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 2389-research/claude-pluginsnpx agentmods add plugins/2389-research/claude-plugins/marketplacegit clone --depth 1 https://github.com/2389-research/claude-pluginsGrade A, and why
2389-research marketplace 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 3d 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.
How it starts
The opening of the file, as written. The whole thing — 650 lines — stays where its author put it; the contents beside it link to each section on GitHub.
{
"name": "2389-research",
"owner": {
"name": "2389 Research Inc",
"email": "[email protected]",
"url": "https://2389.ai"
},
"metadata": {
"description": "Plugins and MCP servers we use at 2389",
"version": "2.0.0"
},
"plugins": [
{
"name": "css-development",
"category": "development",
"source": {
"source": "url",
"url": "https://github.com/2389-research/css-development.git"
},
"description": "CSS development workflows with Tailwind composition, semantic naming, and dark mode by default",
"version": "1.0.0",
"keywords": [
"css",
"tailwind",
"styling",
"components",
"dark-mode"
],
"strict": false
},
{
"name": "firebase-development",
"category": "infrastructure",
"source": {
"source": "url",
"url": "https://github.com/2389-research/firebase-development.git"
},
"description": "Firebase project workflows including setup, features, debugging, and validation",
"version": "1.0.0",
"keywords": [
"firebase",
"firestore",
"cloud-functions",
"hosting",
"emulator"
],
"strict": false
},
{
"name": "landing-page-design",
"category": "development",
"source": {
"source": "url",
"url": "https://github.com/2389-research/landing-page-design.git"
},
"description": "Create high-converting, visually distinctive landing pages with Vibe Discovery process and anti-AI-slop principles",
"version": "1.0.0",
"keywords": [
"landing-page",
"marketing",
"design",
"conversion",
"hero",
"saas",
"homepage"
],
"strict": false
},
{
"name": "xtool",
"category": "development",
"source": {
"source": "url",
"url": "https://github.com/2389-research/xtool.git"
},
"descrThe plugins it lists here
This marketplace lists 1 plugin kept in the same repository. Each has its own page, its own measurements and its own install command.
What ships with it
1 file 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.
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.
- 3d ago First seen · 650 lines scan A 51b7ccf8fa43
2389-research marketplace is a plugin published in the GitHub repository 2389-research/claude-plugins (93 stars, last pushed 7d 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
debt-ops
Every shortcut your coding agent takes, saved to your repo as it happens. Fix them when you're ready.
fabler-x402-tools
Paid agent tools for secrets, agent configs, diffs, deploy evidence, URL security, web scraping, OG rendering, and funding-rate spreads over x402 on Base, plus a free catalog.
sipcode
Token-economy observatory for Claude Code: forensic per-session audit, A/B savings verifier, reproducible benchmark, and cost prediction — directly in Claude chat. Auto-installs via npx on first use; no separate npm install required.
mas-desktop-ops
MAS Desktop Ops - Major AI Skills specialized plugin.
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.