openhumancy

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

openhumancy 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.

.claude-plugin/marketplace.json · 26 lines

What it actually says

{
  "name": "openhumancy",
  "owner": {
    "name": "OpenHumancy",
    "url": "https://openhumancy.com"
  },
  "metadata": {
    "description": "Skills and plugins for OpenHumancy — delegate real-world tasks to human workers.",
    "version": "0.1.0"
  },
  "plugins": [
    {
      "name": "openhumancy",
      "source": "./plugins/openhumancy",
      "description": "Delegate real-world tasks to human workers via the OpenHumancy API.",
      "version": "0.1.0",
      "author": "OpenHumancy",
      "homepage": "https://openhumancy.com",
      "repository": "https://github.com/openhumancy/openhumancy-skill",
      "license": "MIT",
      "keywords": ["openhumancy", "humans", "tasks", "ton", "delivery", "mystery-shopping"],
      "category": "integrations"
    }
  ]
}

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