hands-on-deck

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.

Security

Grade A, and why

hands-on-deck 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 yesterday.

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.

.claude-plugin/marketplace.json · 19 lines

What it actually says

{
  "name": "hands-on-deck",
  "owner": {
    "name": "Every Consulting"
  },
  "metadata": {
    "description": "Agent-native PowerPoint manipulation \u2014 deck.py, a CLI built around how LLM agents actually fail.",
    "version": "1.0.0"
  },
  "plugins": [
    {
      "name": "hands-on-deck",
      "source": "./",
      "description": "Agent-native PowerPoint manipulation. One CLI (deck.py) lets agents inspect, edit, create, and verify .pptx files through atomic JSON patches \u2014 with self-correcting errors, deterministic geometry repair, and built-in visual verification.",
      "version": "3.1.0"
    }
  ]
}

Files

What ships with it

1 file beside marketplace.json in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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.

Related

Other plugins, from other repositories