claude-plugins CLAUDE.md

Project instructions for a collection of Claude Code plugins, which add commands, skills, agents, or external tool connections to Claude Code. They explain how plugins are organised and listed in the marketplace.

In plain words
What is it for?
Use them when installing dependencies, creating a plugin, adding plugin components, bundling scripts, or updating the marketplace catalogue.
Why use it?
They reduce the chance of adding a plugin with missing files, invalid metadata, or an out-of-date marketplace listing. They also document the build and synchronisation steps.

Instructions file

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 instructions/nicknisi/claude-plugins/claude-md
Clone the repo
git clone --depth 1 https://github.com/nicknisi/claude-plugins
Per session 552 This file is loaded in full into every session.
When invoked 552 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 $0.00552 $0.00552
Opus 5 $0.00276 $0.00276
Sonnet 5 $0.00110 $0.00110
Haiku 4.5 $0.00055 $0.00055

Measured yesterday against content hash c37a087c0628, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

claude-plugins CLAUDE.md 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.

CLAUDE.md · 102 lines

How it starts

The opening of the file, as written. The whole thing — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Claude Code Plugin Marketplace

Personal collection of Claude Code plugins. For plugin and marketplace documentation, see:

Quick Start

# Install dependencies
pnpm install

# Bundle plugin scripts, then regenerate marketplace.json + the README list
pnpm run build && pnpm run sync

Plugin Structure

plugins/{name}/
├── .claude-plugin/
│   └── plugin.json          # Required metadata
├── .mcp.json                # Optional: MCP server config
├── agents/*.md              # Optional: agent definitions
├── skills/*/SKILL.md        # Optional: skills
├── commands/*.md            # Optional: slash commands
└── mcp-server/              # Optional: custom MCP server
    └── dist/                # Bundled output

Adding a Plugin

  1. Create plugin directory:

    mkdir -p plugins/my-plugin/.claude-plugin
    
  2. Create plugin.json:

    {
      "name": "my-plugin",
      "version": "0.1.0",
      "description": "Plugin description",
      "author": {
        "name": "Nick Nisi",
        "email": "[email protected]"
      },
      "keywords": ["optional", "search", "terms"]
    }
    
  3. Add components (agents, skills, commands, or MCP servers)

  4. Sync marketplace:

    pnpm run sync
    

The sync script auto-discovers plugins and generates marketplace.json.

  1. Make sure to update the README for that plugin.

MCP Servers

Custom MCP Server

Use ${CLAUDE_PLUGIN_ROOT} for paths:

{
  "mcpServers": {
    "my-server": {
      "command": "node",
      "args": ["${CLAUDE_PLUGIN_ROOT}/mcp-server/dist/index.js"],
      "env": {
        "API_KEY": "${API_KEY}"
      }
    }
  }
}

Build: pnpm run build (bundles to dist/)

External MCP Server

{
  "mcpServers": {
    "external": {
      "command": "npx",
      "args": ["-y", "@org/mcp-server"]
    }
  }
}

Read the full file on GitHub · 102 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. yesterday First seen · 102 lines · 552 tokens per session scan A c37a087c0628

Subscribe to this mod's changes

claude-plugins CLAUDE.md is an instructions file published in the GitHub repository nicknisi/claude-plugins (114 stars, last pushed 21d ago), licensed MIT. It adds 552 tokens to every session, about $0.0028 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.