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/alexfrmn/murmurWrote 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/alexfrmn/murmur/claude-code)<a href="https://agentmods.dev/plugins/alexfrmn/murmur/claude-code"><img src="https://agentmods.dev/badge/plugins/alexfrmn/murmur/claude-code/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/alexfrmn/murmur/claude-code"><img src="https://agentmods.dev/badge/plugins/alexfrmn/murmur/claude-code.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
murmur 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
{
"$schema": "https://json.schemastore.org/claude-code-plugin-manifest.json",
"name": "murmur",
"displayName": "Murmur",
"version": "0.1.0",
"description": "Read and send Murmur messages through MCP, with explicit inbox and terminal status helpers.",
"author": {
"name": "Murmur contributors"
},
"repository": "https://github.com/alexfrmn/murmur",
"license": "MIT",
"keywords": ["murmur", "mcp", "messaging", "statusline"],
"defaultEnabled": false,
"userConfig": {
"node_command": {
"type": "file",
"title": "Node.js command",
"description": "Absolute path to the Node.js executable used to run Murmur.",
"required": true
},
"murmur_entrypoint": {
"type": "file",
"title": "Murmur CLI entrypoint",
"description": "Absolute path to packages/setup/bin/murmur.mjs in an installed or runtime-bundle copy of Murmur.",
"required": true
},
"data_dir": {
"type": "directory",
"title": "Murmur profile",
"description": "Absolute path to the Murmur profile used by this Claude Code instance.",
"required": true
}
}
}
What it installs
The manifest is a name and a version. 3 skills, 1 MCP server travel with it, and installing the plugin installs all of them — 45 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 First seen · 35 lines scan A 39743b9ea55f
murmur is a plugin published in the GitHub repository alexfrmn/murmur (19 stars, last pushed today), 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 2026-09-21.
Other plugins, from other repositories
agent-comm
Agent-to-agent messaging for AI coding agents — sessions, direct/broadcast/channel messages, shared state, real-time feed, and a file-coordination hook for parallel edits.
obsidian-mcp-server
Read, write, search, and surgically edit Obsidian vault notes, tags, and frontmatter via MCP. STDIO or Streamable HTTP.
ntfy-mcp-server
Send, manage, and replay ntfy push notifications via MCP. STDIO or Streamable HTTP.
todox
The log your next session resumes from: decisions, dead ends, handoffs and open tasks, shared across machines, agents and people over the todox MCP server. Reminds a session to read the log first and to write it up before finishing.
ebb-ai
Auto-dispatch "do it later" work. Invoke whenever the user signals deferral: "do this later", "by tomorrow", "tonight", "overnight", "by EOD", "sometime this week", "when you have a moment", "remind me to", "queue this up", "schedule this", "no rush". The plugin's /ebb-ai:defer command queues the task to dispatch at…
slack-mcp
Multi-workspace Slack MCP server with draft+confirm safety, vault auto-export, and triple-mode auth (xoxc/xoxp/xoxb).