setup

An installer plugin for adding selected tools to a project. It connects to the official installers for LifeOS, MuleSoft API-design skills, Salesforce agent skills, and a Spring Boot project generator.

In plain words
What is it for?
Use it to install LifeOS, MuleSoft Anypoint API skills, Salesforce Agentforce skills, or the Dr JSkill Spring Boot generator.
Why use it?
It avoids keeping copies of those tools in the plugin and lets each setup use the upstream installation when permission is given. It also provides separate setup commands for each target.

Plugin for Claude Code

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.

Claude Code
/plugin marketplace add rsts-dev/claude-buddy-marketplace
agentmods
npx agentmods add plugins/rsts-dev/claude-buddy-marketplace/setup
Clone the repo
git clone --depth 1 https://github.com/rsts-dev/claude-buddy-marketplace

Made for: Claude Code.

Per session not measured What this adds to a session before it is invoked.
When invoked not measured The manifest loads nothing itself; its 4 skills, 4 commands cost 589 tokens a session between them.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Security

Grade A, and why

setup 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.

plugins/setup/.claude-plugin/plugin.json · 11 lines

What it actually says

{
  "name": "setup",
  "version": "2.1.0",
  "description": "Multi-target setup plugin — thin wrappers that drive the OFFICIAL installers for LifeOS (the Life Operating System), MuleSoft API-design skills, Salesforce agent skills, and the Dr JSkill Spring Boot generator. Nothing is vendored; each target fetches the upstream install at run time with permission. USE WHEN setup lifeos, install lifeos, /setup:lifeos, set up mulesoft skills, install anypoint api skills, /setup:mulesoft, set up salesforce skills, install agentforce skills, sf skills, /setup:salesforce, set up spring boot, install dr jskill, java project generator, /setup:springboot.",
  "author": { "name": "Claude Buddy Contributors", "url": "https://github.com/rsts-dev/claude-buddy-marketplace" },
  "license": "MIT",
  "homepage": "https://claude-buddy.dev",
  "repository": "https://github.com/rsts-dev/claude-buddy-marketplace",
  "keywords": ["setup", "lifeos", "mulesoft", "salesforce", "springboot", "skills", "installer", "anypoint", "agentforce", "dr-jskill", "pai", "telos"]
}
Contents

What it installs

The manifest is a name and a version. 4 skills, 4 commands travel with it, and installing the plugin installs all of them — 589 tokens a session between them. Each is measured on its own page, and each can be installed alone.

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 · 11 lines scan A 8aa9d88e538b

Subscribe to this mod's changes

setup is a plugin published in the GitHub repository rsts-dev/claude-buddy-marketplace (17 stars, last pushed 12d ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 2026-08-30.