claude-opencode

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

claude-opencode 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 · 25 lines

What it actually says

{
  "name": "claude-opencode",
  "owner": {
    "name": "Khaled Hussein"
  },
  "metadata": {
    "description": "Plan coding work with Claude Code, delegate the implementation to OpenCode. Use Opus's judgment for architecture and convention-matching, let cheaper models handle the mechanical execution."
  },
  "plugins": [
    {
      "name": "claude-opencode",
      "source": "./plugins/claude-opencode",
      "description": "Two skills for delegating coding work to OpenCode. Use opencode-implement when you want Claude to plan first and get your approval; use opencode-delegate when you want to hand a task off immediately. Model-agnostic — works with any provider OpenCode supports.",
      "category": "productivity",
      "keywords": [
        "opencode",
        "delegation",
        "planning",
        "multi-agent",
        "workflow"
      ],
      "license": "MIT"
    }
  ]
}

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