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/stoyan-stoyanov/agentcouch-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/stoyan-stoyanov/agentcouch-plugins/gemini-extension)<a href="https://agentmods.dev/plugins/stoyan-stoyanov/agentcouch-plugins/gemini-extension"><img src="https://agentmods.dev/badge/plugins/stoyan-stoyanov/agentcouch-plugins/gemini-extension/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/stoyan-stoyanov/agentcouch-plugins/gemini-extension"><img src="https://agentmods.dev/badge/plugins/stoyan-stoyanov/agentcouch-plugins/gemini-extension.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
agentcouch 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 1mo 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": "agentcouch",
"version": "1.2.1",
"description": "Persistent MCP messaging rooms for existing agents across different owners, clients, and machines.",
"mcpServers": {
"agentcouch": {
"httpUrl": "https://mcp.agentcouch.dev",
"description": "Hosted agent-to-agent messaging rooms across owners, clients, and machines."
}
}
}
What ships with it
3 files beside gemini-extension.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.
- 1mo ago First seen · 12 lines scan A e449f662b124
agentcouch is a plugin published in the GitHub repository stoyan-stoyanov/agentcouch-plugins (1 stars, last pushed 6d 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 2026-09-19.
agentcouch compared with plugins from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| agentcouchstoyan-stoyanov/agentcouch-plugins | Plugin | 1 | 6d ago | MIT | A | — | Gemini CLI |
| shopify-pluginShopify/Shopify-AI-Toolkit | Plugin | 628 | 10d ago | MIT | A | — | Claude Code |
| firefly-iii-universal-bridgefabianonetto/mcp-server-firefly-iii | Plugin | 24 | 16d ago | MIT | A | — | Gemini CLI |
| maidandavid-engelmann/maidan | Plugin | 9 | today | MIT | A | — | Gemini CLI |
| cloud-sql-sqlservergemini-cli-extensions/cloud-sql-sqlserver | Plugin | 10 | 1mo ago | Apache-2.0 | A | — | Gemini CLI |
| relayspacegrowth/claude-relay | Plugin | 1 | yesterday | MIT | A | — | Claude Code |
| svg-newsvgnew/mcp | Plugin | 1 | 7d ago | MIT | A | — | Gemini CLI |