ponytail

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

ponytail 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.

plugins/ponytail/.claude-plugin/plugin.json · 36 lines

What it actually says

{
  "author": {
    "name": "DietrichGebert",
    "url": "https://github.com/DietrichGebert"
  },
  "description": "Forces the laziest solution that actually works.",
  "hooks": {
    "SubagentStart": [
      {
        "hooks": [
          {
            "command": "node \"${CLAUDE_PLUGIN_ROOT}/hooks/ponytail-subagent.js\"",
            "statusMessage": "Loading ponytail mode...",
            "timeout": 5,
            "type": "command"
          }
        ]
      }
    ],
    "UserPromptSubmit": [
      {
        "hooks": [
          {
            "command": "node \"${CLAUDE_PLUGIN_ROOT}/hooks/ponytail-mode-tracker.js\"",
            "statusMessage": "Tracking ponytail mode...",
            "timeout": 5,
            "type": "command"
          }
        ]
      }
    ]
  },
  "name": "ponytail",
  "version": "0.1.0"
}

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