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/ArshiaEcho/stratos-memory-stackWrote 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/arshiaecho/stratos-memory-stack/plugin)<a href="https://agentmods.dev/plugins/arshiaecho/stratos-memory-stack/plugin"><img src="https://agentmods.dev/badge/plugins/arshiaecho/stratos-memory-stack/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/arshiaecho/stratos-memory-stack/plugin"><img src="https://agentmods.dev/badge/plugins/arshiaecho/stratos-memory-stack/plugin.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
stratos-memory-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 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": "stratos-memory-stack",
"version": "2.0.0",
"description": "Memory that learns and keeps itself current. A seven-layer persistent memory stack for Claude Code (claude-mem, basic-memory, Obsidian, Pinecone, CLAUDE.md/MEMORY.md, STATE.md, and an optional unified retrieval engine: one pgvector table over every corpus, hybrid search fused with RRF, served as MCP primitives), plus a nightly learning loop (capture, consolidation, scouts, conductor). Auto-audits which layers you have, then guides setup.",
"author": {
"name": "Arshia Navabi",
"email": "[email protected]",
"url": "https://www.stratosagency.ai"
},
"homepage": "https://github.com/ArshiaEcho/stratos-memory-stack",
"repository": "https://github.com/ArshiaEcho/stratos-memory-stack",
"license": "MIT",
"keywords": [
"agents",
"basic-memory",
"claude-mem",
"hybrid-search",
"knowledge-base",
"knowledge-management",
"learning-loop",
"memory",
"obsidian",
"pgvector",
"pinecone",
"rag",
"rrf",
"self-evolving",
"self-improving",
"stack",
"stratos",
"unified-retrieval"
]
}
What it installs
The manifest is a name and a version. 1 skill travel with it, and installing the plugin installs all of them — 150 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.
- 1mo ago First seen · 34 lines scan A 894089f737e1
stratos-memory-stack is a plugin published in the GitHub repository ArshiaEcho/stratos-memory-stack (6 stars, last pushed 2mo 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
llm-wiki
Build a shared Markdown knowledge base with local hybrid search and an optional evidence-linked workflow to capture task lessons, evaluate skill improvements, and apply or roll back tested changes.
membrain
Graph-based agent memory — search, trace, and manage what your agent knows.
capture
Capture session information into a staging file for later reflection and knowledge graph processing.
cortexes
Personal knowledge vault plugin — session recording, memory distillation, indexed retrieval.
arscontexta
Conversational derivation engine — generate agent-native memory architecture from natural conversation. 15 kernel primitives, 26 commands, 17 feature blocks, 3 presets.
memex
Collaborative memory for human-AI work — persistent, searchable, interconnected.