learning-mode-marketplace

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

learning-mode-marketplace 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 · 18 lines

What it actually says

{
  "name": "learning-mode-marketplace",
  "owner": {
    "name": "Muhammad El Sayed",
    "url": "https://github.com/melsayedx"
  },
  "description": "A hands-on learning plugin that makes the learner own one target while the assistant guides, validates, verifies, and preserves progress.",
  "plugins": [
    {
      "name": "learning-mode",
      "source": "./plugins/learning-mode",
      "description": "Adaptive, hands-on learning: define one outcome, diagnose the next prerequisite, guide and validate attempts without completing the learning target, verify load-bearing claims, and optionally preserve progress.",
      "version": "1.3.0",
      "homepage": "https://github.com/melsayedx/learning-mode"
    }
  ]
}

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