continuous-improvement

naimkatiman/continuous-improvement

★ 3 stars JavaScript 🤖 AI/LLM Updated today

The 7 Laws of AI Agent Discipline for Claude Code (engine: Mulahazah). Stop your agent from skipping steps, guessing, and declaring 'done' without verifying. 13-skill plugin, MCP server, observation hooks, GitHub Action transcript linter.

View on GitHub →

Quick Install

Copy the config for your editor. Some servers may need additional setup — check the README.

Add to claude_desktop_config.json:

{
  "mcpServers": {
    "continuous-improveme": {
      "command": "npx",
      "args": [
        "-y",
        "naimkatiman/continuous-improvement"
      ]
    }
  }
}

README Excerpt

<p align="center"> <img src="assets/combined.gif" alt="Before vs After — The 7 Laws of AI Agent Discipline" width="700" /> </p> <h1 align="center">The 7 Laws of AI Agent Discipline</h1> <p align="center"> <b>Stop your Claude Code agent from skipping steps, guessing, and declaring "done" without verifying.</b>

Topics

ai-agentsai-disciplineanthropicclaude-codeclaude-code-marketplaceclaude-code-plugincodexcoding-agentscontinuous-improvementcursordeveloper-toolsgithub-actionhooksinstinct-learningllm

continuous-improvement

Quick Install

README Excerpt

Topics

Related AI/LLM Servers