Help us improve
Share bugs, ideas, or general feedback.
Share bugs, ideas, or general feedback.
Share bugs, ideas, or general feedback.
By kookr-ai
Curated skills and review subagents for AI-assisted development. Code patterns (TypeScript, async, error handling, DI, DDD), workflow (TDD, git commit hygiene, token efficiency), OSS contribution (PR critic, reviewer distillation, fork manager), and 15 review subagents (boundary-critic, design-minimalist, failure-mode-analyst, etc.) used by Kookr for iterative RFC review and pre-PR quality gates.
npx claudepluginhub kookr-ai/kookr --plugin kookr-toolkitFinds places in an RFC, roadmap, or deferred-feature list where scope was capped to dodge the hard part. Counterweight to design-minimalist. Invoke in rounds 1-2 of rfc-iterative-review; skip after round 3 unless the latest revision adds new "deferred" or "future work" items.
Audits HTTP routes and WebSocket message types for consistency, completeness, type safety, and test coverage. Use when the API surface changes or before releases.
Detects architecture drift two ways — (1) doc-vs-code drift (stale docs, undocumented modules, broken dependency directions) and (2) structural drift (file-size distribution, layer-boundary violations, dependency-graph corruption). Produces a drift score and hotspot list. Use periodically or before major changes.
Proactively scans codebase for architecture smells — god modules, scattered features, ambiguous ownership, feature envy, dense coupling. Evaluates the architecture itself, not just doc alignment. Use to find structural problems before they compound.
Traces assumptions inherited from referenced ADRs and accepted RFCs back to their source and checks whether the underlying reasoning is still valid. Invoke ONLY when the RFC proposes changes to behavior originally justified by an ADR's reasoning. Do NOT invoke for UI polish, documentation-only RFCs, or organizational changes.
Detect AI-induced architecture drift by measuring file-size distribution, layer-boundary violations, and dependency-graph corruption. Use to score structural health, spot drift hotspots, and produce a drift report.
Async flow control patterns - AbortController cancellation, async iterators for large datasets, worker thread selection, Promise combinator choice, stream backpressure in async pipelines
Claude Code hook system — all 25 event types, payloads, matchers, state machine, and integration patterns for agent monitoring
Analyze Claude Code telemetry, stats-cache, and history data from ~/.claude to identify UX friction, performance issues, workflow inefficiencies, and improvement opportunities.
Claude Code permission system — modes, allow/deny/ask rules, pattern syntax, settings precedence, and optimal configuration for minimal prompts with safety guardrails
Uses power tools
Uses Bash, Write, or Edit tools
Share bugs, ideas, or general feedback.
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge.
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge.
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Comprehensive skill pack with 66 specialized skills for full-stack developers: 12 language experts (Python, TypeScript, Go, Rust, C++, Swift, Kotlin, C#, PHP, Java, SQL, JavaScript), 10 backend frameworks, 6 frontend/mobile, plus infrastructure, DevOps, security, and testing. Features progressive disclosure architecture for 50% faster loading.
Develop, test, build, and deploy Godot 4.x games with Claude Code. Includes GdUnit4 testing, web/desktop exports, CI/CD pipelines, and deployment to Vercel/GitHub Pages/itch.io.
Harness-native ECC operator layer - 64 agents, 261 skills, 85 legacy command shims, reusable hooks, rules, selective install profiles, and production-ready workflows for Claude Code, Codex, OpenCode, Cursor, and related agent harnesses
Access thousands of AI prompts and skills directly in your AI coding assistant. Search prompts, discover skills, save your own, and improve prompts with AI.
Tools to maintain and improve CLAUDE.md files - audit quality, capture session learnings, and keep project memory current.
Comprehensive PR review agents specializing in comments, tests, error handling, type design, code quality, and code simplification
A smart attention router for developers running multiple AI coding agents.
Features · Architecture · Roadmap · ADRs
You run 5 Claude Code agents in parallel. One silently loops on the same failing test for the 50th time. Another asks a permission question. A third drifts off-task. Which one needs you?
Kookr watches them all, detects failure patterns, and routes your attention to the agent that needs you most.
~/.kookr/playbooks/ (per-user), and <repo>/.kookr/playbooks/ (project-local). See docs/playbook-scoping.md.node-pty) and the vendored dtach binary# Node.js 24 via NodeSource (tested version; v22 is also supported)
curl -fsSL https://deb.nodesource.com/setup_24.x | sudo -E bash -
sudo apt-get install -y nodejs
# Build tools + git — dtach is vendored and compiled via `pnpm build:dtach`
sudo apt-get install -y build-essential git
# pnpm
sudo npm install -g pnpm
# Xcode command line tools (provides git + build tools)
xcode-select --install
# Node.js + pnpm via Homebrew — dtach is vendored and compiled via `pnpm build:dtach`
brew install node@22 pnpm
Only required if you plan to regenerate the demo video with pnpm demo:record. Skip this section otherwise.
sudo apt-get install fonts-noto-color-emoji && fc-cache -fv. macOS: ships with the system. A startup preflight (demo/lib/preflight.ts) refuses to record if Chromium can't render colored emoji.sudo apt-get install ffmpeg. macOS: brew install ffmpeg. Used to mux the captured video with TTS narration.KOOKR_TTS=true). Skip if you record silent (KOOKR_TTS=) or point at an external TTS endpoint via KOOKR_TTS_URL.git clone https://github.com/kookr-ai/kookr.git && cd kookr
pnpm install
pnpm dev # backend on :4801 + Vite frontend on :5173
Open http://localhost:5173 in your browser. You're ready to launch and supervise agents.