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.
git clone --depth 1 https://github.com/n24q02m/claude-pluginsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/plugins/n24q02m/claude-plugins/agent-chat-plugin)<a href="https://agentmods.dev/plugins/n24q02m/claude-plugins/agent-chat-plugin"><img src="https://agentmods.dev/badge/plugins/n24q02m/claude-plugins/agent-chat-plugin/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/plugins/n24q02m/claude-plugins/agent-chat-plugin"><img src="https://agentmods.dev/badge/plugins/n24q02m/claude-plugins/agent-chat-plugin.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
agent-chat-plugin 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 26d 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": "agent-chat-plugin",
"description": "Peer AI agents coordinate through markdown messages in shared channel folders — group chat / blackboard, no orchestrator, autonomous zero-token waiting, cross-platform.",
"version": "0.7.5",
"author": {
"name": "n24q02m",
"url": "https://github.com/n24q02m"
},
"homepage": "https://github.com/n24q02m/agent-chat-plugin",
"userConfig": {
"AGENT_CHAT_NAME": {
"type": "string",
"title": "Agent identity",
"description": "This session's name in the chat (e.g. claude-1). Required for the inbox hook.",
"required": false
},
"AGENT_CHAT_ROOT": {
"type": "string",
"title": "Chat root directory",
"description": "Where channels live. Default: ~/agent-chat",
"required": false
},
"AGENT_CHAT_CHANNELS": {
"type": "string",
"title": "Channels to watch",
"description": "Comma-separated channels checked at session start. Empty = all.",
"required": false
}
},
"mcpServers": {}
}
What it installs
The manifest is a name and a version. 1 skill, 1 command, 3 hooks travel with it, and installing the plugin installs all of them — 39 tokens a session between them. Each is measured on its own page, and each can be installed alone.
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.
- 26d ago Changed 79293a526280
- 27d ago Changed f17dda7635b0
- 1mo ago Changed cf58352df0eb
- 1mo ago Changed 69b1b2bd8698
- 1mo ago Changed ed662002d441
- 1mo ago Changed 04649cd34054
- 1mo ago Changed 0e66d6935301
- 1mo ago First seen · 32 lines scan A 01561512684f
agent-chat-plugin is a plugin published in the GitHub repository n24q02m/claude-plugins (4 stars, last pushed today), 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
moai-lawyer
A collection of legal-work tools for contracts, confidentiality agreements, regulatory checks, legal research, patents, and food or drug safety rules. It connects to Korea's national law information service to verify legal citations.
moai-media
A collection of media-generation skills for creating images, videos, 3D content, voice, dubbing, and sound effects from natural-language requests.
moai-accountant
A collection of finance and tax-focused AI skills for analysing financial statements, closing accounts, explaining differences, preparing investor-relations material, and handling personal budgeting and tax topics. It also connects to OpenDART, a Korean electronic disclosure service.
moai-analyst
A data-analysis assistant that handles spreadsheet profiling, charts, and selected South Korean public-data lookups, including property, auctions, stocks, statistics, and building records.
moai-pm
A project-starting hub for Claude Cowork that interviews you about the work, reviews installed add-ons, and creates project-specific instructions, agents, and workflows. It is intended to help both developers and non-developers set up a project.
moai-marketer
A marketing-focused AI coworker containing tools for campaign planning, performance analysis, keyword research, growth experiments, retention, blogs, newsletters, and social content.