data-wise-craft

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Security

Grade A, and why

data-wise-craft scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.

The scan reads marketplace.json. This mod also ships 2 executable files (hooks/orchestrate-hooks.sh, hooks/pretooluse.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

.claude-plugin/marketplace.json · 41 lines

What it actually says

{
  "name": "data-wise-craft",
  "owner": {
    "name": "Data-Wise",
    "email": "[email protected]"
  },
  "metadata": {
    "description": "Full-stack developer toolkit for Claude Code with 48 commands, 2 agents, and 41 skills",
    "version": "4.6.0"
  },
  "plugins": [
    {
      "name": "craft",
      "source": {
        "source": "github",
        "repo": "Data-Wise/craft"
      },
      "description": "Full-stack developer toolkit for Claude Code with 48 commands, 2 agents, and 41 skills",
      "version": "4.6.0",
      "author": {
        "name": "Data-Wise",
        "email": "[email protected]"
      },
      "homepage": "https://data-wise.github.io/craft/",
      "repository": "https://github.com/Data-Wise/craft",
      "license": "MIT",
      "category": "development",
      "keywords": [
        "workflow",
        "automation",
        "git",
        "testing",
        "documentation",
        "ci-cd",
        "release",
        "architecture"
      ]
    }
  ]
}

Files

What ships with it

12 files beside marketplace.json in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

Related

Other plugins, from other repositories