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 ArshiaEcho/stratos-memory-stacknpx agentmods add plugins/arshiaecho/stratos-memory-stack/plugingit clone --depth 1 https://github.com/ArshiaEcho/stratos-memory-stackGrade 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 yesterday.
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 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.
- yesterday 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 17d 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
scaccogatto
Claude Code plugins by scaccogatto.
okf
Open Knowledge Format for Claude: the OKF skill, /okf:gem setup and doctor, and a post-edit hook that runs the okf CLI's validate and lint checks on the bundle you touched.
prd-os
PRD operating system: capture rough ideas, draft reviewable PRDs, run standard and adversarial review (Codex or a Claude senior-staff-engineer subagent, recorded truthfully), triage findings, decompose approved PRDs into atomic issue specs, and execute those issues with scope enforcement, stop-gate receipts, and…
scraps-migration
LLM migration workflows for moving Scraps wikis from v0 to v1. Runs version-pinned audits, converts tag and config syntax, and verifies the result with v1 lint/build.
wikimate-marketplace
Plugin marketplace listing 1 plugin: wikimate.
memex
Zettelkasten-based agent memory system with bidirectional links.