### Workflow Example: Start developing

Source: https://github.com/anthropics/claude-code/blob/main/plugins/agent-sdk-dev/README.md

Commands to set the API key and run the agent after project setup.

```bash
# Set your API key
echo "ANTHROPIC_API_KEY=your_key_here" > .env

# Run your agent
npm start
```

--------------------------------

### Usage

Source: https://github.com/anthropics/claude-code/blob/main/plugins/plugin-dev/skills/plugin-structure/examples/minimal-plugin.md

Example of how to invoke the '/hello' command after installing the plugin and its expected output.

```bash
$ claude
> /hello
Hello! This is a simple command from the hello-world plugin.

Use this as a starting point for building more complex plugins.

Executed at: 2025-01-15 14:30:22 UTC
```

--------------------------------

### Test Plugin Commands with Plugin Installed

Source: https://github.com/anthropics/claude-code/blob/main/plugins/plugin-dev/skills/command-development/examples/plugin-commands.md

Example of how to test a plugin command after installing the plugin.

```bash
cd /path/to/plugin
claude /command-name args
```

--------------------------------

### Example: /new-sdk-app customer-support-agent

Source: https://github.com/anthropics/claude-code/blob/main/plugins/agent-sdk-dev/README.md

Demonstrates creating a new Agent SDK project for a customer support agent, including setup and verification steps.

```bash
/new-sdk-app customer-support-agent
# 
# Creates a new Agent SDK project for a customer support agent
# 
# Sets up TypeScript or Python environment
# 
# Installs latest SDK version
# 
# Verifies the setup automatically
```

--------------------------------

### Using yq for YAML Parsing

Source: https://github.com/anthropics/claude-code/blob/main/plugins/plugin-dev/skills/plugin-settings/references/parsing-techniques.md

Example demonstrating how to use `yq` for more robust YAML parsing, including installation instructions.

```bash
# Install: brew install yq

# Parse YAML properly
FRONTMATTER=$(sed -n '/^---$/,/^---$/{ /^---$/d; p; }' "$FILE")

# Extract fields with yq
ENABLED=$(echo "$FRONTMATTER" | yq '.enabled')
MODE=$(echo "$FRONTMATTER" | yq '.mode')
LIST=$(echo "$FRONTMATTER" | yq -o json '.list_field')
```

--------------------------------

### Environment variable example

Source: https://github.com/anthropics/claude-code/blob/main/plugins/agent-sdk-dev/commands/new-sdk-app.md

Example content for a .env.example file to set the Anthropic API key.

```env
ANTHROPIC_API_KEY=your_api_key_here
```

--------------------------------

### Installation Instructions

Source: https://github.com/anthropics/claude-code/blob/main/plugins/pr-review-toolkit/README.md

Commands to install the plugin from a personal marketplace.

```bash
/plugins
# Find "pr-review-toolkit"
# Install
```

--------------------------------

### Deployment Command Usage

Source: https://github.com/anthropics/claude-code/blob/main/plugins/plugin-dev/skills/command-development/examples/simple-commands.md

Example usage of the /deploy command.

```bash
> /deploy staging v1.2.3
```

--------------------------------

### Example Block Format

Source: https://github.com/anthropics/claude-code/blob/main/plugins/plugin-dev/skills/agent-development/references/triggering-examples.md

The standard format for triggering examples.

```markdown
<example>
Context: [Describe the situation - what led to this interaction]
user: "[Exact user message or request]"
assistant: "[How Claude should respond before triggering]"
<commentary>
[Explanation of why this agent should be triggered in this scenario]
</commentary>
assistant: "[How Claude triggers the agent - usually 'I'll use the [agent-name] agent...']"
</example>
```

--------------------------------

### Debugging Commands

Source: https://github.com/anthropics/claude-code/blob/main/plugins/plugin-dev/skills/plugin-structure/examples/advanced-plugin.md

Kubectl commands for getting pod details, logs, executing commands, and checking resource usage.

```bash
kubectl describe pod <name>
kubectl logs <name>
kubectl logs <name> --previous  # logs from crashed container
```

```bash
kubectl exec -it <name> -- /bin/sh
kubectl exec <name> -- env
```

```bash
kubectl top nodes
kubectl top pods
```

--------------------------------

### Quick Start Command

Source: https://github.com/anthropics/claude-code/blob/main/plugins/ralph-wiggum/README.md

Example command to start a Ralph loop for building a REST API for todos with a completion promise and iteration limit.

```bash
/ralph-loop "Build a REST API for todos. Requirements: CRUD operations, input validation, tests. Output <promise>COMPLETE</promise> when done." --completion-promise "COMPLETE" --max-iterations 50
```

--------------------------------

### Hardcoding plugin paths

Source: https://github.com/anthropics/claude-code/blob/main/plugins/plugin-dev/skills/command-development/examples/plugin-commands.md

Shows the problem with hardcoding absolute plugin paths, which can break on different installations, and the correct approach using `${CLAUDE_PLUGIN_ROOT}` for portability.

```markdown
# Wrong - breaks on different installations
@/home/user/.claude/plugins/my-plugin/config.json

# Correct - works everywhere
@${CLAUDE_PLUGIN_ROOT}/config.json
```

--------------------------------

### Documentation Generator Command Usage

Source: https://github.com/anthropics/claude-code/blob/main/plugins/plugin-dev/skills/command-development/examples/simple-commands.md

Example usage of the /document command.

```bash
> /document src/api/users.ts
```

--------------------------------

### Comparison Command Usage

Source: https://github.com/anthropics/claude-code/blob/main/plugins/plugin-dev/skills/command-development/examples/simple-commands.md

Example usage of the /compare-files command.

```bash
> /compare-files src/old-api.ts src/new-api.ts
```

--------------------------------

### Pod Security Example

Source: https://github.com/anthropics/claude-code/blob/main/plugins/plugin-dev/skills/plugin-structure/examples/advanced-plugin.md

Example configuration for applying pod security best practices like running as non-root, read-only filesystem, and dropping capabilities.

```yaml
securityContext:
  runAsNonRoot: true
  runAsUser: 1000
  readOnlyRootFilesystem: true
  capabilities:
    drop:
      - ALL
```

--------------------------------

### Install from claude-code-marketplace

Source: https://github.com/anthropics/claude-code/blob/main/plugins/plugin-dev/README.md

Command to install the plugin-dev plugin from the marketplace.

```bash
/plugin install plugin-dev@claude-code-marketplace
```

--------------------------------

### Install Plugin

Source: https://github.com/anthropics/claude-code/blob/main/plugins/security-guidance/README.md

Command to install the security-guidance plugin using the Claude Code CLI.

```bash
/plugin install security-guidance@claude-plugins-official
```

--------------------------------

### Good Example: Referencing Additional Resources

Source: https://github.com/anthropics/claude-code/blob/main/plugins/plugin-dev/skills/skill-development/SKILL.md

Example of a SKILL.md file that clearly references additional resources like reference files and examples.

```markdown
# SKILL.md

[Core content]

## Additional Resources

### Reference Files
- **`references/patterns.md`** - Detailed patterns
- **`references/advanced.md`** - Advanced techniques

### Examples
- **`examples/script.sh`** - Working example
```

--------------------------------

### Regex Examples

Source: https://github.com/anthropics/claude-code/blob/main/plugins/hookify/skills/writing-rules/SKILL.md

Examples demonstrating common regex metacharacters and their matching behavior.

```regex
rm\s+-rf         Matches: rm -rf, rm  -rf
console\.log\(   Matches: console.log(
(eval|exec)\(    Matches: eval( or exec(
chmod\s+777      Matches: chmod 777, chmod  777
API_KEY\s*=      Matches: API_KEY=, API_KEY =
```

--------------------------------

### Code Review Command Usage

Source: https://github.com/anthropics/claude-code/blob/main/plugins/plugin-dev/skills/command-development/examples/simple-commands.md

Example usage of the /review command.

```bash
> /review
```

--------------------------------

### Test Command with File Argument Usage

Source: https://github.com/anthropics/claude-code/blob/main/plugins/plugin-dev/skills/command-development/examples/simple-commands.md

Example usage of the /test-file command.

```bash
> /test-file src/utils/helpers.test.ts
```

--------------------------------

### Multi-Script Workflow

Source: https://github.com/anthropics/claude-code/blob/main/plugins/plugin-dev/skills/command-development/examples/plugin-commands.md

Orchestrate build, test, and deploy workflow

```markdown
---
description: Execute complete release workflow
argument-hint: [version]
allowed-tools: Bash(*), Read
---

Executing release workflow for version $1:

**Step 1 - Pre-release validation:**
!`bash ${CLAUDE_PLUGIN_ROOT}/scripts/pre-release-check.sh $1`

**Step 2 - Build artifacts:**
!`bash ${CLAUDE_PLUGIN_ROOT}/scripts/build-release.sh $1`

**Step 3 - Run test suite:**
!`bash ${CLAUDE_PLUGIN_ROOT}/scripts/run-tests.sh`

**Step 4 - Package release:**
!`bash ${CLAUDE_PLUGIN_ROOT}/scripts/package.sh $1`

Review all step outputs and report:
1. Any failures or warnings
2. Build artifacts location
3. Test results summary
4. Next steps for deployment
5. Rollback plan if needed
```

--------------------------------

### Self-Correction (Good Example)

Source: https://github.com/anthropics/claude-code/blob/main/plugins/ralph-wiggum/README.md

Example of a prompt guiding the AI through a Test-Driven Development (TDD) process for self-correction.

```markdown
Implement feature X following TDD:
1. Write failing tests
2. Implement feature
3. Run tests
4. If any fail, debug and fix
5. Refactor if needed
6. Repeat until all green
7. Output: <promise>COMPLETE</promise>
```

--------------------------------

### Script-Based Analysis

Source: https://github.com/anthropics/claude-code/blob/main/plugins/plugin-dev/skills/command-development/examples/plugin-commands.md

Run comprehensive analysis using multiple plugin scripts

```markdown
---
description: Complete code audit using plugin suite
argument-hint: [directory]
allowed-tools: Bash(*)
model: sonnet
---

Running complete audit on $1:

**Security scan:**
!`bash ${CLAUDE_PLUGIN_ROOT}/scripts/security-scan.sh $1`

**Performance analysis:**
!`bash ${CLAUDE_PLUGIN_ROOT}/scripts/perf-analyze.sh $1`

**Best practices check:**
!`bash ${CLAUDE_PLUGIN_ROOT}/scripts/best-practices.sh $1`

Analyze all results and create comprehensive report including:
- Critical issues requiring immediate attention
- Performance optimization opportunities
- Security vulnerabilities and fixes
- Overall health score and recommendations
```

--------------------------------

### Get Pod Logs

Source: https://github.com/anthropics/claude-code/blob/main/plugins/plugin-dev/skills/plugin-structure/examples/advanced-plugin.md

JavaScript code to get logs for a specific pod and container using the `k8s_get_logs` tool.

```javascript
const logs = await tools.k8s_get_logs({ pod: 'api-xyz', container: 'app' })
```

--------------------------------

### Cover Different Phrasings

Source: https://github.com/anthropics/claude-code/blob/main/plugins/plugin-dev/skills/agent-development/references/triggering-examples.md

Examples demonstrating how to cover various user phrasings for the same request.

```markdown
<example>
user: "Review my code"
[...]
</example>

<example>
user: "Can you check my implementation?"
[...]
</example>

<example>
user: "Look over these changes"
[...]
</example>
```

--------------------------------

### Git Status Summary Command Usage

Source: https://github.com/anthropics/claude-code/blob/main/plugins/plugin-dev/skills/command-development/examples/simple-commands.md

Example usage of the /git-status command.

```bash
> /git-status
```

--------------------------------

### Verify SDK Installation (Python)

Source: https://github.com/anthropics/claude-code/blob/main/plugins/agent-sdk-dev/commands/new-sdk-app.md

Command to verify the installed version of the Claude Agent SDK in a Python project.

```bash
pip show claude-agent-sdk
```

--------------------------------

### Verify SDK Installation (TypeScript)

Source: https://github.com/anthropics/claude-code/blob/main/plugins/agent-sdk-dev/commands/new-sdk-app.md

Command to verify the installed version of the Claude Agent SDK in a TypeScript project.

```bash
npm list @anthropic-ai/claude-agent-sdk
```

--------------------------------

### Command with Smart Defaults

Source: https://github.com/anthropics/claude-code/blob/main/plugins/plugin-dev/skills/command-development/references/marketplace-considerations.md

Example demonstrating how to use shell parameter expansion for sensible defaults and how users can override them via arguments or a configuration file.

```markdown
---
description: Command with smart defaults
---

# Smart Defaults

Configuration:
- Format: ${FORMAT:-json}  # Defaults to json
- Output: ${OUTPUT:-stdout}  # Defaults to stdout
- Verbose: ${VERBOSE:-false}  # Defaults to false

These defaults work for 80% of use cases.

Override with arguments:
  /command --format yaml --output file.txt --verbose

Or set in .claude/plugin-name.local.md:
```yaml
---
format: yaml
output: custom.txt
verbose: true
---
```
```

--------------------------------

### Install Claude Agent SDK (Python)

Source: https://github.com/anthropics/claude-code/blob/main/plugins/agent-sdk-dev/commands/new-sdk-app.md

Command to install the latest version of the Claude Agent SDK for Python projects.

```bash
pip install claude-agent-sdk
```

--------------------------------

### Template-Based Generation

Source: https://github.com/anthropics/claude-code/blob/main/plugins/plugin-dev/skills/command-development/examples/plugin-commands.md

Generate documentation following plugin template

```markdown
---
description: Generate API documentation from template
argument-hint: [api-file]
---

Template structure: @${CLAUDE_PLUGIN_ROOT}/templates/api-documentation.md

API implementation: @$1

Generate complete API documentation following the template format above.

Ensure documentation includes:
- Endpoint descriptions with HTTP methods
- Request/response schemas
- Authentication requirements
- Error codes and handling
- Usage examples with curl commands
- Rate limiting information

Format output as markdown suitable for README or docs site.
```

--------------------------------

### Install Claude Agent SDK (TypeScript)

Source: https://github.com/anthropics/claude-code/blob/main/plugins/agent-sdk-dev/commands/new-sdk-app.md

Command to install the latest version of the Claude Agent SDK for TypeScript projects.

```bash
npm install @anthropic-ai/claude-agent-sdk@latest
```

--------------------------------

### Python Type Hints

Source: https://github.com/anthropics/claude-code/blob/main/plugins/plugin-dev/skills/plugin-structure/examples/standard-plugin.md

Demonstrates the use of type hints for function signatures in Python.

```python
# Good
def calculate_average(numbers: list[float]) -> float:
    return sum(numbers) / len(numbers)

# Bad
def calculate_average(numbers):
    return sum(numbers) / len(numbers)
```

--------------------------------

### Interactive Bug Fix

Source: https://github.com/anthropics/claude-code/blob/main/plugins/ralph-wiggum/commands/help.md

An example command to start a Ralph loop for an interactive bug fix.

```bash
/ralph-loop "Fix the token refresh logic in auth.ts. Output <promise>FIXED</promise> when all tests pass." --completion-promise "FIXED" --max-iterations 10
```

--------------------------------

### Version and Changelog Example

Source: https://github.com/anthropics/claude-code/blob/main/plugins/plugin-dev/skills/command-development/references/documentation-patterns.md

An example of how to structure versioning, changelog, migration notes, deprecation warnings, and known issues within a documentation block.

```markdown
<!--
VERSION: 2.1.0
LAST UPDATED: 2025-01-15
AUTHOR: DevOps Team

CHANGELOG:
  v2.1.0 (2025-01-15):
    - Added support for YAML configuration
    - Improved error messages
    - Fixed bug with special characters in arguments

  v2.0.0 (2025-01-01):
    - BREAKING: Changed argument order
    - BREAKING: Removed deprecated --old-flag
    - Added new validation checks
    - Migration guide: /migration-v2

  v1.5.0 (2024-12-15):
    - Added --verbose flag
    - Improved performance by 50%

  v1.0.0 (2024-12-01):
    - Initial stable release

MIGRATION NOTES:
  From v1.x to v2.0:
    Old: /command arg1 arg2 --old-flag
    New: /command arg2 arg1

  The --old-flag is removed. Use --new-flag instead.

DEPRECATION WARNINGS:
  - The --legacy-mode flag is deprecated as of v2.1.0
  - Will be removed in v3.0.0 (estimated 2025-06-01)
  - Use --modern-mode instead

KNOWN ISSUES:
  - #123: Slow performance with large files (workaround: use --stream flag)
  - #456: Special characters in Windows (fix planned for v2.2.0)
-->
```

--------------------------------

### Guided Workflow Command Usage

Source: https://github.com/anthropics/claude-code/blob/main/plugins/plugin-dev/README.md

Examples of how to use the /plugin-dev:create-plugin command, with and without an optional description.

```bash
/plugin-dev:create-plugin [optional description]

# Examples:
/plugin-dev:create-plugin
/plugin-dev:create-plugin A plugin for managing database migrations
```

--------------------------------

### Documenting Token Requirements

Source: https://github.com/anthropics/claude-code/blob/main/plugins/plugin-dev/skills/mcp-integration/references/authentication.md

Example of documenting token setup, obtaining tokens, and permissions in a README file.

```markdown
## Setup

### Required Environment Variables

Set these environment variables before using the plugin:

```bash
export API_TOKEN="your-token-here"
export API_SECRET="your-secret-here"
```

### Obtaining Tokens

1. Visit https://api.example.com/tokens
2. Create a new API token
3. Copy the token and secret
4. Set environment variables as shown above

### Token Permissions

The API token needs the following permissions:
- Read access to resources
- Write access for creating items
- Delete access (optional, for cleanup operations)

```

--------------------------------

### Using Agents

Source: https://github.com/anthropics/claude-code/blob/main/plugins/plugin-dev/skills/plugin-structure/examples/standard-plugin.md

Example of using a code-reviewer agent to review changes in a specific file, detailing critical issues and suggestions.

```shell
> Review the changes in src/api/users.js

[code-reviewer agent selected automatically]

Code Review: src/api/users.js

Critical Issues:
  1. Line 45: SQL injection vulnerability
     - Using string concatenation for SQL query
     - Replace with parameterized query
     - Priority: CRITICAL

  2. Line 67: Missing error handling
     - Database query without try/catch
     - Could crash server on DB error
     - Priority: HIGH

Suggestions:
  1. Line 23: Consider caching user data
     - Frequent DB queries for same users
     - Add Redis caching layer
     - Priority: MEDIUM
```

--------------------------------

### Example command

Source: https://github.com/anthropics/claude-code/blob/main/plugins/plugin-dev/skills/mcp-integration/references/tool-usage.md

A full command example demonstrating how to define allowed tools and provide instructions for searching and creating Asana tasks.

```markdown
---
description: Search and create Asana tasks
allowed-tools: [
  "mcp__plugin_asana_asana__asana_search_tasks",
  "mcp__plugin_asana_asana__asana_create_task"
]
---

# Asana Task Management

## Searching Tasks

To search for tasks:
1. Use mcp__plugin_asana_asana__asana_search_tasks
2. Provide search filters (assignee, project, etc.)
3. Display results to user

## Creating Tasks

To create a task:
1. Gather task details:
   - Title (required)
   - Description
   - Project
   - Assignee
   - Due date
2. Use mcp__plugin_asana_asana__asana_create_task
3. Show confirmation with task link
```

--------------------------------

### Example quick-check.sh script

Source: https://github.com/anthropics/claude-code/blob/main/plugins/plugin-dev/skills/hook-development/references/advanced.md

A bash script for immediate approval of safe commands in a multi-stage validation setup.

```bash
#!/bin/bash
input=$(cat)
command=$(echo "$input" | jq -r '.tool_input.command')

# Immediate approval for safe commands
if [[ "$command" =~ ^(ls|pwd|echo|date|whoami)$ ]]; then
  exit 0
fi

# Let prompt hook handle complex cases
exit 0
```

--------------------------------

### Unsupported Beta Header Comment

Source: https://github.com/anthropics/claude-code/blob/main/plugins/claude-opus-4-5-migration/skills/claude-opus-4-5-migration/SKILL.md

Example of how to add a comment when the context-1m-2025-08-07 beta header is not supported with Opus 4.5.

```python
# Note: 1M context beta (context-1m-2025-08-07) not yet supported with Opus 4.5
```

--------------------------------

### Complete Example

Source: https://github.com/anthropics/claude-code/blob/main/plugins/plugin-dev/skills/plugin-settings/references/parsing-techniques.md

This comprehensive bash script demonstrates robust settings handling by parsing frontmatter from a settings file, applying defaults, performing validation, and recovering from errors.

```bash
#!/bin/bash
set -euo pipefail

# Configuration
SETTINGS_FILE=".claude/my-plugin.local.md"

# Quick exit if not configured
if [[ ! -f "$SETTINGS_FILE" ]]; then
  # Use defaults
  ENABLED=true
  MODE=standard
  MAX_SIZE=1000000
else
  # Parse frontmatter
  FRONTMATTER=$(sed -n '/^---$/,/^---$/{ /^---$/d; p; }' "$SETTINGS_FILE")

  # Extract fields with defaults
  ENABLED=$(echo "$FRONTMATTER" | grep '^enabled:' | sed 's/enabled: *//')
  ENABLED=${ENABLED:-true}

  MODE=$(echo "$FRONTMATTER" | grep '^mode:' | sed 's/mode: *//' | sed 's/^"\(.*\)"$/\1/')
  MODE=${MODE:-standard}

  MAX_SIZE=$(echo "$FRONTMATTER" | grep '^max_size:' | sed 's/max_size: *//')
  MAX_SIZE=${MAX_SIZE:-1000000}

  # Validate values
  if [[ "$ENABLED" != "true" ]] && [[ "$ENABLED" != "false" ]]; then
    echo "⚠️  Invalid enabled value, using default" >&2
    ENABLED=true
  fi

  if ! [[ "$MAX_SIZE" =~ ^[0-9]+$ ]]; then
    echo "⚠️  Invalid max_size, using default" >&2
    MAX_SIZE=1000000
  fi
fi

# Quick exit if disabled
if [[ "$ENABLED" != "true" ]]; then
  exit 0
fi

# Use configuration
echo "Configuration loaded: mode=$MODE, max_size=$MAX_SIZE" >&2

# Apply logic based on settings
case "$MODE" in
  strict)
    # Strict validation
    ;;
  standard)
    # Standard validation
    ;;
  lenient)
    # Lenient validation
    ;;
esac
```

--------------------------------

### Running Commands

Source: https://github.com/anthropics/claude-code/blob/main/plugins/plugin-dev/skills/plugin-structure/examples/standard-plugin.md

Example of running linter and test commands via the Claude interface, showing output for issues, warnings, and test results.

```shell
$ claude
> /lint
Running linter checks...

Critical Issues (2):
  src/api/users.js:45 - SQL injection vulnerability
  src/utils/helpers.js:12 - Unhandled promise rejection

Warnings (5):
  src/components/Button.tsx:23 - Missing PropTypes
  ...

Style Suggestions (8):
  src/index.js:1 - Use const instead of let
  ...

> /test
Running test suite...

Test Results:
  ✓ 245 passed
  ✗ 3 failed
  ○ 2 skipped

Coverage: 87.3%

Untested Files:
  src/utils/cache.js - 0% coverage
  src/api/webhooks.js - 23% coverage

Failed Tests:
  1. User API › GET /users › should handle pagination
     Expected 200, received 500
  ...
```

--------------------------------

### commands/hello.md

Source: https://github.com/anthropics/claude-code/blob/main/plugins/plugin-dev/skills/plugin-structure/examples/minimal-plugin.md

The content of the 'hello' command markdown file, including front matter and implementation details.

```markdown
---
name: hello
description: Prints a friendly greeting message
---

# Hello Command

Print a friendly greeting to the user.

## Implementation

Output the following message to the user:

> Hello! This is a simple command from the hello-world plugin.
>
> Use this as a starting point for building more complex plugins.

Include the current timestamp in the greeting to show the command executed successfully.
```

--------------------------------

### Message for no configured Hookify rules

Source: https://github.com/anthropics/claude-code/blob/main/plugins/hookify/commands/list.md

The message displayed when no Hookify rules are found, providing instructions on how to get started with creating rules.

```markdown
## No Hookify Rules Configured

You haven't created any hookify rules yet.

To get started:
1. Use `/hookify` to analyze conversation and create rules
2. Or manually create `.claude/hookify.my-rule.local.md` files
3. See `/hookify:help` for documentation

Example:
```
/hookify Warn me when I use console.log
```

Check `${CLAUDE_PLUGIN_ROOT}/examples/` for example rule files.
```

--------------------------------

### Deployment Command Definition

Source: https://github.com/anthropics/claude-code/blob/main/plugins/plugin-dev/skills/command-development/examples/simple-commands.md

File: .claude/commands/deploy.md

```markdown
---
description: Deploy to specified environment
argument-hint: [environment] [version]
allowed-tools: Bash(kubectl:*), Read
---

Deploy to $1 environment using version $2

**Pre-deployment Checks:**
1. Verify $1 configuration exists
2. Check version $2 is valid
3. Verify cluster accessibility: !`kubectl cluster-info`

**Deployment Steps:**
1. Update deployment manifest with version $2
2. Apply configuration to $1
3. Monitor rollout status
4. Verify pod health
5. Run smoke tests

**Rollback Plan:**
Document current version for rollback if issues occur.

Proceed with deployment? (yes/no)
```

--------------------------------

### Progressive Disclosure

Source: https://github.com/anthropics/claude-code/blob/main/plugins/plugin-dev/skills/command-development/references/interactive-commands.md

Example demonstrating how to use AskUserQuestion to implement progressive disclosure, offering different setup paths based on user choice.

```markdown
# Start Simple, Get Detailed as Needed ## Question 1: Setup Type Use AskUserQuestion: Question: "How would you like to set up?" Header: "Setup type" Options: - Quick (Use recommended defaults) - Custom (Configure all options) - Guided (Step-by-step with explanations) If "Quick":   Apply defaults, minimal questions If "Custom":   Ask all available configuration questions If "Guided":   Ask questions with extra explanation   Provide recommendations along the way
```

--------------------------------

### Actionable Instructions Examples

Source: https://github.com/anthropics/claude-code/blob/main/plugins/plugin-dev/skills/agent-development/references/system-prompt-design.md

Examples demonstrating concrete steps vs. vague instructions in system prompts.

```text
✅ Read the file using the Read tool, then search for patterns using Grep
❌ Analyze the code

✅ Generate test file at test/path/to/file.test.ts
❌ Create tests
```

--------------------------------

### README Documentation Template

Source: https://github.com/anthropics/claude-code/blob/main/plugins/plugin-dev/skills/command-development/references/documentation-patterns.md

A comprehensive template for structuring a command's companion README file, covering installation, usage, arguments, examples, configuration, requirements, troubleshooting, contributing, license, and support.

```markdown
# Command Name

Brief description of what the command does.

## Installation

This command is part of the [plugin-name] plugin.

Install with:
```
/plugin install plugin-name
```

## Usage

Basic usage:
```
/command-name [arg1] [arg2]
```

## Arguments

- `arg1`: Description (required)
- `arg2`: Description (optional, defaults to X)

## Examples

### Example 1: Basic Usage
```
/command-name value1 value2
```

Description of what happens.

### Example 2: Advanced Usage
```
/command-name value1 --option
```

Description of advanced feature.

## Configuration

Optional configuration file: `.claude/command-name.local.md`

```markdown
---
default_arg: value
enable_feature: true
---
```

## Requirements

- Git 2.x or later
- jq (for JSON processing)
- Node.js 14+ (optional, for advanced features)

## Troubleshooting

### Issue: Command not found

**Solution:** Ensure plugin is installed and enabled.

### Issue: Permission denied

**Solution:** Check file permissions and allowed-tools setting.

## Contributing

Contributions welcome! See [CONTRIBUTING.md](CONTRIBUTING.md).

## License

MIT License - See [LICENSE](LICENSE).

## Support

- Issues: https://github.com/user/plugin/issues
- Docs: https://docs.example.com
- Email: support@example.com
```

--------------------------------

### Example workflow

Source: https://github.com/anthropics/claude-code/blob/main/plugins/code-review/README.md

Demonstrates how to run /code-review locally and post as a PR comment.

```bash
# On a PR branch, run locally (outputs to terminal):
/code-review

# Post review as PR comment:
/code-review --comment

# Claude will:
# - Launch 4 review agents in parallel
# - Score each issue for confidence
# - Output issues ≥80 confidence (to terminal or PR depending on flag)
# - Skip if no high-confidence issues found
```

--------------------------------

### Directory Structure

Source: https://github.com/anthropics/claude-code/blob/main/plugins/plugin-dev/skills/plugin-structure/examples/minimal-plugin.md

The directory structure for the minimal 'hello-world' plugin.

```text
hello-world/
├── .claude-plugin/
│   └── plugin.json
└── commands/
    └── hello.md
```

--------------------------------

### hooks/hooks.json

Source: https://github.com/anthropics/claude-code/blob/main/plugins/plugin-dev/skills/plugin-structure/examples/advanced-plugin.md

This JSON configuration defines various hooks that trigger commands or prompts at different stages of plugin execution, such as before tool use, after tool use, on session stop, and on session start. Each hook includes a matcher to determine when it applies and a command or prompt to execute, along with a timeout.

```json
{
  "PreToolUse": [
    {
      "matcher": "Write|Edit",
      "hooks": [
        {
          "type": "command",
          "command": "bash ${CLAUDE_PLUGIN_ROOT}/hooks/scripts/security/scan-secrets.sh",
          "timeout": 30
        }
      ]
    },
    {
      "matcher": "Bash",
      "hooks": [
        {
          "type": "prompt",
          "prompt": "Evaluate if this bash command is safe for production environment. Check for destructive operations, missing safeguards, and potential security issues. Commands should be idempotent and reversible.",
          "timeout": 20
        }
      ]
    }
  ],
  "PostToolUse": [
    {
      "matcher": "Bash",
      "hooks": [
        {
          "type": "command",
          "command": "bash ${CLAUDE_PLUGIN_ROOT}/hooks/scripts/workflow/update-status.sh",
          "timeout": 15
        }
      ]
    }
  ],
  "Stop": [
    {
      "matcher": ".*",
      "hooks": [
        {
          "type": "command",
          "command": "bash ${CLAUDE_PLUGIN_ROOT}/hooks/scripts/quality/check-config.sh",
          "timeout": 45
        },
        {
          "type": "command",
          "command": "bash ${CLAUDE_PLUGIN_ROOT}/hooks/scripts/workflow/notify-team.sh",
          "timeout": 30
        }
      ]
    }
  ],
  "SessionStart": [
    {
      "matcher": ".*",
      "hooks": [
        {
          "type": "command",
          "command": "bash ${CLAUDE_PLUGIN_ROOT}/hooks/scripts/security/validate-permissions.sh",
          "timeout": 20
        }
      ]
    }
  ]
}
```

--------------------------------

### Example-Driven Documentation

Source: https://github.com/anthropics/claude-code/blob/main/plugins/plugin-dev/skills/command-development/references/documentation-patterns.md

Illustrates a documentation style where examples are presented first, showing input, command, and output for different transformations.

```shell
---description: Example-heavy command---# Transformation Command## What This DoesTransforms data from one format to another.## Examples First### Example 1: JSON to YAML**Input:** `data.json````json{"name": "test", "value": 42}```**Command:** `/transform data.json yaml`**Output:** `data.yaml````yamlname: testvalue: 42```### Example 2: CSV to JSON**Input:** `data.csv````csvname,valuetest,42```**Command:** `/transform data.csv json`**Output:** `data.json````json[{"name": "test", "value": "42"}]```### Example 3: With Options**Command:** `/transform data.json yaml --pretty --sort-keys`**Result:** Formatted YAML with sorted keys---## Your TransformationFile: $1Format: $2[Perform transformation...]
```

```json
{"name": "test", "value": 42}
```

```yaml
name: test
value: 42
```

```csv
name,value
test,42
```

```json
[{"name": "test", "value": "42"}]
```

--------------------------------

### Workflow Example: Create a new project

Source: https://github.com/anthropics/claude-code/blob/main/plugins/agent-sdk-dev/README.md

Command to initiate the creation of a new code-reviewer-agent project.

```bash
/new-sdk-app code-reviewer-agent
```

--------------------------------

### Network Policy Example

Source: https://github.com/anthropics/claude-code/blob/main/plugins/plugin-dev/skills/plugin-structure/examples/advanced-plugin.md

Example configuration for restricting pod communication using Kubernetes Network Policies.

```yaml
apiVersion: networking.k8s.io/v1
kind: NetworkPolicy
metadata:
  name: api-allow
spec:
  podSelector:
    matchLabels:
      app: api
  ingress:
    - from:
      - podSelector:
          matchLabels:
            app: frontend
```

--------------------------------

### Clarity and Specificity Examples

Source: https://github.com/anthropics/claude-code/blob/main/plugins/plugin-dev/skills/agent-development/references/system-prompt-design.md

Examples demonstrating specific vs. vague instructions in system prompts.

```text
✅ Check for SQL injection by examining all database queries for parameterization
❌ Look for security issues

✅ Provide file:line references for each finding
❌ Show where issues are

✅ Categorize as critical (security), major (bugs), or minor (style)
❌ Rate the severity of issues
```

--------------------------------

### Selecting a Model

Source: https://github.com/anthropics/claude-code/blob/main/plugins/security-guidance/README.md

Examples of how to configure the SECURITY_REVIEW_MODEL environment variable for different providers (1P/gateway, Bedrock, Vertex).

```bash
# 1P / gateway: a canonical model id
SECURITY_REVIEW_MODEL=claude-opus-4-7   # default
```

```bash
# Bedrock: use the inference-profile id
SECURITY_REVIEW_MODEL=us.anthropic.claude-opus-4-7
```

```bash
# Vertex: use the Vertex date-tag form
SECURITY_REVIEW_MODEL=claude-opus-4-7@20260218
```

--------------------------------

### Error Handling Example Pattern

Source: https://github.com/anthropics/claude-code/blob/main/plugins/plugin-dev/skills/plugin-structure/examples/standard-plugin.md

Example of a robust error handling pattern in JavaScript, including logging and re-throwing specific errors.

```javascript
async function processData(data) {
  try {
    const result = await transform(data)
    return result
  } catch (error) {
    logger.error('Data processing failed', {
      data: sanitize(data),
      error: error.message,
      stack: error.stack
    })
    throw new DataProcessingError('Failed to process data', { cause: error })
  }
}
```

--------------------------------

### Lint Command Implementation

Source: https://github.com/anthropics/claude-code/blob/main/plugins/plugin-dev/skills/plugin-structure/examples/standard-plugin.md

Bash script execution for running linting checks.

```bash
bash ${CLAUDE_PLUGIN_ROOT}/scripts/run-linter.sh
```

--------------------------------

### Security Analyzer Agent Definition

Source: https://github.com/anthropics/claude-code/blob/main/plugins/plugin-dev/skills/agent-development/examples/complete-agent-examples.md

Configuration and usage examples for the security-analyzer agent, including its name, description, example conversational triggers, model, color, and tools.

```markdown
---
name: security-analyzer
description: Use this agent when the user implements security-critical code (auth, payments, data handling), explicitly requests security analysis, or before deploying sensitive changes. Examples:

<example>
Context: User implemented authentication logic
user: "I've added JWT token validation"
assistant: "Let me check the security."
<commentary>
Authentication code is security-critical. Proactively trigger security-analyzer.
</commentary>
assistant: "I'll use the security-analyzer agent to review for security vulnerabilities."
</example>

<example>
Context: User requests security check
user: "Check my code for security issues"
assistant: "I'll use the security-analyzer agent to perform a thorough security review."
<commentary>
Explicit security review request triggers the agent.
</commentary>
</example>

model: inherit
color: red
tools: ["Read", "Grep", "Glob"]
---
```

--------------------------------

### Documentation Generator Agent Definition

Source: https://github.com/anthropics/claude-code/blob/main/plugins/plugin-dev/skills/agent-development/examples/complete-agent-examples.md

Configuration and usage examples for the docs-generator agent, including its name, description, example conversational triggers, model, color, and tools.

```markdown
---
name: docs-generator
description: Use this agent when the user has written code needing documentation, API endpoints requiring docs, or explicitly requests documentation generation. Examples:

<example>
Context: User implemented new public API
user: "I've added the user management API endpoints"
assistant: "Let me document these endpoints."
<commentary>
New public API needs documentation. Proactively trigger docs-generator.
</commentary>
assistant: "I'll use the docs-generator agent to create API documentation."
</example>

<example>
Context: User requests documentation
user: "Generate docs for this module"
assistant: "I'll use the docs-generator agent to create comprehensive documentation."
<commentary>
Explicit documentation request triggers the agent.
</commentary>
</example>

model: inherit
color: cyan
tools: ["Read", "Write", "Grep", "Glob"]
---
```

--------------------------------

### Minimal Command example

Source: https://github.com/anthropics/claude-code/blob/main/plugins/plugin-dev/skills/command-development/references/frontmatter-reference.md

Example of a command with no frontmatter.

```markdown
Review this code for common issues and suggest improvements.
```

--------------------------------

### Python Import Organization

Source: https://github.com/anthropics/claude-code/blob/main/plugins/plugin-dev/skills/plugin-structure/examples/standard-plugin.md

Shows the recommended order for organizing Python imports: standard library, third-party, then local.

```python
# Good
import os
import sys

import numpy as np
import pandas as pd

from app.models import User
from app.utils import helper

# Bad - mixed order
from app.models import User
import numpy as np
import os
```

--------------------------------

### validate-hook-schema.sh Example

Source: https://github.com/anthropics/claude-code/blob/main/plugins/plugin-dev/skills/hook-development/scripts/README.md

Example of using validate-hook-schema.sh.

```bash
cd my-plugin
./validate-hook-schema.sh hooks/hooks.json
```

--------------------------------

### Allowed Tools Security and Clarity Examples

Source: https://github.com/anthropics/claude-code/blob/main/plugins/plugin-dev/skills/command-development/references/frontmatter-reference.md

Examples demonstrating how to use `allowed-tools` for security restrictions, clarity, and enabling specific Bash commands.

```yaml
allowed-tools: Read, Grep  # Read-only command
```

```yaml
allowed-tools: Bash(git:*), Read
```

```yaml
allowed-tools: Bash(git status:*), Bash(git diff:*)
```

--------------------------------

### JavaScript Async/Await vs. Promise Chains

Source: https://github.com/anthropics/claude-code/blob/main/plugins/plugin-dev/skills/plugin-structure/examples/standard-plugin.md

Compares `async/await` with traditional promise chains, advocating for the former.

```javascript
// Good
async function fetchUserData(userId) {
  const user = await db.getUser(userId)
  const orders = await db.getOrders(user.id)
  return { user, orders }
}

// Bad
function fetchUserData(userId) {
  return db.getUser(userId)
    .then(user => db.getOrders(user.id)
      .then(orders => ({ user, orders })))
}
```

--------------------------------

### Usage in Hooks

Source: https://github.com/anthropics/claude-code/blob/main/plugins/plugin-dev/skills/plugin-settings/examples/example-settings.md

Bash script demonstrating how to check for and read plugin settings from a local markdown file within a hook.

```bash
# Check if plugin is configured
if [[ ! -f ".claude/my-plugin.local.md" ]]; then
  exit 0  # Not configured, skip hook
fi

# Read settings
FRONTMATTER=$(sed -n '/^---$/,/^---$/{ /^---$/d; p; }' ".claude/my-plugin.local.md")
ENABLED=$(echo "$FRONTMATTER" | grep '^enabled:' | sed 's/enabled: *//')

# Apply settings
if [[ "$ENABLED" == "true" ]]; then
  # Hook is active
  # ...
fi
```

--------------------------------

### Helper Commands: Get help

Source: https://github.com/anthropics/claude-code/blob/main/plugins/hookify/README.md

Command to get help for hookify.

```bash
/hookify:help
```

--------------------------------

### Test Plugin Commands Across Different Working Directories

Source: https://github.com/anthropics/claude-code/blob/main/plugins/plugin-dev/skills/command-development/examples/plugin-commands.md

Examples of testing plugin commands from various working directories to ensure robustness.

```bash
cd /tmp && claude /command-name
cd /other/project && claude /command-name
```

--------------------------------

### Batching Requests: Good Example

Source: https://github.com/anthropics/claude-code/blob/main/plugins/plugin-dev/skills/mcp-integration/references/tool-usage.md

An example of an efficient batching request using a single query with filters.

```markdown
Steps:
1. Call mcp__plugin_api_server__search with filters:
   - project_id: "123"
   - status: "active"
   - limit: 100
2. Process all results
```

--------------------------------

### First-run experience

Source: https://github.com/anthropics/claude-code/blob/main/plugins/plugin-dev/skills/command-development/references/marketplace-considerations.md

A command that provides a welcome message, explains its purpose, and offers quick start instructions on its first execution.

```markdown
---description: Command with onboardingallowed-tools: Read, Write---# First Run Checkif [ ! -f ".claude/command-initialized" ]; then  **Welcome to Command Name!**  This appears to be your first time using this command.  WHAT THIS COMMAND DOES:  [Brief explanation of purpose and benefits]  QUICK START:  1. Basic usage: /command [arg]  2. For help: /command help  3. Examples: /command examples  SETUP:  No additional setup required. You're ready to go!  ✓ Initialization complete  [Create initialization marker]  Ready to proceed with your request...fi[Normal command execution...]
```

--------------------------------

### Keywords Field Example

Source: https://github.com/anthropics/claude-code/blob/main/plugins/plugin-dev/skills/plugin-structure/references/manifest-reference.md

Example of the `keywords` field as an array of strings.

```json
["testing", "automation", "ci-cd", "quality-assurance"]
```

--------------------------------

### Cover Proactive and Reactive

Source: https://github.com/anthropics/claude-code/blob/main/plugins/plugin-dev/skills/agent-development/references/triggering-examples.md

Examples showing both explicit user requests (reactive) and proactive agent triggering based on context.

```markdown
<example>
Context: User explicitly requests review
user: "Review my code for issues"
[...]
</example>

<example>
Context: After user writes code
user: "I've implemented the feature"
assistant: "Great! Now let me review it."
<commentary>
Code written, proactively review.
</commentary>
[...]
</example>
```

--------------------------------

### Categorized Structure Example

Source: https://github.com/anthropics/claude-code/blob/main/plugins/plugin-dev/skills/plugin-structure/references/component-patterns.md

Example of a categorized directory structure for commands.

```plaintext
commands/              # Core commands
├── build.md
└── test.md

admin-commands/        # Administrative
├── configure.md
└── manage.md

workflow-commands/     # Workflow automation
├── review.md
└── deploy.md
```

--------------------------------

### Ralph Loop Initialization Script

Source: https://github.com/anthropics/claude-code/blob/main/plugins/plugin-dev/skills/plugin-settings/references/real-world-examples.md

A bash script to set up the Ralph loop by creating a local markdown state file with initial configuration.

```bash
#!/bin/bash
PROMPT="$1"
MAX_ITERATIONS="${2:-0}"
COMPLETION_PROMISE="${3:-}"

# Create state file
cat > ".claude/ralph-loop.local.md" <<EOF
---
iteration: 1
max_iterations: $MAX_ITERATIONS
completion_promise: "$COMPLETION_PROMISE"
started_at: "$(date -Iseconds)"
---

$PROMPT
EOF

echo "Ralph loop initialized: .claude/ralph-loop.local.md"
```

--------------------------------

### Flat Structure Example

Source: https://github.com/anthropics/claude-code/blob/main/plugins/plugin-dev/skills/plugin-structure/references/component-patterns.md

Example of a flat directory structure for commands.

```plaintext
commands/
├── build.md
├── test.md
├── deploy.md
├── review.md
└── docs.md
```

--------------------------------

### Standard Command example

Source: https://github.com/anthropics/claude-code/blob/main/plugins/plugin-dev/skills/command-development/references/frontmatter-reference.md

Example of a command with description and allowed-tools frontmatter.

```markdown
---
description: Review Git changes
allowed-tools: Bash(git:*), Read
---

Current changes: !`git diff --name-only`

Review each changed file for:
- Code quality
- Potential bugs
- Best practices
```

--------------------------------

### Simple Command with description example

Source: https://github.com/anthropics/claude-code/blob/main/plugins/plugin-dev/skills/command-development/references/frontmatter-reference.md

Example of a command with only a description in its frontmatter.

```markdown
---
description: Review code for issues
---

Review this code for common issues and suggest improvements.
```

--------------------------------

### disable-model-invocation basic example

Source: https://github.com/anthropics/claude-code/blob/main/plugins/plugin-dev/skills/command-development/references/frontmatter-reference.md

Basic example of setting disable-model-invocation to true.

```yaml
disable-model-invocation: true
```

--------------------------------

### Hybrid Hook Configuration Example

Source: https://github.com/anthropics/claude-code/blob/main/plugins/plugin-dev/skills/hook-development/references/migration.md

JSON configuration demonstrating a hybrid approach using both command and prompt hooks for multi-stage validation.

```json
{
  "PreToolUse": [
    {
      "matcher": "Bash",
      "hooks": [
        {
          "type": "command",
          "command": "bash ${CLAUDE_PLUGIN_ROOT}/scripts/quick-check.sh",
          "timeout": 5
        },
        {
          "type": "prompt",
          "prompt": "Deep analysis of bash command: $TOOL_INPUT",
          "timeout": 15
        }
      ]
    }
  ]
}
```

--------------------------------

### Contextual Help

Source: https://github.com/anthropics/claude-code/blob/main/plugins/plugin-dev/skills/command-development/references/documentation-patterns.md

Illustrates how to provide context-aware help messages when no operation is specified, listing available operations and usage examples.

```shell
---description: Context-aware commandargument-hint: [operation] [target]---# Context-Aware Operationif [ -z "$1" ]; then  **No operation specified**  Available operations:  - analyze: Analyze target for issues  - fix: Apply automatic fixes  - report: Generate detailed report  Usage: /command [operation] [target]  Examples:    /command analyze src/    /command fix src/app.js    /command report  Run /command help for more details.  Exit.fi[Command continues if operation provided...]
```

--------------------------------

### Optional arguments example for argument-hint

Source: https://github.com/anthropics/claude-code/blob/main/plugins/plugin-dev/skills/command-development/references/frontmatter-reference.md

Example of argument-hint with optional arguments.

```yaml
argument-hint: [file-path] [options]
```

--------------------------------

### Security Review Command Usage

Source: https://github.com/anthropics/claude-code/blob/main/plugins/plugin-dev/skills/command-development/examples/simple-commands.md

Example usage of the /security-review command.

```bash
> /security-review
```

--------------------------------

### Usage Examples

Source: https://github.com/anthropics/claude-code/blob/main/plugins/frontend-design/README.md

Examples of prompts to use with the Frontend Design Plugin.

```plaintext
"Create a dashboard for a music streaming app"
"Build a landing page for an AI security startup"
"Design a settings panel with dark mode"
```