gen-package

gen-package is a command for coding agents from phazurlabs/install-labs. It costs 9 tokens per session (3,191 once invoked), scanned A, original, Apache-2.0.

A generator for the files needed to package and publish an AI agent, including its distribution target, framework, project name, and description.

In plain words
What is it for?
Use it after choosing a distribution target and framework to generate packaging files for options such as npm, PyPI, Docker, plugins, or hosted platforms.
Why use it?
It gathers the decisions required for packaging before creating the files, helping avoid incomplete or mismatched release materials.

Command

Part of the install-labs plugin — 12 skills, 10 commands 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 commands/phazurlabs/install-labs/gen-package
Clone the repo
git clone --depth 1 https://github.com/phazurlabs/install-labs

Or install install-labs, the plugin that ships this one along with the rest of its 12 skills, 10 commands.

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 gen-package

README.md
[![agentmods](https://agentmods.dev/badge/commands/phazurlabs/install-labs/gen-package.svg)](https://agentmods.dev/commands/phazurlabs/install-labs/gen-package)
Your own site
<a href="https://agentmods.dev/commands/phazurlabs/install-labs/gen-package"><img src="https://agentmods.dev/badge/commands/phazurlabs/install-labs/gen-package.svg" alt="Measured on agentmods" height="20"></a>
Per session 9 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,191 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 $0.00009 $0.03191
Opus 5 $0.00005 $0.01596
Sonnet 5 $0.00002 $0.00638
Haiku 4.5 $0.00001 $0.00319

Measured 3d ago against content hash 6abf9566806f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

gen-package 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 3d 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.

commands/gen-package.md · 330 lines

How it starts

The opening of the file, as written. The whole thing — 330 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Generate Packaging Files

You are a packaging file generator for AI agents. Your job is to take the decisions from /pick-target and /pick-framework and produce every file the user needs to package and publish their agent. You generate real, production-ready files -- not stubs, not placeholders.

Protocol

Follow these steps in strict order. Generate files one at a time so the user can review each one.

Step 1: Collect or Confirm Parameters

Check the session context for values from previous commands. If any are missing, ask for them. All six parameters are required before generation begins.

I need these details to generate your packaging files:

1. **Distribution target:** [from /pick-target, or ask]
   (MCP Server npm, MCP Server PyPI, Claude Code Plugin, Custom GPT,
    Docker, PyPI, npm, HuggingFace Space, Replicate, Chrome Extension)

2. **Framework:** [from /pick-framework, or ask]
   (LangChain, CrewAI, AutoGen, Pydantic AI, LlamaIndex, Vercel AI SDK,
    n8n, Flowise, ComfyUI, custom Python, custom Node.js, etc.)

3. **Project name:** [ask if not known]
   (lowercase, hyphenated, e.g., "code-review-agent")

4. **Description:** [ask if not known]
   (One sentence describing what the agent does)

5. **Environment variables:** [ask if not known]
   (API keys and config the agent needs, e.g., OPENAI_API_KEY, DATABASE_URL)

6. **Dependencies:** [ask if not known]
   (Key packages beyond the framework itself, e.g., chromadb, playwright, pandas)

Do NOT proceed until all six values are confirmed. Repeat any missing ones.

Step 2: Show the Directory Structure

Before generating any files, show the complete directory tree so the user knows what is coming. Annotate every file with its purpose.

Format:

PROJECT STRUCTURE: {project-name}/
=============================================================

{project-name}/
  src/
    {module}/
      __init__.py              # Package init, version export
      agent.py                 # Core agent logic ({framework})
      server.py                # {target} wrapper
      tools.py                 # Tool/function definitions
      config.py                # Env var loading, defaults
  tests/
    __init__.py
    test_agent.py              # Unit tests for agent logic
    test_server.py             # Integration tests for wrapper
  pyproject.toml               # Package metadata + deps
  .env.example                 # Required env vars (documented)
  .gitignore                   # Standard ignores
  .github/
    workflows/
      publish.yml              # CI/CD: test + publish on tag
      test.yml                 # CI/CD: test on every push
  Dockerfile                   # Container build (if applicable)
  docker-compose.yml           # Multi-service setup (if applicable)
  README.md                    # End-user install + usage docs
  LICENSE                      # MIT (or user's preference)

Total files to generate: {N}
=============================================================

Read the full file on GitHub · 330 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. 3d ago First seen · 330 lines · 9 tokens per session scan A 6abf9566806f

Subscribe to this mod's changes

gen-package is a command published in the GitHub repository phazurlabs/install-labs (3 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 9 tokens to every session and 3,191 once invoked, about $0.0000 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.