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 alaliqing/claude-papernpx agentmods add plugins/alaliqing/claude-paper/plugingit clone --depth 1 https://github.com/alaliqing/claude-paperGrade A, and why
claude-paper 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": "claude-paper",
"version": "1.2.1",
"description": "A plugin for studying research papers with automated material generation and code demos",
"author": {
"name": "alaliqing"
},
"homepage": "https://github.com/alaliqing/claude-paper"
}
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 · 10 lines scan A ca46f6bb7a36
claude-paper is a plugin published in the GitHub repository alaliqing/claude-paper (332 stars, last pushed 18d 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 2026-08-30.
Other plugins, from other repositories
specialist-agent
Your AI development team. 36 agents and 32 skills for building, reviewing, debugging, and shipping production code. Supports Vue, React, Next.js, SvelteKit, Angular, Astro, and Nuxt.
antidote
Stop AI agents from patching symptoms. Forces structural root-cause fixes over symptom patching in any language or stack.
axint
Compile TypeScript intent definitions into native Apple App Intents and MCP tool servers. Define once, ship to Siri, Shortcuts, and Spotlight.
claude-dev-kit
PRD-driven AI dev team control plane for Claude Code.
scaffold
AI-powered software project scaffolding — CLI pipeline with auto-activated skills for Claude Code.
spec-first
Spec-first development: define a spec, implement it, and generate docs.