By ngocsangyem
An opinionated Claude Code harness that orchestrates the full development workflow—from planning, design, and implementation through testing, code review, security auditing, and deployment—while integrating with Jira, Confluence, GitHub, and browser automation for AI-assisted project delivery.
```
```
```
Decompose a spec/PRD into sized user stories with optional Jira ticket creation and codebase-aware tech breakdown. Stops before plan creation.
```
Cost and learning analysis agent that tracks token usage, generates cost reports, extracts patterns from sessions, and maintains institutional memory. Runs automatically at session end (Phase 6) and on demand via /mk:budget command.
System design specialist for architectural tradeoff evaluation and ADR generation. Use when tasks touch database schema, new service boundaries, auth systems, API contracts, or infrastructure. Also use for any task classified as complex by the orchestrator.
Use this agent when you need to brainstorm software solutions, evaluate architectural approaches, or debate technical decisions before implementation. Examples: "Should I use WebSockets or SSE for real-time?", "What's the best approach for file uploads?", "Evaluate REST vs GraphQL for our API." Use proactively during Phase 1 (Plan) when the task involves significant technical decisions or multiple viable approaches.
Execute bulk Confluence operations on 10+ pages via the confluence-as CLI wrapper: bulk-label, bulk-move, bulk-delete. Dry-run is MANDATORY first. Routed by mk:confluence-bulk skill. NOT for single-page ops (confluence-page); NOT for comments/attachments (confluence-collaborate).
Manage Confluence collaboration surface: comments, attachments, labels, watchers. Routed by mk:confluence-collaborate skill. NOT for page CRUD (confluence-page); NOT for bulk ops (confluence-bulk).
AI-agent-driven browser automation (long autonomous sessions, Browserbase-capable). Use when the user needs to interact with websites across many steps, automate complex browser tasks, or run unattended flows. Triggers include 'open a website', 'fill out a form', 'automate browser actions', 'login to a site', or any task requiring programmatic web interaction. NOT for manual E2E test generation (see mk:qa-manual); NOT for deterministic scripted flows (see mk:playwright-cli).
Detects task agent, complexity tier, and model automatically at Phase 0 orient. Invoked first in every workflow. NOT for runtime agent routing inside a single skill (see orchestration-rules.md).
Enforces KISS/DRY/YAGNI during authoring and ad-hoc quality reviews. Pragmatic standards: concise, direct, no unnecessary comments. NOT for post-hoc diff/PR review (see mk:review); NOT for behavior-preserving simplification passes (see mk:simplify).
Use when working with Angular code — components, signals, services, forms, routing, HTTP, testing, SSR, or tooling. Targets Angular v20+ modern patterns. Auto-activates on .ts files in Angular projects (detected via angular.json).
REST/GraphQL API design: resource naming, HTTP methods, status codes, pagination, versioning, error formats. Use for 'design API', 'endpoint patterns'.
Matches all tools
Hooks run on every tool call, not just specific ones
Executes bash commands
Hook triggers when Bash tool is used
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Modifies files
Hook triggers on file write and edit operations
Modifies files
Hook triggers on file write and edit operations
Uses power tools
Uses Bash, Write, or Edit tools
Uses power tools
Uses Bash, Write, or Edit tools
AI agent toolkit for Claude Code
113 skills · 39 agents · 25 commands · 7 modes · 24 rules · 4 conditional rules · 17 hook scripts · 4-layer+ security
MeowKit installs a .claude/ directory that Claude Code reads at session start. It enforces a structured 7-phase workflow with hard gates, TDD, security scanning, and scoped topic-file memory (fixes.md, review-patterns.md, architecture-decisions.md). Zero external dependencies for core workflow.
Homepage: meowkit.dev · Docs: docs.meowkit.dev
MeowKit installs two ways. Pick one per project — running both resolves the
same skills and agents twice (mewkit doctor warns when it detects both).
npx mewkit init
The CLI fetches the latest release from GitHub, prompts for config, and scaffolds .claude/ into your project. Skills resolve as /mk:*, agents as mk:*.
Installs the mk plugin from the MeowKit marketplace. Skills (/mk:*), agents (mk:*), and hooks all resolve under the plugin; nothing is copied into your project.
# Claude Code
claude plugin marketplace add ngocsangyem/MeowKit
claude plugin install mk@meowkit
# Codex
codex plugin marketplace add ngocsangyem/MeowKit
codex plugin add mk@meowkit
The plugin distribution is generated by mewkit build-plugin (the plugin/ payload + marketplace.json for both runtimes) and staged into each release.
After installing MeowKit, run:
npx mewkit setup
This creates the Python venv at .claude/skills/.venv, installs pip packages
(google-genai, pillow, python-dotenv), and interactively prompts for
optional system deps (ImageMagick, FFmpeg, Playwright browsers).
Run once per project. Idempotent — safe to re-run after upgrades.
To verify your environment after setup:
npx mewkit doctor # Verify environment
| Package | npm | Description |
|---|---|---|
mewkit | npx mewkit <cmd> | CLI — init, upgrade, doctor, validate, budget, memory |
meowkit/
├── .claude/ Source of truth — agents, skills, rules, hooks
│ ├── agents/ 39 specialist agents
│ ├── skills/ 113 skills (mk: namespace)
│ ├── rules/ 24 enforcement rules
│ ├── hooks/ 17 hook scripts — lifecycle hooks + handlers + libraries
│ ├── commands/ 25 slash commands
│ ├── modes/ 7 behavioral modes
│ ├── memory/ Machine-local topic files (gitignored; scaffolded by `mewkit setup`)
│ ├── scripts/ Python validators + shell utilities
│ └── settings.json
├── tasks/ Task templates
├── packages/
│ ├── mewkit/ CLI (npm as mewkit)
│ └── landing/ Landing page (meowkit.dev, Nuxt + Tailwind v4)
├── scripts/ Release automation
├── website/ VitePress documentation
├── CLAUDE.md Entry point for Claude Code
├── .releaserc.cjs Semantic release config
└── .github/workflows/ CI/CD (release, beta, PR validation)
See RELEASING.md for the complete release guide — manual steps, CI/CD automation, troubleshooting.
npm install # Install dependencies
npm run build # Build both packages
npm test # Run tests
npm run lint # Lint
npm run typecheck # Type check
MIT
npx claudepluginhub ngocsangyem/meowkit --plugin mkComplete project development toolkit: 23 agents, 23 slash commands, 29 lifecycle hooks, and 69 reusable skills for Claude Code workflows
Universal Claude Code workflow with specialized agents, skills, hooks, and output styles for any software project. Includes orchestrator, code-reviewer, debugger, docs-writer, security-auditor, refactorer, and test-architect agents.
13 agents, 35 skills, 19 commands, 15 hooks — spec-driven, multi-agent orchestration for Claude Code with per-phase model tiers, opt-in lifecycle hooks, and optional cross-device semantic memory.
Multi-agent /workflow development pipeline (planner → plan-review → coder → code-review) with typed handoff contracts, lifecycle hooks, and MCP servers.
Context-Driven Development plugin that transforms Claude Code into a project management tool with structured workflow: Context → Spec & Plan → Implement
Use Claude Code As Is - native plugin leveraging built-in architecture