Claude Code that gets sharper every session: runtime discipline and instinct memory (the 7 Laws of AI Agent Discipline)
This repository also configures its own agents. See what continuous-improvement tells them →
naimkatiman/continuous-improvement
Plugin Claude Code
Bundles 27 skills, 6 hooks · 2,170 tokens together
The persistent-memory and runtime-discipline layer for Claude Code. It remembers the corrections you already gave, grounds every edit in real facts before it lands, and — through the Mulahazah engine — turns each fix into a reusable instinct, so a lesson learned once is applied automatically next time with no…
naimkatiman/continuous-improvement
Plugin Claude Code
Bundles 21 skills · 987 tokens together
Production-grade engineering skills for AI coding agents — covering the full software development lifecycle from spec to ship.
naimkatiman/continuous-improvement
Plugin Claude Code
Bundles 36 skills, 17 agents · 1,301 tokens together
Multi-agent orchestration system for Claude Code.
naimkatiman/continuous-improvement
Plugin Claude Code
Bundles 2 skills, 1 command, 1 agent · 61 tokens together
Agent teams, swarm coordination, Monitor streams, and worktree isolation — wraps 4 swarm + 8 agent MCP tools (12 total) plus 6 topologies (hierarchical / mesh / hierarchical-mesh / ring / star / adaptive).
naimkatiman/continuous-improvement
Plugin Claude Code
Bundles 13 skills · 358 tokens together
Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: