Agent Plugins Marketplace
← All plugins

agent-ops-skills

v0.1.0

Skills from agent-ops-patterns: hand your agent a source (a course, a paper set) and get a disposition record with a quoted file:line or a scoped command with its exit code and output per verdict. First skill: Stanford CS329A "Self-Improving AI Agents".

Claude Code1 Skill

By David KooiLicense: MIT1 GitHub starsUpdated 3 days ago

Directory evidence

Runtimes
Claude Code
Parsed components
1 skill or MCP entry
Source updated
Sep 20, 2026
Manifest status
Canonical path parsed

The directory validates manifest shape and source location. It does not execute the plugin or provide a security endorsement. Review the indexing methodology →

Install agent-ops-skills for Claude Code

Installs for the current user
claude plugin marketplace add IchenDEV/agent-plugin-mkt
claude plugin marketplace update agent-plugin-marketplace
claude plugin install agent-ops-skills@agent-plugin-marketplace

Paste and run these commands in a terminal with Claude Code. They add and refresh the PluginsMP catalog, then install this plugin.

The installer fetches third-party code from the source repository shown on this page. This directory validates manifest structure and source location, but does not perform a security audit; review the manifest, components, and source before installing.

Get the source manually
git clone https://github.com/u00dxk2/agent-ops-patterns

Clone the source repository, then follow its setup instructions to add the plugin to a compatible client. The repository root is the plugin root.

Plugin files

agent-ops-skills/
├── .claude-plugin/plugin.json
└── skills/cs329a-self-improving-agents/SKILL.md

Included Skills1

cs329a-self-improving-agentsskills/cs329a-self-improving-agents/SKILL.md

Read Stanford CS329A "Self-Improving AI Agents" (verifiers, test-time compute, planning, RL, deep-research agents, agentic evals) against THIS repo and write a disposition record - for each of ten ideas, APPLIES / DOES NOT APPLY / ALREADY IN PLACE / NOT DECIDABLE / UNREADABLE with a quoted file:line or a scoped command with its exit code and output per verdict, bars pre-committed before any deciding number is read, and "declined, because" as a complete answer. Use when an operator points the agent at the course, or asks what a system that runs LLM judges, eval gates, health checks, or research ingestion should take from it. Offers, never assigns.

Plugin manifests1

.claude-plugin/plugin.json
{
  "name": "agent-ops-skills",
  "description": "Skills from agent-ops-patterns: hand your agent a source (a course, a paper set) and get a disposition record with a quoted file:line or a scoped command with its exit code and output per verdict. First skill: Stanford CS329A \"Self-Improving AI Agents\".",
  "version": "0.1.0",
  "author": {
    "name": "David Kooi",
    "url": "https://github.com/u00dxk2"
  },
  "homepage": "https://github.com/u00dxk2/agent-ops-patterns",
  "repository": "https://github.com/u00dxk2/agent-ops-patterns",
  "license": "MIT",
  "keywords": [
    "agent-skills",
    "llm-judges",
    "verification",
    "eval-gates",
    "cs329a"
  ]
}

For maintainers

If you maintain this plugin, link to this source-backed listing from your README so users can review its manifest and indexed components.

[agent-ops-skills on Agent Plugins Marketplace](https://pluginsmp.com/plugins/agent-ops-skills)