A scaffolding workflow for creating a new MCP Tool Hub plugin from templates. Scaffolding means generating the basic folders and files needed to begin development.

Use it to create a plugin with named tools, optional configuration support, and an optional PySide6 widget, which is a desktop user-interface component.

It removes repetitive setup work and checks the plugin name before creating files. The generated starter code follows the project's plugin structure.

How ljzloser/mcp_tools configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to ljzloser/mcp_tools. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/ljzloser/mcp_tools/master/.github/skills/new-plugin/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/ljzloser/mcp_tools

Made for: Claude Code.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/ljzloser/mcp_tools/new-plugin/github.svg)](https://agentmods.dev/skills/ljzloser/mcp_tools/new-plugin)

Your own site

<a href="https://agentmods.dev/skills/ljzloser/mcp_tools/new-plugin"><img src="https://agentmods.dev/badge/skills/ljzloser/mcp_tools/new-plugin/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/ljzloser/mcp_tools/new-plugin"><img src="https://agentmods.dev/badge/skills/ljzloser/mcp_tools/new-plugin.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 37 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 518 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00037	$0.00518
Opus 5.5	$0.00015	$0.00207
Sonnet 5.5	$0.00007	$0.00104
Haiku 4.5	$0.00004	$0.00052

Measured 2mo ago against content hash 911fcfd4a550, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

new-plugin 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 2mo ago.

The scan reads SKILL.md. This mod also ships 4 executable files (generate.py, templates/__init__.py, templates/backend.py, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

.github/skills/new-plugin/SKILL.md · 80 lines

What it actually says

New Plugin Workflow

This skill automates creating a new MCP Tool Hub plugin with proper scaffolding.

When to Use

User asks to:

"create a new plugin"
"add a plugin"
"make a new tool"
Any variant expressing intent to create a new MCP plugin

Input Parameters

Parameter	Required	Description
`plugin_name`	Yes	Unique plugin identifier (no `_` or `.` prefix)
`display_name`	No	Human-readable name (defaults to plugin_name)
`tools`	No	Comma-separated list of tool names
`has_widget`	No	Whether to include a PySide6 widget (default: false)
`has_config`	No	Whether to include configuration support (default: false)

Workflow

Step 1: Validate Input

Check plugin_name doesn't start with _ or .
Check plugin_name doesn't already exist in plugins/

Step 2: Create Directory

Create plugins/{plugin_name}/ directory.

Step 3: Generate Files

Generate the following files from templates:

__init__.py:

from .backend import PluginClass

PLUGIN_CLASS = PluginClass
WIDGET_CLASS = None  # or WidgetClass if has_widget=true

backend.py:

Plugin class with ToolDef declarations for each tool
Handler methods handle_{tool_name}
PluginMeta property

widget.py (if has_widget=true):

BasePluginWidget subclass with UI components

README.md:

Plugin description
Tools table
Dependencies list
Usage examples

Step 4: Register in Project

No manual registration needed — PluginManager auto-discovers.

Output

Plugin directory at plugins/{plugin_name}/
All required files generated
Summary of created files and next steps

Example

User: /new-plugin plugin_name=weather,tools=get_forecast;get_weather,has_widget=true

Output: Creates plugins/weather/ with backend.py, widget.py, init.py, README.md

Files

What ships with it

5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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.

2mo ago First seen · 80 lines · 37 tokens per session scan A 911fcfd4a550

Subscribe to this mod's changes

new-plugin is a skill published in the GitHub repository ljzloser/mcp_tools (4 stars, last pushed 4mo ago), licensed MIT. It adds 37 tokens to every session and 518 once invoked, about $0.0001 per session on Opus 5.5. 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.

Building agents

new-plugin next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
new-pluginljzloser/mcp_tools	Skill	4	4mo ago	MIT	A	37	Claude Code
imagegenopenai/codex	Skill	133k	yesterday	Apache-2.0	A	113	Codex
playwright-climicrosoft/playwright	Skill	99k	yesterday	Apache-2.0	A	19	Claude Code
local-ai-agentsmicrosoft/ai-agents-for-beginners	Skill	79k	4d ago	MIT	A	200	Claude Code, Codex
systematic-debuggingobra/superpowers	Skill	313k	3d ago	MIT	A	21	Claude Code
next-cache-components-adoptionvercel/next.js	Skill	143k	today	MIT	A	95	Claude Code
next-partial-prefetching-adoptionvercel/next.js	Skill	143k	today	MIT	A	103	Claude Code

mcp_tools: Skill for Claude Code