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 ANcpLua/ancplua-claude-pluginsnpx agentmods add plugins/ancplua/ancplua-claude-plugins/broken-plugingit clone --depth 1 https://github.com/ANcpLua/ancplua-claude-pluginsGrade A, and why
Bad Name 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 2d ago.
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": "Bad Name",
"version": "not-a-version",
"description": "Broken Claude Code plugin fixture for cc-plugin-eval evaluator tests. Path is set to a missing directory and ${CLAUDE_PLUGIN_ROOT} appears in this metadata field intentionally so cc-plugin-eval emits CC110.",
"license": "MIT",
"skills": "missing-dir/",
"hooks": "./hooks/hooks.json",
"mcpServers": "./.mcp.json",
"lspServers": "./.lsp.json",
"monitors": "./monitors/monitors.json",
"agents": "./agents/",
"userConfig": {
"api-token": {
"type": "string",
"title": "Bad key",
"description": "Key has a hyphen so CC910 fires."
},
"api_token": {
"type": "string",
"title": "API token",
"description": "Secret-shaped name with sensitive missing so CC915 fires."
},
"limit": {
"title": "Limit",
"description": "Missing type so CC911 fires."
},
"color": {
"type": "rainbow",
"title": "Color",
"description": "Invalid type so CC912 fires."
},
"items": {
"type": "number",
"title": "Items",
"description": "multiple on a number type so CC913 fires.",
"multiple": true
}
},
"channels": [
{
"server": "ghost-server"
}
]
}
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.
- 2d ago First seen · 45 lines scan A c8a3d299f203
Bad Name is a plugin published in the GitHub repository ANcpLua/ancplua-claude-plugins (5 stars, last pushed 15d ago), licensed MIT. 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
humanizer
Rewrite AI-sounding text so it reads naturally without changing what it says.
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.