command-patterns

A catalog of user-invoked commands for common coding tasks. The commands are grouped by actions such as reviewing, debugging, testing, refactoring, and working with Git.

In plain words
What is it for?
Use it to organize or create commands for code review, code generation, debugging, test-driven development, feature work, Git workflows, explanations, optimization, and team routines.
Why use it?
A consistent command structure makes recurring development workflows easier to find and run. It also documents how command files accept arguments and restrict tools.

Command for Claude Code

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 commands/thapaliyabikendra/ai-artifacts/command-patterns
Clone the repo
git clone --depth 1 https://github.com/thapaliyabikendra/ai-artifacts

Made for: Claude Code.

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,241 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00000 $0.01241
Opus 5 $0.00000 $0.00620
Sonnet 5 $0.00000 $0.00248
Haiku 4.5 $0.00000 $0.00124

Measured 2d ago against content hash 15ae53d806bb, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

command-patterns 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 2d ago.

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.

.claude/skills/claude-artifact-creator/references/commands/command-patterns.md · 274 lines

How it starts

The opening of the file, as written. The whole thing — 274 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Command Patterns

Commands are user-invoked workflows organized by action (what user wants to DO).

Category Overview

Category Purpose Examples
review/ Analyze existing code code-review, pr-enhance
generate/ Create new code/docs scaffold, doc-generate
debug/ Diagnose and fix issues error-trace, smart-debug
refactor/ Improve existing code cleanup, tech-debt
tdd/ Test-driven development tdd-cycle, tdd-red
feature/ End-to-end feature work feature-development
git/ Version control workflows git-workflow, pr-create
explain/ Code explanation explain-function
optimize/ Performance improvements optimize-query
team/ Team collaboration standup, retro

Command File Format

---
description: Brief description      # Required for SlashCommand tool
allowed-tools: Bash(git:*), Read    # Optional: restrict tools
argument-hint: [file] [options]     # Optional: shown in autocomplete
model: sonnet                       # Optional: override model
---

[Command instructions using $ARGUMENTS]

## Context
- Current status: !`git status`     # Bash execution with ! prefix

## Steps
1. [Step 1]
2. [Step 2]

Key Features

Arguments

Commands receive user input via $ARGUMENTS:

**Target**: $ARGUMENTS (defaults to current directory if not specified)

Bash Execution

Use ! prefix for inline bash:

**Current branch**: !`git branch --show-current`
**Status**: !`git status --short`

Tool Restrictions

Limit what tools a command can use:

# Only git commands and reading
allowed-tools: Bash(git:*), Read

# Full access
allowed-tools: Read, Write, Edit, Bash, Glob, Grep

Common Patterns

Review Pattern

For code analysis commands:

## Review Process

### Step 1: Understand Scope
- Identify files to review
- Check recent changes

### Step 2: Analyze Code
- [Checklist items]

### Step 3: Report Findings
[Output format]

Read the full file on GitHub · 274 lines

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. 2d ago First seen · 274 lines · 0 tokens per session scan A 15ae53d806bb

Subscribe to this mod's changes

command-patterns is a command published in the GitHub repository thapaliyabikendra/ai-artifacts (24 stars, last pushed 5mo ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 1,241 tokens. 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.