plugin-packager

plugin-packager is an agent for coding agents from jimmc414/claude-code-plugin-marketplace. It costs 37 tokens per session (1,757 once invoked), scanned A, original, MIT.

An agent that packages selected Claude Code components into the folder structure required for a marketplace plugin.

In plain words
What is it for?
Use it after scanning components, or when you already know which components to package for submission.
Why use it?
It reduces errors when assembling skills, agents, commands, and hooks and prompts for the metadata needed to describe the plugin.

Agent

Installs and runs on its own, but its text points at files inside its plugin — anything it tells you to read at a ${CLAUDE_PLUGIN_ROOT} path is only there once the plugin is installed. Installing the plugin gets both.

Part of the plugin-publisher plugin — 1 skill, 3 agents shipped together

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 agents/jimmc414/claude-code-plugin-marketplace/plugin-packager
Clone the repo
git clone --depth 1 https://github.com/jimmc414/claude-code-plugin-marketplace

Or install plugin-publisher, the plugin that ships this one along with the rest of its 1 skill, 3 agents.

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 plugin-packager

README.md
[![agentmods](https://agentmods.dev/badge/agents/jimmc414/claude-code-plugin-marketplace/plugin-packager.svg)](https://agentmods.dev/agents/jimmc414/claude-code-plugin-marketplace/plugin-packager)
Your own site
<a href="https://agentmods.dev/agents/jimmc414/claude-code-plugin-marketplace/plugin-packager"><img src="https://agentmods.dev/badge/agents/jimmc414/claude-code-plugin-marketplace/plugin-packager.svg" alt="Measured on agentmods" height="20"></a>
Per session 37 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,757 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 $0.00037 $0.01757
Opus 5 $0.00018 $0.00879
Sonnet 5 $0.00007 $0.00351
Haiku 4.5 $0.00004 $0.00176

Measured today against content hash e5023bc8e967, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

plugin-packager 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 today.

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/plugin-publisher/agents/plugin-packager.md · 313 lines

How it starts

The opening of the file, as written. The whole thing — 313 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Plugin Packager Agent

You are a specialized agent that packages locally installed Claude Code components into a properly structured plugin ready for marketplace submission.

When Invoked

You will receive either:

  • A list of components selected by the user
  • Output from plugin-scanner with user selections
  • Direct user request to package specific components

Step 1: Confirm Components

List the components to be packaged:

## Components to Package

- Skills: [list]
- Agents: [list]
- Commands: [list]
- Hooks: [yes/no]

Proceed with packaging? [Waiting for confirmation]

Step 2: Gather Plugin Metadata

Ask the user for required information (suggest defaults based on components):

Required:

  • Plugin Name: Suggest based on component names (e.g., components parallel-*parallel-workflows)
  • Description: Suggest based on component descriptions
  • Author Name: Ask user

Optional (with smart defaults):

  • Category: Suggest based on component content
    • Code/git/testing related → development
    • Docker/K8s/deploy related → devops
    • Security scanning related → security
    • Test generation related → testing
    • Documentation related → documentation
    • Other → utilities
  • Keywords: Extract from component names and content
  • License: Default to MIT
  • Repository URL: Ask if they have one

Step 3: Analyze Components for Issues

Before copying, scan each component for issues:

# Check each component file for:
issues = []

# Hardcoded paths
if re.search(r'/home/\w+|/Users/\w+|C:\\Users\\\w+', content):
    issues.append("Hardcoded user path found")

# Potential secrets
if re.search(r'api[_-]?key|password|secret|token', content, re.I):
    issues.append("Potential secret reference")

# Local-specific configs
if re.search(r'localhost:\d+|127\.0\.0\.1', content):
    issues.append("Localhost reference - may need generalization")

Report any issues found and ask user how to handle them.

Step 4: Create Plugin Structure

Read the full file on GitHub · 313 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. today First seen · 313 lines · 37 tokens per session scan A e5023bc8e967

Subscribe to this mod's changes

plugin-packager is an agent published in the GitHub repository jimmc414/claude-code-plugin-marketplace (4 stars, last pushed today), licensed MIT. It adds 37 tokens to every session and 1,757 once invoked, about $0.0002 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 2026-09-04.

Related

Other agents, from other repositories

security-reviewer

Cross-ecosystem security audit specialist. Proactively reviews code for vulnerabilities static analysis misses — logic flaws, architectural security gaps, ecosystem-specific pitfalls. Use when modifying authentication, authorization, data handling, API endpoints, or any code processing user input, and before PRs…

melodic-software/claude-code-plugins · 62 tokens

architecture-guardian

Architecture enforcement specialist. Reviews code for dependency-direction violations, layer boundary breaches, pattern compliance, and structural integrity. Use when adding new projects or modules, modifying project references, creating cross-module interactions, or before PRs touching architecture-significant code.

melodic-software/claude-code-plugins · 53 tokens

doc-drift-detector

Documentation freshness and accuracy specialist. Detects stale references, outdated conventions, and documentation that no longer matches the code. Use during maintenance cycles, after significant refactors, or when the user says 'check docs', 'audit documentation', or 'find stale docs'.

melodic-software/claude-code-plugins · 58 tokens

implementer

Scope-fenced implementation worker dispatched per phase by /implementation:implement-dispatch (directly, or chained from callers such as /work-items:work): executes exactly one brief inside its assigned or self-provisioned worktree, commits and pushes early, and returns a verdict plus identifiers. Not intended for…

melodic-software/claude-code-plugins · 70 tokens

intent-tracer

Runs the full /discovery:trace-intent discipline in a fresh context and persists the INTENT.md index plus its sidecars into the topic's memory slice, returning a file pointer and a verification request rather than the review threads, tickets and documents it read. Dispatched by /discovery:trace-intent; not intended…

melodic-software/claude-code-plugins · 77 tokens

researcher

Runs the full /discovery:research discipline in a fresh context and persists the RESEARCH.md index plus its sidecars into the topic's memory slice, returning a file pointer and a verification request rather than the research transcript. Dispatched by /discovery:research and by /discovery:research-deep; not intended…

melodic-software/claude-code-plugins · 75 tokens