agent-packaging-foundations

agent-packaging-foundations is a skill for Claude Code from phazurlabs/install-labs. It costs 66 tokens per session (2,371 once invoked), scanned B, original, Apache-2.0.

A guide to packaging AI agents and automations as software that other people can install. It explains why agents often depend on secrets, model files, several runtimes, changing frameworks, hardware, and stored state.

In plain words
What is it for?
Use it when planning an installable agent, documenting dependencies, designing its configuration, or preparing it for distribution.
Why use it?
It helps avoid packages that only work on the creator's computer because hidden dependencies were missed. It provides principles for making installation and distribution more predictable.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

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 skills/phazurlabs/install-labs/agent-packaging-foundations
Any agent
npx skills add phazurlabs/install-labs --skill agent-packaging-foundations
Clone the repo
git clone --depth 1 https://github.com/phazurlabs/install-labs

Made for: Claude Code.

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 agent-packaging-foundations

README.md
[![agentmods](https://agentmods.dev/badge/skills/phazurlabs/install-labs/agent-packaging-foundations.svg)](https://agentmods.dev/skills/phazurlabs/install-labs/agent-packaging-foundations)
Your own site
<a href="https://agentmods.dev/skills/phazurlabs/install-labs/agent-packaging-foundations"><img src="https://agentmods.dev/badge/skills/phazurlabs/install-labs/agent-packaging-foundations.svg" alt="Measured on agentmods" height="20"></a>
Per session 66 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,371 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 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 $0.00066 $0.02371
Opus 5 $0.00033 $0.01185
Sonnet 5 $0.00013 $0.00474
Haiku 4.5 $0.00007 $0.00237

Measured 6d ago against content hash 21f5dd666d83, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade B, and why

agent-packaging-foundations scanned grade B 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 6d 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.

Asks for rootmediumPrivilege escalation

A mod that escalates privileges can change anything on the machine, not only the project.

Requiring `sudo pip install` or `sudo npm install -g`. Install to user space. If you need system access, explain exactly why.
skills/agent-packaging-foundations/SKILL.md · 241 lines

How it starts

The opening of the file, as written. The whole thing — 241 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Packaging Foundations

Why Agents Are Harder to Package Than Traditional Software

Traditional software has a single runtime, a known dependency tree, and a build artifact. AI agents break every assumption:

Challenge Traditional Software AI Agents
Secrets Maybe one DB connection string 3-8 API keys across providers (OpenAI, Anthropic, Pinecone, etc.)
Model weights No large binary blobs 500MB-70GB model files that can't ship in a package
Runtime environment One language runtime Python + Node.js + system libs + CUDA/Metal
Config sprawl One config file .env, config.yaml, plugin.json, mcp.json, framework configs, all in different directories
Framework churn Stable APIs LangChain, CrewAI, AutoGen — breaking changes monthly
Hardware variance CPU is CPU GPU type, VRAM, quantization level all affect behavior
State Database handles it Vector stores, conversation memory, tool caches across restarts

The result: an agent that works on the author's machine silently depends on 15 things the author forgot they installed.


8 Core Packaging Principles for Agents

1. One Command to Install, One Command to Uninstall

# GOOD: single entry point
npx @your-org/my-agent install
npx @your-org/my-agent uninstall

# GOOD: platform package manager
brew install my-agent && brew uninstall my-agent

# BAD: multi-step scavenger hunt
git clone ... && cd ... && pip install -r ... && cp config.example.yaml ...

If your install instructions have more than one step, wrap them in a script.

2. Secrets via Environment Variables, Never Hardcoded

# GOOD: read at runtime
OPENAI_API_KEY=sk-... my-agent start

# GOOD: .env file (gitignored)
my-agent init  # creates .env template with comments

# BAD: baked into config
# config.yaml: api_key: "sk-proj-abc123..."

Ship a .env.example with every key listed, commented, and explained. Never write a real key to disk in plaintext unless the user explicitly opts in.

Read the full file on GitHub · 241 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. 6d ago First seen · 241 lines · 66 tokens per session scan B 21f5dd666d83

Subscribe to this mod's changes

agent-packaging-foundations is a skill published in the GitHub repository phazurlabs/install-labs (3 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 66 tokens to every session and 2,371 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it B with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.