new-plugin

new-plugin is a command for Claude Code from C0ntr0lledCha0s/claude-code-plugin-automations. It costs 27 tokens per session (2,766 once invoked), scanned C, original, MIT.

A command for creating, checking, or updating Claude Code plugins and coordinating their agents, skills, commands, and hooks.

In plain words
What is it for?
Use it with create, validate, or update actions to start a plugin, check its structure, or revise an existing plugin.
Why use it?
It organizes the multi-step plugin workflow by researching existing patterns, presenting options, creating components in order, and validating them.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: model in frontmatter; reads .claude/ paths; names the AskUserQuestion tool.

Not installable on its own: it runs a file from its repository that does not travel with it. Clone the repository, or install whatever ships that file. The line is python3 claude-component-builder/skills/building-plugins/scripts/validate-plugin.py [plugin]/.claude-plugin/plugin.json.

Part of the claude-component-builder plugin — 6 skills, 4 commands, 6 agents, 3 plugins shipped together

Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add C0ntr0lledCha0s/claude-code-plugin-automations
Claude Code
/plugin install claude-component-builder

Made for: Claude Code.

Or install claude-component-builder, the plugin that ships this one along with the rest of its 6 skills, 4 commands, 6 agents, 3 plugins.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for new-plugin

README.md
[![agentmods](https://agentmods.dev/badge/commands/c0ntr0lledcha0s/claude-code-plugin-automations/new-plugin.svg)](https://agentmods.dev/commands/c0ntr0lledcha0s/claude-code-plugin-automations/new-plugin)
Your own site
<a href="https://agentmods.dev/commands/c0ntr0lledcha0s/claude-code-plugin-automations/new-plugin"><img src="https://agentmods.dev/badge/commands/c0ntr0lledcha0s/claude-code-plugin-automations/new-plugin.svg" alt="Measured on agentmods" height="20"></a>
Per session 27 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,766 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 1 finding. 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 5.1 $0.00027 $0.02766
Opus 5 $0.00014 $0.01383
Sonnet 5 $0.00005 $0.00553
Haiku 4.5 $0.00003 $0.00277

Measured 5d ago against content hash f74532e90399, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade C, and why

new-plugin scanned grade C with 1 finding 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 5d 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.

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

rm -rf my-plugin/
claude-component-builder/commands/new-plugin.md · 454 lines

How it starts

The opening of the file, as written. The whole thing — 454 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Plugin Orchestrator

Create, validate, or update Claude Code plugins. This command handles the complete workflow including research, planning, user confirmation, and parallel component creation.

Arguments:

  • $1 (required): Action - create, validate, update
  • $2 (required for create/update): Plugin name

Full arguments: $ARGUMENTS

Why This Command Exists

Creating plugins involves multiple components (agents, skills, commands, hooks) that must be coordinated. This command:

  • Runs in the main thread (can use Task tool)
  • Orchestrates parallel creation of components
  • Ensures proper sequencing (structure before components)
  • Provides validation at each step

Workflow: Create

Phase 1: Research Existing Patterns

Before creating, explore the codebase:

Use Explore agent to find:
- Existing similar plugins
- Naming conventions in use
- Related components that might overlap

Phase 2: Present Options to User

Present 2-3 template options:

## 📋 Plugin Options

### Option A: Minimal Plugin
- 1-2 commands only
- Basic structure
- Best for: Simple utilities

### Option B: Standard Plugin (Recommended)
- 1-2 agents + 2-3 commands
- README with examples
- Best for: Most use cases

### Option C: Comprehensive Plugin
- Multiple agents + skills + commands + hooks
- Full documentation
- Best for: Major features

**Questions:**
1. Which template? (A/B/C)
2. What components do you need?
3. Any specific requirements?

Phase 3: Confirm Before Creating

Use AskUserQuestion to get explicit confirmation:

Before I create the plugin, please confirm:
- Plugin name: [name]
- Template: [selected]
- Components: [list]

Proceed? (yes/no)

Phase 4: Create Structure (Sequential)

First, create the plugin directory structure:

Task → plugin-builder
Prompt: "Create plugin structure '[name]' with directories for [components]"

This MUST complete before creating components.

Phase 5: Create Components (Parallel)

Read the full file on GitHub · 454 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. 5d ago First seen · 454 lines · 27 tokens per session scan C f74532e90399

Subscribe to this mod's changes

new-plugin is a command published in the GitHub repository C0ntr0lledCha0s/claude-code-plugin-automations (3 stars, last pushed 6mo ago), licensed MIT. It adds 27 tokens to every session and 2,766 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.