claude-plugin:create

A command for creating a new Claude Code plugin, which is a package of reusable coding agents, commands, and skills. It validates the plugin name and requested components before creating the structure.

In plain words
What is it for?
Use it to start plugins with agents, commands, skills, or combinations of these, with optional configuration such as category and model.
Why use it?
It removes the repetitive setup work and helps keep new plugins consistent with the expected layout.

Command

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/geoffjay/claude-plugins/create
Clone the repo
git clone --depth 1 https://github.com/geoffjay/claude-plugins
Per session 19 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,717 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 $0.00019 $0.01717
Opus 5 $0.00010 $0.00859
Sonnet 5 $0.00004 $0.00343
Haiku 4.5 $0.00002 $0.00172

Measured 2d ago against content hash 04a74e945d92, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

claude-plugin:create 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.

plugins/claude-plugin/commands/create.md · 276 lines

How it starts

The opening of the file, as written. The whole thing — 276 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Create Plugin Command

Create a new Claude Code plugin following granular, composable architecture principles.

Arguments

  • $1 - Plugin name (required, hyphen-case format)
  • $2 - Plugin description (required)
  • $3 - Components to create: agents, commands, skills, or combinations like agents,commands (optional, defaults to prompting)
  • $4 - Additional configuration as JSON (optional)

Usage

# Basic usage - will prompt for details
/claude-plugin:create my-plugin-name "Plugin description"

# Specify components
/claude-plugin:create my-plugin-name "Plugin description" agents,commands

# Full configuration
/claude-plugin:create golang-advanced "Advanced Go development tools" agents,commands,skills '{"category":"languages","model":"claude-sonnet-4"}'

Workflow

This command orchestrates plugin creation by:

  1. Validating Input

    • Verify plugin name follows hyphen-case convention
    • Ensure plugin doesn't already exist
    • Validate component specifications
  2. Gathering Requirements

    • If components not specified, ask user what to create
    • Request additional details about agents (names, purposes, models)
    • Request command details (names, purposes, workflows)
    • Request skill details (names, triggers, content structure)
  3. Creating Plugin Structure

    • Create plugin directory: plugins/$PLUGIN_NAME/
    • Create component directories as needed
    • Set up skill subdirectories (SKILL.md, assets/, references/)
  4. Generating Components

    • Use Task tool with subagent_type="claude-plugin" to design and implement components
    • Create agent files with proper frontmatter
    • Create command files with argument handling
    • Create skill files with progressive disclosure
  5. Updating Marketplace

    • Invoke marketplace-update skill to add plugin entry
    • Invoke documentation-update skill to update docs

Implementation

Plugin Name: ${1:-"[REQUIRED]"} Description: ${2:-"[REQUIRED]"} Components: ${3:-"[PROMPT USER]"} Configuration: ${4:-"{}"}

Read the full file on GitHub · 276 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 · 276 lines · 19 tokens per session scan A 04a74e945d92

Subscribe to this mod's changes

claude-plugin:create is a command published in the GitHub repository geoffjay/claude-plugins (8 stars, last pushed 10mo ago), licensed MIT. It adds 19 tokens to every session and 1,717 once invoked, about $0.0001 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 2026-08-31.