Continuous Improvement

Name: Continuous Improvement
Author: naimkatiman

naimkatiman/continuous-improvement·5 plugins

Register a five-plugin marketplace that gives Claude Code persistent memory, agent discipline, Superpowers workflows, and transcript-driven instinct improvement.

Overview

continuous-improvement is a plugin marketplace for the Build phase that bundles persistent-memory agent discipline, MCP recall, hooks, and Superpowers workflow skills for Claude Code.

What is this marketplace?

5 plugins in one marketplace including continuous-improvement (v3.12.3) and bundled superpowers (v5.1.0)
25 bundled skills plus Mulahazah engine turning fixes into reusable instincts
MCP toolset for recall and reflection; instinct-aware hooks and GitHub Action transcript linter
Grounded on 7 Laws of AI Agent Discipline (research, plan, verify, reflect, learn)
Superpowers ships Obra’s workflow library: TDD, debugging, brainstorming, writing-plans, executing-plans, parallel agent
Marketplace lists 5 plugins
continuous-improvement plugin v3.12.3 with 25 bundled skills cited
superpowers plugin v5.1.0 from obra/superpowers

Compatible agents: Claude Code, Cursor, Windsurf, any compatible agent

Community signal: 6 GitHub stars.

What problem does it solve?

Solo builders lose hours re-explaining preferences and watching agents repeat mistakes because chat has no durable memory or enforced research-plan-verify-reflect-learn discipline.

Who is it for?

Heavy Claude Code users who want a packaged discipline layer, MCP memory, hooks, and Obra Superpowers in one five-plugin marketplace.

Skip if: Builders who only need one integration skill, avoid MCP or GitHub Actions setup, or want a minimal plugin count without workflow methodology.

What do I get? / Deliverables

After registering the marketplace, your agent can recall past corrections, lint transcripts into instincts, and chain Superpowers skills for steadier implementation and review habits.

Up to 5 enabled plugins including continuous-improvement and superpowers
25-skill discipline layer with recall MCP and instinct-aware hooks
Chained planning, TDD, debugging, and git workflows from Superpowers v5.1.0

Plugins in this marketplace

5 plugins — install individually after you add the marketplace.

PluginVersion

Continuous ImprovementThe 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 re-teaching. Built on the 7 Laws of AI Agent Discipline (research, plan, verify, reflect, learn) and shipped as 25 bundled skills, instinct-aware hooks, an MCP toolset for recall and reflection, and a GitHub Action transcript linter that feeds real work history back into sharper instincts.3.12.3 SuperpowersObra's core skills library: TDD, debugging, brainstorming, writing-plans, executing-plans, dispatching-parallel-agents, using-git-worktrees, finishing-a-development-branch, subagent-driven-development, requesting-code-review, receiving-code-review, systematic-debugging, verification-before-completion, writing-skills, using-superpowers. Vendored snapshot at third-party/superpowers/ pinned to upstream SHA f2cbfbe (v5.1.0). Companion to the /superpowers dispatcher in continuous-improvement plugin.5.1.0 Agent SkillsAddy Osmani's production-grade engineering skills for AI coding agents — 21 skills covering the full software development lifecycle: spec-driven-development, source-driven-development, context-engineering, idea-refine, incremental-implementation, test-driven-development, code-review-and-quality, code-simplification, security-and-hardening, debugging-and-error-recovery, performance-optimization, api-and-interface-design, frontend-ui-engineering, browser-testing-with-devtools, ci-cd-and-automation, deprecation-and-migration, documentation-and-adrs, git-workflow-and-versioning, planning-and-task-breakdown, shipping-and-launch, using-agent-skills. Vendored snapshot at third-party/addy-agent-skills/ pinned to upstream SHA 742dca5 (v1.0.0).1.0.0 Ruflo SwarmAgent 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). Slash commands /swarm and /watch. Skills swarm-init and monitor-stream. Cherry-picked from ruvnet/ruflo monorepo (the other 31 plugins are explicitly out of scope). Vendored snapshot at third-party/ruflo-swarm/ pinned to upstream SHA addb5cd (v0.2.0). Activation note: assets reference unpinned npx @claude-flow/cli@latest — supply-chain risk inert until installed.0.2.0 Oh My ClaudecodeMulti-agent orchestration system for Claude Code — 38 skills + 19 agents covering audit, plan, build, verify, ship, release, retrospective, and ops. Includes ralph (autonomous PRD loop), release, ultrawork, ultraqa, team, trace, visual-verdict, debug, deep-dive, deep-interview, autopilot, autoresearch. Vendored snapshot at third-party/oh-my-claudecode/ pinned to upstream SHA aacde3e (v4.13.6). Heavy overlap with continuous-improvement /ralph and /superpowers — pick per task.4.13.6

Recommended Marketplaces

1d1sdevkade/1d1s

The 1d1s marketplace from devkade ships one plugin, learning-tools (v0.1.0), framed as a domain learning toolkit that he…

3am.Botbrianclaridge/.3am.tts-agent

3am.bot is a one-plugin Claude Code marketplace entry that ships tts-agent, a cross-platform text-to-speech layer wired …1 stars

5h1wybgwon96/5h1w

The 5h1w marketplace by ybgwon96 distributes one plugin, 5h1w, marketed as a 5W1H Context Gatherer that finds holes in y…

Abdielou Discovery Skillabdielou/discovery-skill

abdielou-discovery-skill is a one-plugin Claude Code marketplace centered on discovery: guided sessions, structured faci…

Abstract To Concrete Designrizkiridha/abstract-to-concreate-design

abstract-to-concrete-design is a one-plugin Claude marketplace aimed at solo founders and designers who tend to jump str…6 stars

Agent Foreman Pluginsmylukin/agent-foreman

Agent-foreman-plugins is a Claude Code marketplace entry that delivers one agent-foreman plugin acting as a Long Task Ha…248 stars

Journey fit

Primary fit

BuildAgent skills & templates

The flagship continuous-improvement plugin is agent runtime and tooling you adopt while building with AI coders; it is the natural first shelf before ship and operate habits compound. Bundles 25 skills, hooks, MCP recall tools, and Superpowers planning/debug skills—core agent-tooling and workflow infrastructure for daily coding sessions.

How it compares

Agent discipline and workflow marketplace (25+ skills), not a single-task MCP connector.

Common Questions / FAQ

Who is Continuous Improvement for?

It is for indie and solo developers using Claude Code who want persistent memory, runtime discipline, and bundled Superpowers workflows without assembling plugins piecemeal.

When should I use Continuous Improvement?

Use it when you start sustained agent-assisted building and want corrections, plans, TDD, and debugging to compound via instincts, hooks, and transcript linting.

How do I add Continuous Improvement to my agent?

Add the naimkatiman/Continuous Improvement marketplace in Claude Code, enable the plugins you need (core plus superpowers), wire MCP and optional GitHub Action linter per repo docs.