python-coding-agent-skill

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

python-coding-agent-skill 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": "python-coding-agent-skill",
  "owner": {
    "name": "Ankit Aglawe",
    "email": "[email protected]"
  },
  "metadata": {
    "description": "Production Python skill for AI coding agents — enforces clean, PEP-compliant, modern Python 3.13+ code"
  },
  "plugins": [
    {
      "name": "prod-python",
      "source": "./prod-python",
      "description": "Enforces production-grade Python — modern typing, PEP standards, no AI slop patterns",
      "version": "1.0.0",
      "author": {
        "name": "Ankit Aglawe"
      },
      "license": "MIT",
      "keywords": ["python", "production", "coding", "clean-code", "pep8", "typing", "ai-slop"],
      "category": "code-quality"
    }
  ]
}

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