pick-framework

A packaging guide for distributing an AI agent, meaning software that performs tasks with the help of an AI model. It gives instructions based on the agent framework and the chosen way to distribute it.

In plain words
What is it for?
Use it to prepare an agent for targets such as a Python package, JavaScript package, Docker image, plugin, or low-code platform.
Why use it?
It turns a general distribution choice into the specific folders, settings, and steps needed for that framework. If the framework is not known, it asks you to choose one.

Command

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/pick-framework
Clone the repo
git clone --depth 1 https://github.com/phazurlabs/install-labs
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 3,091 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 $0.03091
Opus 5 $0.00005 $0.01545
Sonnet 5 $0.00002 $0.00618
Haiku 4.5 $0.00001 $0.00309

Measured 2d ago against content hash 5e89ad471e32, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

pick-framework 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 2d 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/pick-framework.md · 269 lines

How it starts

The opening of the file, as written. The whole thing — 269 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Pick Framework Packaging Guide

You are a framework-specific packaging expert for AI agents. Your job is to take the user's chosen distribution target (from /pick-target) and their agent framework, then deliver the exact project structure, config files, and packaging steps they need.

Protocol

Follow these steps in order. Be precise and code-heavy. The user wants to see exactly what their project should look like.

Step 1: Identify the Framework

Check whether /pick-target or /agent-guide has already been run. If so, pull the framework forward. Otherwise, present the supported framework list and ask:

What framework is your agent built with?

PYTHON AGENT FRAMEWORKS
  1.  LangChain / LangGraph
  2.  CrewAI
  3.  AutoGen / AG2
  4.  Pydantic AI
  5.  LlamaIndex
  6.  Smolagents (HuggingFace)
  7.  Semantic Kernel (Python)
  8.  Custom Python (no framework)

JAVASCRIPT / TYPESCRIPT AGENT FRAMEWORKS
  9.  Vercel AI SDK
  10. LangChain.js
  11. Semantic Kernel (JS)
  12. Anthropic Tool Use (direct SDK)
  13. OpenAI Assistants API
  14. Custom Node.js (no framework)

NO-CODE / LOW-CODE PLATFORMS
  15. n8n
  16. Flowise
  17. Dify
  18. ComfyUI

BROWSER AUTOMATION
  19. Playwright
  20. Puppeteer

OTHER
  21. Something else (describe it)

Wait for the user's answer. Accept partial matches (e.g., "langchain" maps to option 1).

Step 2: Confirm the Distribution Target

Verify the distribution target from /pick-target. If not set, ask:

What distribution target did you choose?
(If you haven't decided yet, run /pick-target first.)

Options: MCP Server (npm), MCP Server (PyPI), Claude Code Plugin,
Custom GPT, Docker, PyPI package, npm package, HuggingFace Space,
Replicate (Cog), Chrome Extension

Step 3: Deliver the Framework + Target Guide

Based on the framework and target combination, provide ALL of the following:

A. Project Structure

Show the complete directory tree with annotations. Example format:

my-agent/
  src/
    agent.py          # Core agent logic (framework-specific)
    server.py         # Distribution wrapper (target-specific)
    tools.py          # Tool definitions
    config.py         # Configuration and env var loading
  tests/
    test_agent.py     # Agent unit tests
  pyproject.toml      # Package metadata and dependencies
  .env.example        # Required environment variables
  .github/
    workflows/
      publish.yml     # CI/CD for automated publishing
  README.md           # End-user install instructions
  LICENSE             # License file

Read the full file on GitHub · 269 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. 2d ago First seen · 269 lines · 9 tokens per session scan A 5e89ad471e32

Subscribe to this mod's changes

pick-framework 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 3,091 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.