create-command

A guide for designing custom Claude commands: reusable instructions you invoke to perform a particular development job.

In plain words
What is it for?
Use it to create project-specific or user-level commands for planning, coding, analysis, testing, documentation, workflows, or utility tasks.
Why use it?
It gives new commands a consistent purpose, location, structure, and usage format instead of leaving their design improvised.

Cursor rule

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add rules/steipete/agent-rules/create-command
Clone the repo
git clone --depth 1 https://github.com/steipete/agent-rules
Per session 410 This file is loaded in full into every session.
When invoked 410 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00410 $0.00410
Opus 5 $0.00205 $0.00205
Sonnet 5 $0.00082 $0.00082
Haiku 4.5 $0.00041 $0.00041

Measured yesterday against content hash 2823d7dfaeb5, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

create-command scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

project-rules/create-command.mdc · 75 lines

What it actually says

Create Command

Guide for creating new custom Claude commands with proper structure.

Process:

1. Understanding Purpose

  • What problem does this command solve?
  • Who will use this command?
  • What is the expected output?
  • How will users interact with it?

2. Category Classification

Determine command type:

  • Planning: Project setup, architecture decisions
  • Implementation: Code generation, feature development
  • Analysis: Code review, performance analysis
  • Testing: Test creation, validation
  • Documentation: Docs generation, updates
  • Workflow: Multi-step processes
  • Utility: Helper commands, tools

3. Pattern Selection

Study similar existing commands:

  • Analyze structure and flow
  • Note common patterns
  • Identify reusable components
  • Follow established conventions

4. Command Location

Choose appropriate location:

  • Project-specific: .claude/commands/
  • User-level: ~/.claude/commands/
  • Consider reusability and context

5. Command Structure

Create with these sections:

  • Title: Clear, action-oriented name
  • Description: One-line summary
  • Usage: How to invoke with parameters
  • Process: Step-by-step instructions
  • Examples: Concrete usage examples
  • Output: Expected results
  • Notes: Special considerations

Template:

# Command Name

Brief description of what this command does.

## Usage:
`/command-name [arguments]`

## Process:
1. First step
2. Second step
3. Third step

## Examples:
- Example 1
- Example 2

## Notes:
- Important considerations
- Limitations

Best Practices:

  • Keep commands focused and single-purpose
  • Include parameter validation
  • Provide helpful error messages
  • Document expected inputs/outputs
  • Consider edge cases
  • Test thoroughly before finalizing
Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. yesterday First seen · 75 lines · 410 tokens per session scan A 2823d7dfaeb5

Subscribe to this mod's changes

create-command is a cursor rule published in the GitHub repository steipete/agent-rules (5,696 stars, last pushed 4mo ago), licensed MIT. It adds 410 tokens to every session, about $0.0020 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.