdated

Report:

  • Packages with newer versions
  • Major vs minor vs patch updates
  • Breaking change risks

5. Specific Checks

**Icon Libraries** (common bloat):

find . -name "*.tsx" -o -name "*.ts" | xargs grep -h "from.*icons" | sort -u

Analyze:

  • Which icon libraries used
  • Usage patterns
  • Consolidation opportunities

**Large Packages**:

du -sh node_modules/* | sort -hr | head -20

Identify:

  • Top 20 largest packages
  • Unnecessary large dependencies

6. Create Audit Report

Document findings in `docs/agent-outputs/technical-docs/dependency-audit-report-{date}.md`:

# Dependency Audit Report

**Date**: {current-date}
**Scope**: Full dependency audit
**Tools**: yarn audit, depcheck, bundle-analyzer

## Executive Summary

- Total packages: {count}
- Security issues: {count} ({severity})
- Optimization potential: {size} MB
- Quick wins: {count} tickets

## Findings

### 1. Security Issues

- List critical/high issues
- Recommended actions

### 2. Bundle Size Optimization

- Current size: {size}
- Bloat identified: {list}
- Savings potential: {size}

### 3. Unused Dependencies

- Runtime: {list}
- DevDependencies: {list}
- Action: Can remove

### 4. Missing Dependencies

- {list}
- Action: Should add

### 5. Outdated Packages

- Major updates: {list}
- Minor updates: {list}
- Patch updates: {list}

## Recommendations

### Immediate Actions (High Priority)

1. {action}
2. {action}

### Short-term (Medium Priority)

1. {action}
2. {action}

### Long-term (Low Priority)

1. {action}
2. {action}

## Implementation Tickets

Create Linear tickets for each actionable item:

- {{TICKET_PREFIX}}-{number}: {description}

7. Create Linear Tickets

For each significant finding:

  • Create ticket with clear scope
  • Add to backlog
  • Prioritize based on impact
  • Estimate effort

Use MCP:

mcp__{{MCP_LINEAR_SERVER}}__create_issue

Audit Frequency

Run audits:

  • **Monthly**: Quick security check
  • **Quarterly**: Full dependency audit
  • **Before major releases**: Comprehensive audit
  • **After dependency upgrades**: Validation audit

Success Criteria

  • โœ… All audit tools run successfully
  • โœ… Findings documented completely
  • โœ… Tickets created for actionable items
  • โœ… Team has clear prioritization
  • โœ… Baseline established for next audit

This provides systematic approach to dependency management and optimization.

Customization Guide

To adapt this command for your infrastructure, replace these placeholders:

| Placeholder | Description | Example | | ----------------- | ------------------------- | --------------------- | | `{{TICKET_PREFIX}}` | Your Linear ticket prefix | `WOR`, `PROJ`, `TASK` |

Read more
Ships withsafe-agentic-workflow

SAW โ€” SAFe Agentic Workflow AI Agent Harness for Multi-Agent Team Workflows Built on SAFe methodology (Scaled Agile Framework), adapted for AI agent teams (Now With AI-DLC!) Works for any team with repeatable processes: Software, Marketing, Research, Legal, Operations.

Get the whole plugin