Skip to main content
ClaudeWave
EN, English
Slash Command32.8k repo starsupdated today

cleanup-cache

The cleanup-cache slash command removes temporary files and caches from package managers, browsers, development tools, and machine learning frameworks to free disk space. Use this when available storage is low, with the default conservative mode for safe cleanup, the --aggressive flag to include browser and IDE caches, or --maximum flag for Docker and node_modules removal.

Install in Claude Code
Copy
mkdir -p ~/.claude/commands && curl -fsSL https://raw.githubusercontent.com/davila7/claude-code-templates/HEAD/.claude/commands/cleanup-cache.md -o ~/.claude/commands/cleanup-cache.md
Then start a new Claude Code session; the slash command loads automatically.

cleanup-cache.md

# System Cache Cleanup

Clean temporary files and caches to free disk space: $ARGUMENTS

## Current Disk Usage

- **Disk space**: !`df -h / | tail -1`
- **npm cache**: !`du -sh ~/.npm 2>/dev/null || echo "Not found"`
- **Yarn cache**: !`du -sh ~/Library/Caches/Yarn 2>/dev/null || echo "Not found"`
- **Homebrew cache**: !`brew cleanup -n 2>/dev/null | head -5 || echo "Homebrew not installed"`

## Cleanup Options

Based on the arguments provided, execute the appropriate cleanup level:

### Option 1: Conservative Cleanup (default)

Safe cleanup of package manager caches that can be easily rebuilt:

```bash
# Record starting disk space
echo "Starting cleanup..."
df -h / | tail -1 | awk '{print "Before: " $4 " free"}'

# Clean npm cache
echo "Cleaning npm cache..."
npm cache clean --force

# Clean Homebrew
echo "Cleaning Homebrew..."
brew cleanup

# Clean Yarn cache
echo "Cleaning Yarn cache..."
rm -rf ~/Library/Caches/Yarn

# Show results
df -h / | tail -1 | awk '{print "After: " $4 " free"}'
```

### Option 2: Aggressive Cleanup (--aggressive flag)

Includes all conservative cleanup plus browser and development tool caches:

```bash
# Run conservative cleanup first (from Option 1)
npm cache clean --force
brew cleanup
rm -rf ~/Library/Caches/Yarn

# Clean browser caches
echo "Cleaning browser caches..."
rm -rf ~/Library/Caches/Google
rm -rf ~/Library/Caches/com.operasoftware.Opera
rm -rf ~/Library/Caches/Firefox
rm -rf ~/Library/Caches/Mozilla
rm -rf ~/Library/Caches/zen
rm -rf ~/Library/Caches/Arc

# Clean development tool caches
echo "Cleaning development caches..."
rm -rf ~/Library/Caches/JetBrains
rm -rf ~/Library/Caches/pnpm
rm -rf ~/.cache/puppeteer
rm -rf ~/.cache/selenium

# Clean Python/ML caches
echo "Cleaning Python/ML caches..."
rm -rf ~/.cache/uv
rm -rf ~/.cache/huggingface
rm -rf ~/.cache/torch
rm -rf ~/.cache/whisper

# Show results
df -h / | tail -1 | awk '{print "After aggressive cleanup: " $4 " free"}'
```

### Option 3: Maximum Cleanup (--maximum flag)

Includes all aggressive cleanup plus Docker and old node_modules:

```bash
# Run aggressive cleanup first (from Option 2)
npm cache clean --force
brew cleanup
rm -rf ~/Library/Caches/Yarn
rm -rf ~/Library/Caches/{Google,com.operasoftware.Opera,Firefox,Mozilla,zen,Arc,JetBrains,pnpm}
rm -rf ~/.cache/{puppeteer,selenium,uv,huggingface,torch,whisper}

# Clean Docker (if installed)
echo "Cleaning Docker..."
docker system prune -af --volumes 2>/dev/null || echo "Docker not running or not installed"

# List node_modules directories for manual review
echo "Finding node_modules directories..."
echo "Note: Not auto-deleting. Review and delete manually if needed."
find ~ -name "node_modules" -type d -prune 2>/dev/null | head -20

# Show results
df -h / | tail -1 | awk '{print "After maximum cleanup: " $4 " free"}'
```

## Execution Steps

1. **Determine Cleanup Level**
   - No arguments or empty: Run Conservative Cleanup (Option 1)
   - `--aggressive`: Run Aggressive Cleanup (Option 2)
   - `--maximum`: Run Maximum Cleanup (Option 3)

2. **Safety Checks**
   - Verify sufficient permissions
   - Ensure critical applications are closed (browsers for Option 2+)
   - Warn about Docker containers being removed (Option 3)

3. **Execute Cleanup**
   - Run appropriate commands based on the selected option
   - Show progress for each cleanup step
   - Handle errors gracefully (missing directories, permissions)

4. **Report Results**
   - Display disk space before and after
   - Show amount of space recovered
   - List what was cleaned
   - Provide recommendations if more space is needed

## Important Notes

**Conservative Cleanup** (default):
- ✅ Always safe to run
- ✅ Caches rebuild automatically when needed
- ✅ No application impact

**Aggressive Cleanup** (--aggressive):
- ⚠️ Close browsers before running
- ⚠️ Browser caches will rebuild on next use
- ⚠️ ML models will re-download if needed

**Maximum Cleanup** (--maximum):
- ⚠️ Stops and removes all Docker containers/images
- ⚠️ Only deletes node_modules after manual review
- ⚠️ Most impactful but recovers the most space

## Recovery

All cleaned caches are temporary and will rebuild automatically:

- **npm/Yarn**: Rebuilds on next `npm install`
- **Homebrew**: Downloaded on next `brew install`
- **Browsers**: Rebuilds on next browsing session
- **Python/ML**: Re-downloads models on next use
- **Docker**: Pull images again with `docker pull`

## Example Usage

```bash
# Conservative cleanup (default)
/cleanup-cache

# Aggressive cleanup
/cleanup-cache --aggressive

# Maximum cleanup
/cleanup-cache --maximum
```

After cleanup, verify the results and inform the user of:
1. Space freed
2. Current free space
3. What was cleaned
4. Whether additional cleanup is recommended
agent-evaluationSkill

Testing and benchmarking LLM agents including behavioral testing, capability assessment, reliability metrics, and production monitoring—where even top agents achieve less than 50% on real-world benchmarks Use when: agent testing, agent evaluation, benchmark agents, agent reliability, test agent.

agent-expertSubagent

Use this agent when creating specialized Claude Code agents for the claude-code-templates components system. Specializes in agent design, prompt engineering, domain expertise modeling, and agent best practices. Examples: <example>Context: User wants to create a new specialized agent. user: 'I need to create an agent that specializes in React performance optimization' assistant: 'I'll use the agent-expert agent to create a comprehensive React performance agent with proper domain expertise and practical examples' <commentary>Since the user needs to create a specialized agent, use the agent-expert agent for proper agent structure and implementation.</commentary></example> <example>Context: User needs help with agent prompt design. user: 'How do I create an agent that can handle both frontend and backend security?' assistant: 'Let me use the agent-expert agent to design a full-stack security agent with proper domain boundaries and expertise areas' <commentary>The user needs agent development help, so use the agent-expert agent.</commentary></example>

agent-managementSkill

Create, manage, and orchestrate AI agents using the AI Maestro CLI. Use when the user asks to "create agent", "list agents", "delete agent", "hibernate agent", "wake agent", "install plugin", "show agent", "restart agent", or any agent lifecycle management task.

agent-manager-skillSkill

Manage multiple local CLI agents via tmux sessions (start/stop/monitor/assign) with cron-friendly scheduling.

agent-memory-mcpSkill

A hybrid memory system that provides persistent, searchable knowledge management for AI agents (Architecture, Patterns, Decisions).

agent-memory-systemsSkill

Memory is the cornerstone of intelligent agents. Without it, every interaction starts from zero. This skill covers the architecture of agent memory: short-term (context window), long-term (vector stores), and the cognitive architectures that organize them. Key insight: Memory isn't just storage - it's retrieval. A million stored facts mean nothing if you can't find the right one. Chunking, embedding, and retrieval strategies determine whether your agent remembers or forgets. The field is fragm

agent-messagingSkill

Send and receive cryptographically signed messages between AI agents using the Agent Messaging Protocol (AMP). Use when the user asks to "send a message to an agent", "check agent inbox", "message another agent", "reply to a message", "notify an agent", or any inter-agent communication task.

agent-tool-builderSkill

Tools are how AI agents interact with the world. A well-designed tool is the difference between an agent that works and one that hallucinates, fails silently, or costs 10x more tokens than necessary. This skill covers tool design from schema to error handling. JSON Schema best practices, description writing that actually helps the LLM, validation, and the emerging MCP standard that's becoming the lingua franca for AI tools. Key insight: Tool descriptions are more important than tool implementa