by drobins25 · Agent Tool · ★ 52
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
A Claude Code plugin that runs your work through a creative → implement → review loop, builds the expert agents you consult, and locks in the taste you keep showing. Stop vibe coding, start crafting.
| Stars | 52 |
| Forks | 5 |
| Language | Shell |
| Category | Agent Tool |
| License | MIT |
| Quality Score | 52.0310638192928/100 |
| Last Updated | 2026-08-20 |
| Created | 2026-05-01 |
| Platforms | claude-code, cli |
| Est. Tokens | ~10k |
These tools work well together with craft for enhanced workflows:
Looking for a craft alternative? If you're comparing craft with other agent tool tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
> CLAUDER - a safer and supercharged Claude Code
Hands-on tutorials for building AI agents from scratch. Learn LLM APIs, prompt engineering, tool calling, and
HeyClaude (formerly Claude Pro Directory) is a searchable collection of pre-built AI skills, agents, MCP serve
Just another desktop client for OpenCode 2. Manage projects, sessions, parallel agents, requests, and changes
iOS development ClaudeCode plugin for mindful token and context usage. Contains modular MCPs that group variou
Open source AI coding platform with Web IDE, multi-agent system, 37+ tools, MCP protocol. MIT licensed.
Explore other popular agent tool tools:
craft is A Claude Code plugin that runs your work through a creative → implement → review loop, builds the expert agents you consult, and locks in the taste you keep showing. Stop vibe coding, start crafting.. It is categorized as a Agent Tool with 52 GitHub stars.
craft is primarily written in Shell. It covers topics such as agentic-ai, agentic-workflow, ai-coding-assistant.
You can find installation instructions and usage details in the craft GitHub repository at github.com/drobins25/craft. The project has 52 stars and 5 forks, indicating an active community.
craft is released under the MIT license, making it free to use and modify according to the license terms.
The top alternatives to craft on Agent Skills Hub include clauder, agentic-ai-engineering, claudepro-directory. 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: