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/Neboy72/nexus-memoryWrote 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/neboy72/nexus-memory/claude-code)<a href="https://agentmods.dev/plugins/neboy72/nexus-memory/claude-code"><img src="https://agentmods.dev/badge/plugins/neboy72/nexus-memory/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/neboy72/nexus-memory/claude-code"><img src="https://agentmods.dev/badge/plugins/neboy72/nexus-memory/claude-code.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
nexus-memory 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 16d 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": "nexus-memory",
"version": "1.2.7",
"description": "Self-hosted memory for Claude Code via Qdrant. Auto-Recall injects relevant memories before each prompt. Auto-Capture stores facts after each turn. Hybrid retrieval, reranking, memory dynamics, guardrails. Self-report: the plugin publishes its health and warns the agent when memory is broken. One store shared with OpenClaw and Hermes (MCP). Attribution note: the MCP server is pinned to NEXUS_AGENT_ID=\"claude-code\" here (this env entry overrides the shell value for the MCP process), while the hook scripts inherit the shell value — exporting NEXUS_AGENT_ID shell-wide therefore only changes the hooks, not the MCP server.",
"author": {
"name": "Neboy72",
"url": "https://github.com/Neboy72/nexus-memory"
},
"hooks": "./hooks/nexus-hooks.json",
"mcpServers": {
"nexus": {
"command": "python3",
"args": [
"${CLAUDE_PLUGIN_ROOT}/scripts/mcp_bootstrap.py"
],
"env": {
"NEXUS_AGENT_ID": "claude-code"
}
}
}
}
What it installs
The manifest is a name and a version. 1 skill travel with it, and installing the plugin installs all of them — 175 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.
- 16d ago Changed 87e4dccb4187
- 25d ago Changed · +1 lines f5c25d31a62a
- 1mo ago Changed 8e0f1e5e4b5d
- 1mo ago Changed 30498a7dd2fc
- 1mo ago Changed · +11 lines fead114d267b
- 1mo ago First seen · 10 lines scan A a3eb3b099871
nexus-memory is a plugin published in the GitHub repository Neboy72/nexus-memory (3 stars, last pushed yesterday), 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
engram
The context spine that 10x's your Claude Code sessions. Local-first SQLite knowledge graph + MCP server that intercepts file reads and replaces them with structural summaries. Measured 89% token reduction on a real codebase. Apache 2.0, no cloud, no telemetry.
yaggo-brain
yaggo-brain panel integration for Claude Code.
agent-recall
Persistent memory for AI coding agents. SQLite knowledge graph with scoped entities, MCP tools, and LLM-summarized briefings.
ownmem
Git-native project memory for AI coding agents, with deterministic local recall, evidence gates, and layered delivery that quotes, points, or abstains.
engraphis-memory
Give agents durable, scoped, explainable memory across sessions and repos via the Engraphis MCP tools. Use when you learn something worth keeping, need prior context before acting, or ask why/how a fact changed. Covers remember/recall, why/timeline, forget/pin/correct, sessions, and code search.
project-brain
Folder structure + collaboration protocol so AI sessions can resume project context after compaction or window switch. One brain/ folder, 5 core files (PROJECT/MAP/STATUS/DECISIONS/HANDOFF), and a topic taxonomy.