Borrowing it
Nothing to install: this file belongs to Neboy72/nexus-memory. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/Neboy72/nexus-memory/main/AGENTS.mdgit 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/instructions/neboy72/nexus-memory/agents-md)<a href="https://agentmods.dev/instructions/neboy72/nexus-memory/agents-md"><img src="https://agentmods.dev/badge/instructions/neboy72/nexus-memory/agents-md/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/instructions/neboy72/nexus-memory/agents-md"><img src="https://agentmods.dev/badge/instructions/neboy72/nexus-memory/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.08236 | $0.08236 |
| Opus 5.5 | $0.03294 | $0.03294 |
| Sonnet 5.5 | $0.01647 | $0.01647 |
| Haiku 4.5 | $0.00824 | $0.00824 |
Grade C, and why
nexus-memory AGENTS.md scanned grade C with 2 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 4d 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
Before any destructive operation (`rm -rf`, `drop`, `kill -9`, `recreate_collection`), the guardrail checks Qdrant for stored protection rules (category=`rule` with protection keywords like "never delete", "protected", " Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl http://127.0.0.1:9122/healthz # {"status":"ok","qdrant":true,"version":...} How it starts
The opening of the file, as written. The whole thing — 713 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Nexus Memory — AGENTS.md (AI Installation Guide)
Tell your AI agent: "Read https://raw.githubusercontent.com/Neboy72/nexus-memory/main/AGENTS.md and follow the installation instructions."
Overview
Nexus Memory is a universal memory layer for AI agents. One memory for all your agents — Hermes, OpenClaw, Claude Code, Cursor, or any MCP-compatible agent.
Hermes Native Plugin (Recommended for Hermes Agent)
If you use Hermes Agent, install Nexus Memory as a native MemoryProvider plugin. This gives you direct Qdrant access with zero MCP overhead — Hermes reads/writes memories as part of its core loop.
One-Command Install
cd ~/nexus-memory
./scripts/install_hermes_plugin.sh
This script:
- Symlinks the
nexusplugin into~/.hermes/hermes-agent/plugins/memory/ - Sets
memory.providertonexusin Hermes config - Verifies the installation
Manual Setup
Or, run these commands yourself:
# Link the plugin
ln -s ~/nexus-memory/plugins/memory/nexus ~/.hermes/hermes-agent/plugins/memory/nexus
# Activate it
hermes config set memory.provider nexus
Verify
hermes config get memory.provider
# → nexus
Restart Hermes Gateway. Nexus tools appear as nexus_recall, nexus_remember, nexus_forget.
Self-Report (memory health)
The plugin writes a self-check file on every process start
(<data-dir>/agent-selfcheck-<agent-id>.json; legacy agent-selfcheck.json is
still read). The Nexus server reads it and reports when an agent's memory is
loaded but not working — you do not need to build a watchdog.
- What it detects. (1) A fresh
ok: falseself-check — e.g. a dependency missing in that agent's interpreter. (2) Suspicious silence: apluginagent that has used its memory before but has not called back for 4–14 days. MCP-only agents and long-dormant agents are deliberately ignored. - Channels. Set
NEXUS_ALERT_WEBHOOK_URLfor a JSON POST (Discord-compatiblecontentfield;NEXUS_WEBHOOK_URLis the fallback), and/orNEXUS_ALERT_MACOS=1for a macOS desktop notification. With no channel configured nothing is sent. - Knobs.
NEXUS_SELFREPORT=0disables the daemon;NEXUS_SELFREPORT_INTERVAL_SEC(default 21600 = 6 h) andNEXUS_SELFREPORT_START_DELAY(default 90 s) tune it.NEXUS_DATA_DIRmoves the whole data directory (self-checks + registry) — set it consistently for the server AND every agent, or the watcher reads a different directory than the plugins write. - Probe cost. The plugin's self-check probes Qdrant at most once per
NEXUS_PROBE_TTL_SEC(default 30 s) instead of on every prompt build, withNEXUS_QDRANT_TIMEOUT(default 5 s) so a hung server cannot delay a turn. - Repair a broken plugin. Run the one-line command the plugin itself reports:
uv pip install -e "<nexus-memory checkout>" --python "<agent interpreter>"(or"<agent interpreter>" -m pip install --upgrade nexus-memoryfor a packaged install). Stored memories are safe and not lost; running the fix restores memory.
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.
- 4d ago Changed · +28 lines · +164 tokens per session 5f4f98f76455
- 19d ago Changed · +20 lines · +480 tokens per session 7a0538846400
- 20d ago Changed · -11 tokens per session f9ad01d60660
- 26d ago Changed · +47 tokens per session a3e993f95632
- 27d ago Changed · +9 lines · +180 tokens per session 2400b19f505d
- 29d ago Changed · +28 lines · +476 tokens per session 821623adb142
- 1mo ago Changed · +12 lines · +113 tokens per session 81176c93050c
- 1mo ago Changed · +32 lines · +414 tokens per session f9c21f3eeff9
- 1mo ago Changed · +18 lines · +336 tokens per session beeaf9a779f9
- 1mo ago First seen · 566 lines · 6,037 tokens per session scan C baaa9794a07b
nexus-memory AGENTS.md is an instructions file published in the GitHub repository Neboy72/nexus-memory (3 stars, last pushed yesterday), licensed MIT. It adds 8,236 tokens to every session, about $0.0329 per session on Opus 5.5. A static security scan graded it C with 2 findings (recursive force delete, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
data-scientist copilot-instructions.md
Repository instructions for a data-science workflow in GitHub Copilot, covering datasets, statistics, and analysis files.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).