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 verygoodplugins/mcp-automemnpx agentmods add plugins/verygoodplugins/mcp-automem/automemgit clone --depth 1 https://github.com/verygoodplugins/mcp-automemGrade A, and why
automem 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 2d 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": "automem",
"version": "0.16.0",
"description": "Persistent memory for Claude Code via AutoMem: silent session-start recall, in-turn LLM-judged storage guidance, and the AutoMem MCP memory tools.",
"author": {
"name": "Very Good Plugins",
"email": "[email protected]",
"url": "https://github.com/verygoodplugins"
},
"homepage": "https://github.com/verygoodplugins/mcp-automem",
"repository": "https://github.com/verygoodplugins/mcp-automem",
"license": "MIT",
"keywords": [
"memory",
"context",
"automem",
"mcp",
"persistence",
"knowledge-graph"
],
"mcpServers": "./.mcp.json",
"userConfig": {
"api_url": {
"type": "string",
"title": "AutoMem API URL",
"description": "Base URL of your AutoMem service (e.g. http://127.0.0.1:8001 or your Railway URL). Leave empty to use AUTOMEM_API_URL/AUTOMEM_ENDPOINT from your environment; falls back to http://127.0.0.1:8001."
},
"api_key": {
"type": "string",
"title": "AutoMem API key",
"description": "API key if your AutoMem deployment requires auth. Leave empty for unauthenticated local instances or to use AUTOMEM_API_KEY from your environment.",
"sensitive": true
}
}
}
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.
- 2d ago First seen · 36 lines scan A 465a13207eef
automem is a plugin published in the GitHub repository verygoodplugins/mcp-automem (64 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
hal-9000
Plugin marketplace listing 3 plugins: hal-voice, hal-session-auto-rename, hal-skills.
hal-voice
Play HAL 9000 voice clips on Claude Code hook events.
mcp-server
Model Context Protocol (MCP) server for AI-assisted development of CAP applications.
vovk
Claude Code plugin for Vovk.ts — topic-based skills covering segments, procedures, validation, SSR, and project setup.
wikimate-marketplace
Plugin marketplace listing 1 plugin: wikimate.
ensemble-ai
AI SDK skills for OpenAI, and other AI providers for Claude Code.