Command Development for Claude Code

Overview

Slash commands are frequently-used prompts defined as Markdown files that Claude executes during interactive sessions. Understanding command structure, frontmatter options, and dynamic features enables creating powerful, reusable workflows.

Key concepts:

• Markdown file format for commands
• YAML frontmatter for configuration
• Dynamic arguments and file references
• Bash execution for context
• Command organization and namespacing

Command Basics

What is a Slash Command?

A slash command is a Markdown file containing a prompt that Claude executes when invoked. Commands provide:

• Reusability: Define once, use repeatedly
• Consistency: Standardize common workflows
• Sharing: Distribute across team or projects
• Efficiency: Quick access to complex prompts

Critical: Commands are Instructions FOR Claude

Commands are written for agent consumption, not human consumption.

When a user invokes /command-name, the command content becomes Claude’s instructions. Write commands as directives TO Claude about what to do, not as messages TO the user.

Correct approach (instructions for Claude):

1Review this code for security vulnerabilities including:
2- SQL injection
3- XSS attacks
4- Authentication issues
5
6Provide specific line numbers and severity ratings.

Incorrect approach (messages to user):

1This command will review your code for security issues.
2You'll receive a report with vulnerability details.

The first example tells Claude what to do. The second tells the user what will happen but doesn’t instruct Claude. Always use the first approach.

Command Locations

Project commands (shared with team):

• Location: .claude/commands/
• Scope: Available in specific project
• Label: Shown as “(project)” in /help
• Use for: Team workflows, project-specific tasks

Personal commands (available everywhere):

• Location: ~/.claude/commands/
• Scope: Available in all projects
• Label: Shown as “(user)” in /help
• Use for: Personal workflows, cross-project utilities

Plugin commands (bundled with plugins):

• Location: plugin-name/commands/
• Scope: Available when plugin installed
• Label: Shown as “(plugin-name)” in /help
• Use for: Plugin-specific functionality

File Format

Basic Structure

Commands are Markdown files with .md extension:

.claude/commands/
├── review.md           # /review command
├── test.md             # /test command
└── deploy.md           # /deploy command

Simple command:

1Review this code for security vulnerabilities including:
2- SQL injection
3- XSS attacks
4- Authentication bypass
5- Insecure data handling

No frontmatter needed for basic commands.

With YAML Frontmatter

Add configuration using YAML frontmatter:

1---
2description: Review code for security issues
3allowed-tools: Read, Grep, Bash(git:*)
4model: sonnet
5---
6
7Review this code for security vulnerabilities...

YAML Frontmatter Fields

description

Purpose: Brief description shown in /help Type: String Default: First line of command prompt

1---
2description: Review pull request for code quality
3---

Best practice: Clear, actionable description (under 60 characters)

allowed-tools

Purpose: Specify which tools command can use Type: String or Array Default: Inherits from conversation

1---
2allowed-tools: Read, Write, Edit, Bash(git:*)
3---

Patterns:

• Read, Write, Edit - Specific tools
• Bash(git:*) - Bash with git commands only
• * - All tools (rarely needed)

Use when: Command requires specific tool access

model

Purpose: Specify model for command execution Type: String (sonnet, opus, haiku) Default: Inherits from conversation

1---
2model: haiku
3---

Use cases:

• haiku - Fast, simple commands
• sonnet - Standard workflows
• opus - Complex analysis

argument-hint

Purpose: Document expected arguments for autocomplete Type: String Default: None

1---
2argument-hint: [pr-number] [priority] [assignee]
3---

Benefits:

• Helps users understand command arguments
• Improves command discovery
• Documents command interface

disable-model-invocation

Purpose: Prevent SlashCommand tool from programmatically calling command Type: Boolean Default: false

1---
2disable-model-invocation: true
3---

Use when: Command should only be manually invoked

Dynamic Arguments

Using $ARGUMENTS

Capture all arguments as single string:

1---
2description: Fix issue by number
3argument-hint: [issue-number]
4---
5
6Fix issue #$ARGUMENTS following our coding standards and best practices.

Usage:

> /fix-issue 123
> /fix-issue 456

Expands to:

Fix issue #123 following our coding standards...
Fix issue #456 following our coding standards...

Using Positional Arguments

Capture individual arguments with $1, $2, $3, etc.:

1---
2description: Review PR with priority and assignee
3argument-hint: [pr-number] [priority] [assignee]
4---
5
6Review pull request #$1 with priority level $2.
7After review, assign to $3 for follow-up.

Usage:

> /review-pr 123 high alice

Expands to:

Review pull request #123 with priority level high.
After review, assign to alice for follow-up.

Combining Arguments

Mix positional and remaining arguments:

1Deploy $1 to $2 environment with options: $3

Usage:

> /deploy api staging --force --skip-tests

Expands to:

Deploy api to staging environment with options: --force --skip-tests

File References

Using @ Syntax

Include file contents in command:

1---
2description: Review specific file
3argument-hint: [file-path]
4---
5
6Review @$1 for:
7- Code quality
8- Best practices
9- Potential bugs

Usage:

> /review-file src/api/users.ts

Effect: Claude reads src/api/users.ts before processing command

Multiple File References

Reference multiple files:

1Compare @src/old-version.js with @src/new-version.js
2
3Identify:
4- Breaking changes
5- New features
6- Bug fixes

Static File References

Reference known files without arguments:

1Review @package.json and @tsconfig.json for consistency
2
3Ensure:
4- TypeScript version matches
5- Dependencies are aligned
6- Build configuration is correct

Bash Execution in Commands

Commands can execute bash commands inline to dynamically gather context before Claude processes the command. This is useful for including repository state, environment information, or project-specific context.

When to use:

• Include dynamic context (git status, environment vars, etc.)
• Gather project/repository state
• Build context-aware workflows

Implementation details: For complete syntax, examples, and best practices, see references/plugin-features-reference.md section on bash execution. The reference includes the exact syntax and multiple working examples to avoid execution issues

Command Organization

Flat Structure

Simple organization for small command sets:

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

Use when: 5-15 commands, no clear categories

Namespaced Structure

Organize commands in subdirectories:

.claude/commands/
├── ci/
│   ├── build.md        # /build (project:ci)
│   ├── test.md         # /test (project:ci)
│   └── lint.md         # /lint (project:ci)
├── git/
│   ├── commit.md       # /commit (project:git)
│   └── pr.md           # /pr (project:git)
└── docs/
    ├── generate.md     # /generate (project:docs)
    └── publish.md      # /publish (project:docs)

Benefits:

• Logical grouping by category
• Namespace shown in /help
• Easier to find related commands

Use when: 15+ commands, clear categories

Best Practices

Command Design

1. Single responsibility: One command, one task
2. Clear descriptions: Self-explanatory in /help
3. Explicit dependencies: Use allowed-tools when needed
4. Document arguments: Always provide argument-hint
5. Consistent naming: Use verb-noun pattern (review-pr, fix-issue)

Argument Handling

1. Validate arguments: Check for required arguments in prompt
2. Provide defaults: Suggest defaults when arguments missing
3. Document format: Explain expected argument format
4. Handle edge cases: Consider missing or invalid arguments

1---
2argument-hint: [pr-number]
3---
4
5$IF($1,
6  Review PR #$1,
7  Please provide a PR number. Usage: /review-pr [number]
8)

File References

1. Explicit paths: Use clear file paths
2. Check existence: Handle missing files gracefully
3. Relative paths: Use project-relative paths
4. Glob support: Consider using Glob tool for patterns

Bash Commands

1. Limit scope: Use Bash(git:*) not Bash(*)
2. Safe commands: Avoid destructive operations
3. Handle errors: Consider command failures
4. Keep fast: Long-running commands slow invocation

Documentation

1. Add comments: Explain complex logic
2. Provide examples: Show usage in comments
3. List requirements: Document dependencies
4. Version commands: Note breaking changes

 1---
 2description: Deploy application to environment
 3argument-hint: [environment] [version]
 4---
 5
 6<!--
 7Usage: /deploy [staging|production] [version]
 8Requires: AWS credentials configured
 9Example: /deploy staging v1.2.3
10-->
11
12Deploy application to $1 environment using version $2...

Common Patterns

Review Pattern

 1---
 2description: Review code changes
 3allowed-tools: Read, Bash(git:*)
 4---
 5
 6Files changed: !`git diff --name-only`
 7
 8Review each file for:
 91. Code quality and style
102. Potential bugs or issues
113. Test coverage
124. Documentation needs
13
14Provide specific feedback for each file.

Testing Pattern

1---
2description: Run tests for specific file
3argument-hint: [test-file]
4allowed-tools: Bash(npm:*)
5---
6
7Run tests: !`npm test $1`
8
9Analyze results and suggest fixes for failures.

Documentation Pattern

 1---
 2description: Generate documentation for file
 3argument-hint: [source-file]
 4---
 5
 6Generate comprehensive documentation for @$1 including:
 7- Function/class descriptions
 8- Parameter documentation
 9- Return value descriptions
10- Usage examples
11- Edge cases and errors

Workflow Pattern

 1---
 2description: Complete PR workflow
 3argument-hint: [pr-number]
 4allowed-tools: Bash(gh:*), Read
 5---
 6
 7PR #$1 Workflow:
 8
 91. Fetch PR: !`gh pr view $1`
102. Review changes
113. Run checks
124. Approve or request changes

Troubleshooting

Command not appearing:

• Check file is in correct directory
• Verify .md extension present
• Ensure valid Markdown format
• Restart Claude Code

Arguments not working:

• Verify $1, $2 syntax correct
• Check argument-hint matches usage
• Ensure no extra spaces

Bash execution failing:

• Check allowed-tools includes Bash
• Verify command syntax in backticks
• Test command in terminal first
• Check for required permissions

File references not working:

• Verify @ syntax correct
• Check file path is valid
• Ensure Read tool allowed
• Use absolute or project-relative paths

Plugin-Specific Features

CLAUDE_PLUGIN_ROOT Variable

Plugin commands have access to ${CLAUDE_PLUGIN_ROOT}, an environment variable that resolves to the plugin’s absolute path.

Purpose:

• Reference plugin files portably
• Execute plugin scripts
• Load plugin configuration
• Access plugin templates

Basic usage:

1---
2description: Analyze using plugin script
3allowed-tools: Bash(node:*)
4---
5
6Run analysis: !`node ${CLAUDE_PLUGIN_ROOT}/scripts/analyze.js $1`
7
8Review results and report findings.

Common patterns:

 1# Execute plugin script
 2!`bash ${CLAUDE_PLUGIN_ROOT}/scripts/script.sh`
 3
 4# Load plugin configuration
 5@${CLAUDE_PLUGIN_ROOT}/config/settings.json
 6
 7# Use plugin template
 8@${CLAUDE_PLUGIN_ROOT}/templates/report.md
 9
10# Access plugin resources
11@${CLAUDE_PLUGIN_ROOT}/docs/reference.md

Why use it:

• Works across all installations
• Portable between systems
• No hardcoded paths needed
• Essential for multi-file plugins

Plugin Command Organization

Plugin commands discovered automatically from commands/ directory:

plugin-name/
├── commands/
│   ├── foo.md              # /foo (plugin:plugin-name)
│   ├── bar.md              # /bar (plugin:plugin-name)
│   └── utils/
│       └── helper.md       # /helper (plugin:plugin-name:utils)
└── plugin.json

Namespace benefits:

• Logical command grouping
• Shown in /help output
• Avoid name conflicts
• Organize related commands

Naming conventions:

• Use descriptive action names
• Avoid generic names (test, run)
• Consider plugin-specific prefix
• Use hyphens for multi-word names

Plugin Command Patterns

Configuration-based pattern:

 1---
 2description: Deploy using plugin configuration
 3argument-hint: [environment]
 4allowed-tools: Read, Bash(*)
 5---
 6
 7Load configuration: @${CLAUDE_PLUGIN_ROOT}/config/$1-deploy.json
 8
 9Deploy to $1 using configuration settings.
10Monitor deployment and report status.

Template-based pattern:

1---
2description: Generate docs from template
3argument-hint: [component]
4---
5
6Template: @${CLAUDE_PLUGIN_ROOT}/templates/docs.md
7
8Generate documentation for $1 following template structure.

Multi-script pattern:

 1---
 2description: Complete build workflow
 3allowed-tools: Bash(*)
 4---
 5
 6Build: !`bash ${CLAUDE_PLUGIN_ROOT}/scripts/build.sh`
 7Test: !`bash ${CLAUDE_PLUGIN_ROOT}/scripts/test.sh`
 8Package: !`bash ${CLAUDE_PLUGIN_ROOT}/scripts/package.sh`
 9
10Review outputs and report workflow status.

See references/plugin-features-reference.md for detailed patterns.

Integration with Plugin Components

Commands can integrate with other plugin components for powerful workflows.

Agent Integration

Launch plugin agents for complex tasks:

 1---
 2description: Deep code review
 3argument-hint: [file-path]
 4---
 5
 6Initiate comprehensive review of @$1 using the code-reviewer agent.
 7
 8The agent will analyze:
 9- Code structure
10- Security issues
11- Performance
12- Best practices
13
14Agent uses plugin resources:
15- ${CLAUDE_PLUGIN_ROOT}/config/rules.json
16- ${CLAUDE_PLUGIN_ROOT}/checklists/review.md

Key points:

• Agent must exist in plugin/agents/ directory
• Claude uses Task tool to launch agent
• Document agent capabilities
• Reference plugin resources agent uses

Skill Integration

Leverage plugin skills for specialized knowledge:

 1---
 2description: Document API with standards
 3argument-hint: [api-file]
 4---
 5
 6Document API in @$1 following plugin standards.
 7
 8Use the api-docs-standards skill to ensure:
 9- Complete endpoint documentation
10- Consistent formatting
11- Example quality
12- Error documentation
13
14Generate production-ready API docs.

Key points:

• Skill must exist in plugin/skills/ directory
• Mention skill name to trigger invocation
• Document skill purpose
• Explain what skill provides

Hook Coordination

Design commands that work with plugin hooks:

• Commands can prepare state for hooks to process
• Hooks execute automatically on tool events
• Commands should document expected hook behavior
• Guide Claude on interpreting hook output

See references/plugin-features-reference.md for examples of commands that coordinate with hooks

Multi-Component Workflows

Combine agents, skills, and scripts:

 1---
 2description: Comprehensive review workflow
 3argument-hint: [file]
 4allowed-tools: Bash(node:*), Read
 5---
 6
 7Target: @$1
 8
 9Phase 1 - Static Analysis:
10!`node ${CLAUDE_PLUGIN_ROOT}/scripts/lint.js $1`
11
12Phase 2 - Deep Review:
13Launch code-reviewer agent for detailed analysis.
14
15Phase 3 - Standards Check:
16Use coding-standards skill for validation.
17
18Phase 4 - Report:
19Template: @${CLAUDE_PLUGIN_ROOT}/templates/review.md
20
21Compile findings into report following template.

When to use:

• Complex multi-step workflows
• Leverage multiple plugin capabilities
• Require specialized analysis
• Need structured outputs

Validation Patterns

Commands should validate inputs and resources before processing.

Argument Validation

 1---
 2description: Deploy with validation
 3argument-hint: [environment]
 4---
 5
 6Validate environment: !`echo "$1" | grep -E "^(dev|staging|prod)$" || echo "INVALID"`
 7
 8If $1 is valid environment:
 9  Deploy to $1
10Otherwise:
11  Explain valid environments: dev, staging, prod
12  Show usage: /deploy [environment]

File Existence Checks

 1---
 2description: Process configuration
 3argument-hint: [config-file]
 4---
 5
 6Check file exists: !`test -f $1 && echo "EXISTS" || echo "MISSING"`
 7
 8If file exists:
 9  Process configuration: @$1
10Otherwise:
11  Explain where to place config file
12  Show expected format
13  Provide example configuration

Plugin Resource Validation

 1---
 2description: Run plugin analyzer
 3allowed-tools: Bash(test:*)
 4---
 5
 6Validate plugin setup:
 7- Script: !`test -x ${CLAUDE_PLUGIN_ROOT}/bin/analyze && echo "✓" || echo "✗"`
 8- Config: !`test -f ${CLAUDE_PLUGIN_ROOT}/config.json && echo "✓" || echo "✗"`
 9
10If all checks pass, run analysis.
11Otherwise, report missing components.

Error Handling

 1---
 2description: Build with error handling
 3allowed-tools: Bash(*)
 4---
 5
 6Execute build: !`bash ${CLAUDE_PLUGIN_ROOT}/scripts/build.sh 2>&1 || echo "BUILD_FAILED"`
 7
 8If build succeeded:
 9  Report success and output location
10If build failed:
11  Analyze error output
12  Suggest likely causes
13  Provide troubleshooting steps

Best practices:

• Validate early in command
• Provide helpful error messages
• Suggest corrective actions
• Handle edge cases gracefully

For detailed frontmatter field specifications, see references/frontmatter-reference.md. For plugin-specific features and patterns, see references/plugin-features-reference.md. For command pattern examples, see examples/ directory.