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.
/plugin marketplace add VoidTechnology/voidtech-claude-pluginsnpx agentmods add plugins/voidtechnology/voidtech-claude-plugins/marketplacegit clone --depth 1 https://github.com/VoidTechnology/voidtech-claude-pluginsGrade A, and why
voidtech 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.
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.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
{
"name": "voidtech",
"description": "VoidTech 内部 Claude Code 插件市场：Core、Product、Design、Engineering、工程内循环与按需 MCP",
"owner": { "name": "VoidTech" },
"plugins": [
{
"name": "voidtech-core",
"source": "./plugins/voidtech-core",
"description": "公共能力：中文约定、跨领域工作流与共享 Archify Runtime"
},
{
"name": "voidtech-product",
"source": "./plugins/voidtech-product",
"description": "产品工作流：模块化 PRD、需求同步与产品验收",
"defaultEnabled": true
},
{
"name": "voidtech-design",
"source": "./plugins/voidtech-design",
"description": "设计工作流：标准 DESIGN.md、设计 brief、一次性 UI 原型与独立设计审查",
"defaultEnabled": true
},
{
"name": "voidtech-engineering",
"source": "./plugins/voidtech-engineering",
"description": "工程工作流：架构、实现、调试、测试、Issue 与发布",
"defaultEnabled": true
},
{
"name": "voidtech-loop",
"source": "./plugins/voidtech-loop",
"description": "默认启用的 Loop Engineering 工程内循环：不可变 Goal Spec、确定性控制器与指定 commit 验收",
"defaultEnabled": true
},
{
"name": "voidtech-mcp-common",
"source": "./plugins/voidtech-mcp-common",
"description": "可选通用 MCP：Context7 与 Chrome DevTools",
"defaultEnabled": false
},
{
"name": "voidtech-mcp-apple",
"source": "./plugins/voidtech-mcp-apple",
"description": "可选 Apple MCP：Apple Docs 与 XcodeBuildMCP",
"defaultEnabled": false
}
]
}
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.
- yesterday First seen · 49 lines scan A bb752a72d6a7
voidtech is a plugin published in the GitHub repository VoidTechnology/voidtech-claude-plugins (2 stars, last pushed 28d ago), licensed Apache-2.0. Its token cost is not measured: this kind of file is read by the harness, not the model. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other plugins, from other repositories
nextjs
Official Next.js skills: adopt and optimize Cache Components, adopt Partial Prefetching, and verify runtime behavior against a running dev server.
nextjs
Official Claude Code plugin marketplace for Next.js, serving the skills that ship in the vercel/next.js repository.
claude-plugins-official
Directory of popular Claude Code extensions including development tools, productivity plugins, and MCP integrations.
knowledge-work-plugins
Plugin marketplace listing 97 plugins: noibu, productivity, enterprise-search, cowork-plugin-management, sales.
ecc
Plugin marketplace listing 1 plugin: ecc.
ecc
Harness-native ECC plugin for engineering teams - 68 agents, 286 skills, 94 legacy command shims, reusable hooks, rules, MCP conventions, and operator workflows for Claude Code plus adjacent agent harnesses.