No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
by duthaho · Claude Skill · ★ 97
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is claudekit safe to install? View the security audit →
Claude Kit The development-workflow plugin for Claude Code. Opinionated skills and agents that teach Claude how to think, plan, review, and ship — so you don't spend your context window reinventing process. Features 35 Skills organized around a 6-phase workflow: Think → Review → Build → Ship → Maintain → Setup 13 user-invocable spine skills — typed directly as , the rest auto-trigger by context 24 Specialized Agents — planners, reviewers, implementers, and 4 plan-dimension reviewers Interactive Setup Wizard — scaffolds rules, modes, hooks, and MCP configs 7 Behavioral Modes — task-specific response optimization (installed via init) MCP Integrations — Context7, Sequential Thinking, Playwright, Memory, Filesystem (configured via init) Quick Start Install via Marketplace Add the claudekit marketplace: Install the plugin: Run the setup wizard to configure your project: Or install everything at once: Local Development Test the plugin locally without installing: What Configures The setup wizard interactively scaffolds project-level configuration: | Rules
| Stars | 97 |
| Forks | 56 |
| Language | JavaScript |
| Category | Claude Skill |
| License | MIT |
| Quality Score | 73.3915195694789/100 |
| Last Updated | 2026-07-22 |
| Created | 2025-11-29 |
| Platforms | claude-code, cli, mcp, node |
| Est. Tokens | ~15k |
These tools work well together with claudekit for enhanced workflows:
Looking for a claudekit alternative? If you're comparing claudekit with other claude skill tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
The Ultimate Claude Code Toolkit — 127 skills, 86 agents, 109 marketplace repos (11,700+ community skills), 30
Professional Claude Code marketplace with 140 development tools: 67 skills, 28 commands, 30 agents, 15 workflo
Sync MCP servers, Skills, Agents & Commands across Claude Code, Cursor, OpenCode, Codex. One config, all tools
Finish What You Start — Context engineering for Claude Code. Sessions last 20+ exchanges instead of cr
Zero-config Claude Code setup with enforced task scaffolding, structured memory, persistent context after comp
The Universal AI-Optimized Project Boilerplate. A Tiered Memory System (TMS) designed to maximize AI agent per
Explore other popular claude skill tools:
claudekit is A verification-first engineering toolkit for Claude Code. Built for senior ICs and tech leads who already know how to ship production code — and want a workflow that keeps the discipline tight without. It is categorized as a Claude Skill with 97 GitHub stars.
claudekit is primarily written in JavaScript. It covers topics such as ai-assistant, ai-coding, ai-tools.
You can find installation instructions and usage details in the claudekit GitHub repository at github.com/duthaho/claudekit. The project has 97 stars and 56 forks, indicating an active community.
claudekit is released under the MIT license, making it free to use and modify according to the license terms.
The top alternatives to claudekit on Agent Skills Hub include .claude, luxor-claude-marketplace, vsync. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.
The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.
Sources & who's responsible: