---
title: "Command Development for Claude Code: review, setup & limitations · Undominated.ai"
canonical: https://undominated.ai/skills/anthropic-command-development/
description: "Explains how to write Claude Code slash-command files: frontmatter fields, $ARGUMENTS and positional arguments, @file references, inline Bash and plugin command patterns."
---

# Command Development for Claude Code: review, setup & limitations · Undominated.ai

> Explains how to write Claude Code slash-command files: frontmatter fields, $ARGUMENTS and positional arguments, @file references, inline Bash and plugin command patterns.

[← Explore all skills](/skills/)

AGENT DEVELOPMENT / Anthropic

# Command Development for Claude Code

Explains how to write Claude Code slash-command files: frontmatter fields, $ARGUMENTS and positional arguments, @file references, inline Bash and plugin command patterns.

 [See setup guidance ↓](#setup)[Original source ↗](https://github.com/anthropics/claude-plugins-official/tree/41f32e407b450055044f167db7ded5e8ff67d203/plugins/plugin-dev/skills/command-development)

SOURCE REVIEW

 Reviewed 2026-10-21
 Evidence 5 linked sources
 Publisher Anthropic
 Licence [Apache-2.0 ↗](https://raw.githubusercontent.com/anthropics/claude-plugins-official/41f32e407b450055044f167db7ded5e8ff67d203/plugins/plugin-dev/LICENSE)
 Revision 41f32e407b45
 [Read what was—and wasn’t—checked ↓](#review)

“This skill should be used when the user asks to "create a slash command", "add a command", "write a custom command", "define command arguments", "use command frontmatter", "organize commands", "create command with file references", "interactive command", "use AskUserQuestion in command", or needs guidance on slash command structure, YAML frontmatter fields, dynamic arguments, bash execution in commands, user interaction patterns, or command development best practices for Claude Code.”

 [Anthropic · upstream description ↗](https://raw.githubusercontent.com/anthropics/claude-plugins-official/41f32e407b450055044f167db7ded5e8ff67d203/plugins/plugin-dev/skills/command-development/SKILL.md) Our analysis follows below.

01 / THE REASONING

## Why this made the selection.

 - It covers the five command frontmatter fields it names (description, allowed-tools, model, argument-hint, disable-model-invocation) together with $ARGUMENTS, $1/$2 positional arguments, @file references and inline Bash.
- It gives the scope of each command location: .claude/commands/ for one project, ~/.claude/commands/ for every project, and a plugin's commands/ directory while that plugin is installed.

### A good fit for

 - Write a slash command that takes [pr-number]-style arguments through argument-hint and $1/$2
- Narrow a command's tools with an allowed-tools pattern such as Bash(git:*)
- Call a plugin's own scripts and templates from a command through ${CLAUDE_PLUGIN_ROOT}

### Weigh up before choosing

 - Last commit touching plugins/plugin-dev/skills/command-development at revision 41f32e40: 2026-03-17 (6b70f99f).
- The SKILL.md opens by calling .claude/commands/ a legacy format and saying new skills should use the .claude/skills/<name>/SKILL.md layout covered by the skill-development skill.
- Its Bash advice says to use Bash(git:*) rather than Bash(*), yet three of its own plugin examples grant allowed-tools: Bash(*) or Read, Bash(*).
- For complete inline-Bash syntax, examples and practices the SKILL.md defers to references/plugin-features-reference.md, which this review did not open.
- Several example commands pass arguments unquoted into inline shell commands, for example !`test -f $1 && echo "EXISTS" || echo "MISSING"`, !`npm test $1` and !`gh pr view $1`.
- command-development ships in plugin-dev, whose README has a License section reading "MIT License - See repository for details" while plugins/plugin-dev/LICENSE is the Apache License, Version 2.0. This record follows the LICENSE file.
- The plugin-dev README's install line, the way command-development is installed, names a marketplace called claude-code-marketplace; the repository's marketplace file is named claude-plugins-official.

02 / THE REVIEW RECORD

## What we actually inspected.

Source review has boundaries. A clear record is more useful than a “safe” badge.

### Material inspected

 - plugins/plugin-dev/skills/command-development/SKILL.md
- plugins/plugin-dev/skills/command-development/README.md
- plugins/plugin-dev/README.md
- plugins/plugin-dev/LICENSE
- .claude-plugin/marketplace.json (name and plugin-dev entry)

### Our findings

 - The skill directory holds Markdown only (SKILL.md, README.md, examples/ and references/); it ships no script, and the SKILL.md frontmatter declares no allowed-tools.
- allowed-tools and model default to the conversation's settings when a command omits them; disable-model-invocation defaults to false.
- Commands are described as instructions for Claude, not messages to the user, and the SKILL.md shows a correct and an incorrect version of the same command.
- Plugin command patterns reach plugin files through ${CLAUDE_PLUGIN_ROOT}, for example !`node ${CLAUDE_PLUGIN_ROOT}/scripts/analyze.js $1`.

### Not established by this review

 - No command was written or invoked from this guidance.
- The seven files in references/ and the two files in examples/ were not opened, including references/plugin-features-reference.md and references/interactive-commands.md.
- Not executed: it was not installed or run.

The review applies to the material and revision named here. A newer upstream release can change its behavior.

03 / PUT IT TO WORK

## Add a skill to your workflow.

[Upstream setup instructions ↗](https://raw.githubusercontent.com/anthropics/claude-plugins-official/41f32e407b450055044f167db7ded5e8ff67d203/plugins/plugin-dev/README.md)
 - The plugin-dev README prints `/plugin install plugin-dev@claude-code-marketplace`. Its marketplace, claude-code-marketplace, is not the one this repository defines (claude-plugins-official, per .claude-plugin/marketplace.json), and the line installs all seven plugin-dev skills, command-development among them, so install.command is null.
- To load command-development from a local checkout instead, the same README prints `cc --plugin-dir /path/to/plugin-dev`.
- This review ran neither line.

### Before you start

 - Claude Code (the commands it describes are Claude Code slash commands)

### Compatibility

Claude Code

### Markdown guidance only; commands built from it can run inline shell commands

 - No allowed-tools in the SKILL.md frontmatter and no script in the skill directory
- Commands written from it are Markdown files in .claude/commands/, ~/.claude/commands/ or a plugin's commands/ directory
- Its example commands run git diff, gh pr view, npm test and plugin scripts inline; a command that omits allowed-tools inherits the conversation's tools, per the SKILL.md

### Cost model

Apache-2.0 per plugins/plugin-dev/LICENSE; reading the guidance calls no external service

04 / FOLLOW THE EVIDENCE

## The source trail.

Our notes are separate from the original resource. Check upstream before adopting a new version.

 - [command-development SKILL.md ↗](https://raw.githubusercontent.com/anthropics/claude-plugins-official/41f32e407b450055044f167db7ded5e8ff67d203/plugins/plugin-dev/skills/command-development/SKILL.md) Checked 2026-10-21 https://raw.githubusercontent.com/anthropics/claude-plugins-official/41f32e407b450055044f167db7ded5e8ff67d203/plugins/plugin-dev/skills/command-development/SKILL.md Supports: upstreamDescription, summary, whySelected[0], whySelected[1], bestFor[0], bestFor[1], bestFor[2], limitations[1], limitations[2], limitations[3], limitations[4], compatibility, review.findings[0], review.findings[1], review.findings[2], review.findings[3], access.permissions[0], access.permissions[1], access.permissions[2]
- [command-development README ↗](https://raw.githubusercontent.com/anthropics/claude-plugins-official/41f32e407b450055044f167db7ded5e8ff67d203/plugins/plugin-dev/skills/command-development/README.md) Checked 2026-10-21 https://raw.githubusercontent.com/anthropics/claude-plugins-official/41f32e407b450055044f167db7ded5e8ff67d203/plugins/plugin-dev/skills/command-development/README.md Supports: review.findings[0]
- [plugin-dev README ↗](https://raw.githubusercontent.com/anthropics/claude-plugins-official/41f32e407b450055044f167db7ded5e8ff67d203/plugins/plugin-dev/README.md) Checked 2026-10-21 https://raw.githubusercontent.com/anthropics/claude-plugins-official/41f32e407b450055044f167db7ded5e8ff67d203/plugins/plugin-dev/README.md Supports: install.sourceUrl, install.steps[0], install.steps[1], install.prerequisites[0], limitations[5], limitations[6], compatibility
- [plugin-dev LICENSE ↗](https://raw.githubusercontent.com/anthropics/claude-plugins-official/41f32e407b450055044f167db7ded5e8ff67d203/plugins/plugin-dev/LICENSE) Checked 2026-10-21 https://raw.githubusercontent.com/anthropics/claude-plugins-official/41f32e407b450055044f167db7ded5e8ff67d203/plugins/plugin-dev/LICENSE Supports: license, limitations[5], access.cost
- [Marketplace file, name and plugin-dev entry ↗](https://raw.githubusercontent.com/anthropics/claude-plugins-official/41f32e407b450055044f167db7ded5e8ff67d203/.claude-plugin/marketplace.json) Checked 2026-10-21 https://raw.githubusercontent.com/anthropics/claude-plugins-official/41f32e407b450055044f167db7ded5e8ff67d203/.claude-plugin/marketplace.json Supports: limitations[6], install.steps[0]

KEEP COMPARING

## Other approaches to consider.

Related by category or shared topics. These are alternatives to inspect, not a measured quality order.

 [### Skill Development for Claude Code Plugins ↗ Guides writing a skill that ships inside a Claude Code plugin: directory layout, a third-person trigger description, an imperative SKILL.md body and progressive disclosure into references/, examples/ and scripts/.](/skills/anthropic-skill-development/)[### Agent Development for Claude Code Plugins ↗ Explains how to write a Claude Code plugin agent file (frontmatter, trigger description, system prompt) and ships a Bash script that checks one agent file.](/skills/anthropic-agent-development/)[### Hook Development for Claude Code Plugins ↗ Explains how to write Claude Code plugin hooks, prompt-based and command-based, with their event list, input and output JSON and exit codes, and ships Bash utilities to validate, lint and test them.](/skills/anthropic-hook-development/)

 [AI Tools ↗](/tools/)[Skills ↗](/skills/)[Agents ↗](/agents/)[MCP Servers ↗](/mcp-servers/)[Workflows ↗](/workflows/)

## Continue your investigation

 - [Choose a toolkit](/tools/)
- [Inspect execution hosts](/agents/)
- [Check tool access](/mcp-servers/)
- [Check project dependencies](/check-repo/)
