Plugin

continuous-improvement

Name: continuous-improvement
Author: naimkatiman

The 7 Laws of AI Agent Discipline with Claude Code and Codex-ready skills, hooks, commands, instinct packs, and MCP tools.

Component Overview

/continuous-improvement, /dashboard +5

Commands

Agents

continuous-improvement, ralph +2

Skills

PreToolUse, SessionEnd +2

Hooks

continuous-improvement

MCP Servers

LSP Servers

Output Styles

Install

npx claudepluginhub naimkatiman/continuous-improvement --plugin continuous-improvement

Component Details

Commands (7)

continuous-improvement

/continuous-improvement

Reflect on the current session, analyze observations for patterns, and show instinct status. Runs on-demand to save tokens.

dashboard

/dashboard

Visual dashboard showing instinct health, observation stats, and learning progress

discipline

/discipline

Quick reference card for the 7 Laws of AI Agent Discipline

planning-with-files

/planning-with-files

Create and maintain task_plan.md, findings.md, and progress.md for persistent file-based planning

ralph

/ralph

Convert PRD to executable JSON and run autonomous agent loop until all stories complete

superpowers

/superpowers

Activate mandatory agent workflows: brainstorming, TDD, code review, git worktrees, and structured development

workspace-surface-audit

/workspace-surface-audit

Audit workspace capabilities and recommend ECC-native skills, hooks, and workflows

Skills (4)

continuous-improvement

/continuous-improvement

Install structured self-improvement loops with instinct-based learning into Claude Code — research, plan, execute, verify, reflect, learn, iterate. On-demand or weekly analysis to save tokens. Supports multi-agent parallel analysis.

ralph

/ralph

Ralph is an autonomous AI agent loop that runs repeatedly until all PRD items are complete. Converts PRDs to executable JSON, implements stories iteratively with quality checks, and tracks progress.

superpowers

/superpowers

Agentic skills framework with mandatory workflows. Activates skills automatically before tasks: brainstorming, git-worktrees, writing-plans, test-driven-development, code-review, and more.

workspace-surface-audit

/workspace-surface-audit

Audit the active repo, MCP servers, plugins, connectors, env surfaces, and harness setup, then recommend the highest-value ECC-native skills, hooks, agents, and operator workflows. Use when the user wants help setting up Claude Code or understanding what capabilities are actually available in their environment.

Hooks (1)

Review workflow modifications before installing

Event Hooks

All tools

4 hooks across 4 events

MCP Servers (1)

Connects to external services

continuous-improvement

README

Before vs After — The 7 Laws of AI Agent Discipline

The 7 Laws of AI Agent Discipline

Stop your AI agent from skipping steps, guessing, and declaring "done" without verifying.

简体中文 | 日本語

New here? → QUICKSTART.md gets you working in 2 minutes.

The Problem
Install
The 7 Laws
Mulahazah: Auto-Leveling Learning
GitHub Action
Plugin Architecture
Examples
Works With
Uninstall
Contributing

The Problem

AI agents are great at individual steps. They're terrible at discipline.

They skip research. They plan loosely. They declare "done" before verifying. They add features mid-task. They never reflect. Each session, they repeat the same mistakes.

The 7 Laws fix that — plus a learning system (Mulahazah) that builds instincts over time. No config, no daemon, no manual setup.

Before vs After

Without continuous-improvement — agent skips research, declares "done" without verifying

You: Add rate limiting to the /api/users endpoint

Agent: I'll add rate limiting now.
       *writes express-rate-limit middleware*
       Done! I've added rate limiting to the /api/users endpoint.

You: Did you check if we already have rate limiting somewhere?
Agent: Let me check... oh, there's already a rate limiter in middleware/rateLimit.ts.
       I've created a duplicate. Let me fix that.

You: Did you test it?
Agent: Let me run the tests... they're failing. The import path is wrong.
       *fixes import*
       Now it works!

You: You also broke the /api/auth endpoint — it was sharing that middleware.
Agent: I see. Let me fix that too...

Result: 4 back-and-forth corrections. Duplicate code. Broken endpoint. 15 minutes wasted.

With continuous-improvement — agent follows the 7 laws

You: Add rate limiting to the /api/users endpoint

Agent: **[Law 1: Research]** Searching for existing rate limiting...
       Found: middleware/rateLimit.ts — already applies to /api/auth.
       Found: express-rate-limit already in package.json.

       **[Law 2: Plan]**
       WILL: Extend existing rateLimit middleware to cover /api/users
       WILL NOT: Create new middleware or change existing /api/auth behavior
       VERIFY: Run tests + curl /api/users 101 times to confirm 429 response

       **[Law 3: Execute one thing]** Adding /api/users to the route list
       in middleware/rateLimit.ts...

       **[Law 4: Verify]**
       ✓ npm test — 47/47 passing
       ✓ curl test — 429 after 100 requests
       ✓ /api/auth still works — 200 OK

View full README on GitHub

Similar Plugins

everything-claude-code

Complete collection of battle-tested Claude Code configs from an Anthropic hackathon winner - agents, skills, hooks, rules, and legacy command shims evolved over 10+ months of intensive daily use

Stats

Version3.2.0

Parent Repo Stars3

Parent Repo Forks3

MaintenanceGood

LicenseMIT

AddedApr 21, 2026

Actions

View on GitHub View README Plugin Marketplace JSON Homepage

Available In

continuous-improvement-dev3

Safety Signals

Critical

Matches all tools

Hooks run on every tool call, not just specific ones

The 7 Laws of AI Agent Discipline

Stop your AI agent from skipping steps, guessing, and declaring "done" without verifying.

简体中文 | 日本語

New here? → QUICKSTART.md gets you working in 2 minutes.

The Problem
Install
The 7 Laws
Mulahazah: Auto-Leveling Learning
GitHub Action
Plugin Architecture
Examples
Works With
Uninstall
Contributing

The Problem

AI agents are great at individual steps. They're terrible at discipline.

They skip research. They plan loosely. They declare "done" before verifying. They add features mid-task. They never reflect. Each session, they repeat the same mistakes.

The 7 Laws fix that — plus a learning system (Mulahazah) that builds instincts over time. No config, no daemon, no manual setup.

Before vs After

Without continuous-improvement — agent skips research, declares "done" without verifying

You: Add rate limiting to the /api/users endpoint

Agent: I'll add rate limiting now.
       *writes express-rate-limit middleware*
       Done! I've added rate limiting to the /api/users endpoint.

You: Did you check if we already have rate limiting somewhere?
Agent: Let me check... oh, there's already a rate limiter in middleware/rateLimit.ts.
       I've created a duplicate. Let me fix that.

You: Did you test it?
Agent: Let me run the tests... they're failing. The import path is wrong.
       *fixes import*
       Now it works!

You: You also broke the /api/auth endpoint — it was sharing that middleware.
Agent: I see. Let me fix that too...

Result: 4 back-and-forth corrections. Duplicate code. Broken endpoint. 15 minutes wasted.

With continuous-improvement — agent follows the 7 laws

You: Add rate limiting to the /api/users endpoint

Agent: **[Law 1: Research]** Searching for existing rate limiting...
       Found: middleware/rateLimit.ts — already applies to /api/auth.
       Found: express-rate-limit already in package.json.

       **[Law 2: Plan]**
       WILL: Extend existing rateLimit middleware to cover /api/users
       WILL NOT: Create new middleware or change existing /api/auth behavior
       VERIFY: Run tests + curl /api/users 101 times to confirm 429 response

       **[Law 3: Execute one thing]** Adding /api/users to the route list
       in middleware/rateLimit.ts...

       **[Law 4: Verify]**
       ✓ npm test — 47/47 passing
       ✓ curl test — 429 after 100 requests
       ✓ /api/auth still works — 200 OK

continuous-improvement

Component Overview

Install

Component Details

Commands (7)

Skills (4)

Hooks (1)

MCP Servers (1)

README

The 7 Laws of AI Agent Discipline

Contents

The Problem

Before vs After

Similar Plugins

everything-claude-code

continuous-improvement

Component Overview

Install

Component Details

Commands (7)

Skills (4)

Hooks (1)

MCP Servers (1)

README

The 7 Laws of AI Agent Discipline

Contents

The Problem

Before vs After

Similar Plugins

everything-claude-code

superpowers

context7-plugin

fullstack-dev-skills

planning-with-files

claude-md-management