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 OneWave-AI/open-agent-stacknpx agentmods add plugins/onewave-ai/open-agent-stack/marketplacegit clone --depth 1 https://github.com/OneWave-AI/open-agent-stackGrade A, and why
open-agent-stack 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": "open-agent-stack",
"owner": {
"name": "OneWave AI",
"url": "https://www.onewave-ai.com"
},
"metadata": {
"description": "Open-source plugins, managed agents, orchestrators, and design tokens for Claude Code and any AI tool.",
"version": "0.1.0"
},
"plugins": [
{ "name": "ai-news-hq", "source": "./plugins/ai-news-hq", "description": "An AI-news team and HQ that tracks the field with web search and ships daily briefings." },
{ "name": "release-radar", "source": "./plugins/release-radar", "description": "Track new AI model and tool releases, changelogs, and deprecations." },
{ "name": "competitor-watch", "source": "./plugins/competitor-watch", "description": "Monitor competitor sites, pricing, and content via web search." },
{ "name": "content-engine", "source": "./plugins/content-engine", "description": "Repurpose one piece of content across every channel." },
{ "name": "brand-kit", "source": "./plugins/brand-kit", "description": "Apply a OneWave design style — tokens, theme, and brand commands." },
{ "name": "sales-desk", "source": "./plugins/sales-desk", "description": "The rep's daily loop: pre-call briefs, pipeline hygiene, account snapshots, post-call follow-ups." },
{ "name": "vibe-stack", "source": "./plugins/vibe-stack", "description": "The full vibe-coding loop: scaffold an app or marketing site, animate it (GSAP, scroll, micro-interactions), make the fake data real, unstick it, de-AI it, ship it, demo it." },
{ "name": "market-desk", "source": "./plugins/market-desk", "description": "Personal equity-research desk: ticker briefs, portfolio risk reviews, earnings prep. Research, not advice." }
]
}
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 · 22 lines scan A 4734d92added
open-agent-stack is a plugin published in the GitHub repository OneWave-AI/open-agent-stack (2 stars, last pushed 21d 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
starknet-agentic-skills
Plugin marketplace listing 1 plugin: starknet-agentic-skills.
atera
Claude Code plugin for Atera RMM/PSA - tickets, agents, customers, alerts.
kotlin-lsp
Real-time Kotlin code intelligence for Claude — instant diagnostics, go-to-definition, find references, and type info via kotlin-language-server.
il-laws
Look up and search Illinois Compiled Statutes and Illinois Supreme Court Rules using a verified local corpus downloaded on first use.
unity-devtools
Drive a running Unity Mono development build from your coding agent (Claude Code, Codex CLI): ships the unity-devtools-mcp server (process discovery, live type reflection, C# expression evaluation, and ECS entity/component/buffer read-write over the Mono Soft Debugger protocol, no code injection), plus skills.
rad-chrome-extension
MV3 Chrome extension development standards (WXT, React, TypeScript) with two pure-stdlib Python validators that catch what LLM eyeballing misses. Skills cover architecture, MV3 security (CSP, remote code ban, content script isolation), permission minimization and CWS compliance, typed messaging, storage selection…