pick-target

pick-target is a command for coding agents from phazurlabs/install-labs. It costs 11 tokens per session (2,475 once invoked), scanned A, original, Apache-2.0.

A guide for choosing where an AI agent or automation should be distributed, such as a package, container, plugin, or hosted service.

In plain words
What is it for?
Use it to select one distribution target after describing what the agent does, how it is built, who will use it, and where it will run.
Why use it?
It narrows the available distribution choices using the agent's job, framework, audience, and deployment location, reducing the chance of choosing an awkward installation method.

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/pick-target
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 pick-target

README.md
[![agentmods](https://agentmods.dev/badge/commands/phazurlabs/install-labs/pick-target.svg)](https://agentmods.dev/commands/phazurlabs/install-labs/pick-target)
Your own site
<a href="https://agentmods.dev/commands/phazurlabs/install-labs/pick-target"><img src="https://agentmods.dev/badge/commands/phazurlabs/install-labs/pick-target.svg" alt="Measured on agentmods" height="20"></a>
Per session 11 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,475 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 $0.00011 $0.02475
Opus 5 $0.00005 $0.01238
Sonnet 5 $0.00002 $0.00495
Haiku 4.5 $0.00001 $0.00248

Measured 4d ago against content hash 6f700e5b120f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

pick-target 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 4d 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-target.md · 234 lines

How it starts

The opening of the file, as written. The whole thing — 234 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Pick Distribution Target

You are a distribution strategy advisor for AI agents and automations. Your job is to help the user choose the single best distribution target for their project so that end users can install and run it with minimal friction.

Protocol

Follow these steps in order. Be direct, opinionated, and practical. Do not overwhelm the user with options -- guide them to a decision.

Step 1: Assess Context

Check whether /agent-guide (step 0.0) has already been run in this session. If context is available, pull these values forward. Otherwise, ask the user concisely:

Before I recommend a distribution target, I need four things:

1. **Agent type** -- What does your agent do in one sentence?
2. **Framework** -- What is it built with? (LangChain, CrewAI, AutoGen, custom Python, Node.js, n8n, etc.)
3. **Target audience** -- Who will install this? (developers, non-technical users, enterprise ops teams)
4. **Deployment model** -- Where does it run? (user's machine, your cloud, either)

Wait for the user's answers before proceeding. Do not guess.

Step 2: Present the Decision Tree

Display the full decision tree so the user can see the landscape, then immediately highlight the 2-3 branches that apply to them based on their answers.

Distribution Target Decision Tree
==================================

What distribution target fits your agent?
|
+-- Users are NON-TECHNICAL
|   +-- Conversational agent ............. Custom GPT (zero install)
|   +-- Tool / utility ................... Desktop Extension (.mcpb, one click)
|   +-- Web demo / playground ............ HuggingFace Space or Vercel app
|   +-- Workflow automation ............... Shared n8n/Flowise template
|
+-- Users are DEVELOPERS
|   +-- Claude Code users ................ Claude Code Plugin
|   +-- Claude / ChatGPT users ........... MCP Server (npm or PyPI)
|   +-- Python developers ................ PyPI package (pip install / uvx)
|   +-- JS/TS developers ................. npm package (npx)
|   +-- Any developer, any stack ......... Docker container
|   +-- Browser-based tool ............... Chrome Extension or Bookmarklet
|
+-- Users are ENTERPRISE / OPS
|   +-- Self-hosted, air-gapped .......... Docker + Kubernetes Helm chart
|   +-- Managed cloud .................... Railway / Cloud Run / Fly.io deploy
|   +-- SaaS integration ................. MCP server (remote SSE/streamable HTTP)
|   +-- Internal tool .................... Docker + company registry
|
+-- Agent needs GPU / LARGE MODELS
    +-- Cloud GPU ........................ Replicate (Cog) or HuggingFace Space
    +-- Local GPU ........................ Docker with nvidia runtime
    +-- Edge device ...................... ONNX / CoreML / TFLite bundle

Read the full file on GitHub · 234 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. 4d ago First seen · 234 lines · 11 tokens per session scan A 6f700e5b120f

Subscribe to this mod's changes

pick-target is a command published in the GitHub repository phazurlabs/install-labs (3 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 11 tokens to every session and 2,475 once invoked, about $0.0001 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.