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.
npx agentmods add instructions/morpheusais/morpheus-lumerin-node/agents-mdgit clone --depth 1 https://github.com/MorpheusAIs/Morpheus-Lumerin-NodeWhat 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 | $0.02840 | $0.02840 |
| Opus 5 | $0.01420 | $0.01420 |
| Sonnet 5 | $0.00568 | $0.00568 |
| Haiku 4.5 | $0.00284 | $0.00284 |
Grade A, and why
Morpheus-Lumerin-Node AGENTS.md scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
4. **Page URLs are agent-readable for non-browsers** — CloudFront serves clean Markdown when `Accept` does not include `text/html` (bare `curl`, most agent HTTP clients). Browsers still get the Mintlify UI. You can also How it starts
The opening of the file, as written. The whole thing — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — guidance for AI agents and coding assistants
If you are an LLM (Claude, GPT, Gemini, Copilot, Cursor, etc.) reading this repository to answer questions about Morpheus, read this file first. The Morpheus Lumerin Node has nuance that generic web knowledge gets wrong; this file exists to keep you out of the most common hallucination traps.
How to load documentation (follow this order)
- This file — hard rules, quick lookup, and repo pointers. No network required.
llms-full.txt— fetch this for the complete documentation corpus as plain markdown (~350 KB). Every page title in the export matches a# Headingsection. This is the primary ingestion path.llms.txt— lightweight page index (title, description, URL per page). Links point at per-page.mdfiles.- Page URLs are agent-readable for non-browsers — CloudFront serves clean Markdown when
Acceptdoes not includetext/html(barecurl, most agent HTTP clients). Browsers still get the Mintlify UI. You can also append.md(e.g./ai/myths.md) or use MCP athttps://nodedocs.mor.org/mcp. - Do not rely on rendering the JS HTML UI — prefer
llms-full.txt,.mdURLs, or a non-browser fetch of the page URL. Citation URLs below remain the human-facing paths.
Published site: nodedocs.mor.org. Source files live in /docs/ and are built with Mintlify.
Priority reading (find these sections in llms-full.txt)
Read the AI knowledge pages before answering user questions:
| Topic | Slug | Citation URL |
|---|---|---|
| Myths and corrections | ai/myths |
https://nodedocs.mor.org/ai/myths |
| Where is my MOR? | ai/where-is-my-mor |
https://nodedocs.mor.org/ai/where-is-my-mor |
| Session states (open, close, recover) | ai/session-states-open-close-recover |
https://nodedocs.mor.org/ai/session-states-open-close-recover |
| Why is my MOR locked? | ai/why-locked-in-contract |
https://nodedocs.mor.org/ai/why-locked-in-contract |
| Local vs blockchain models | ai/local-vs-blockchain-models |
https://nodedocs.mor.org/ai/local-vs-blockchain-models |
| LLM prompt cheatsheet | ai/llm-prompt-cheatsheet |
https://nodedocs.mor.org/ai/llm-prompt-cheatsheet |
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 · 131 lines · 2,840 tokens per session scan A 25dc9981168a
Morpheus-Lumerin-Node AGENTS.md is an instructions file published in the GitHub repository MorpheusAIs/Morpheus-Lumerin-Node (21 stars, last pushed 7d ago), licensed MIT. It adds 2,840 tokens to every session, about $0.0142 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
mcpware CLAUDE.md
Instructions for delexw/mcpware, covering claude.md, project overview, key architecture, core components and request flow.
mcp-all-in-one AGENTS.md
Instructions for vtxf/mcp-all-in-one: These instructions are for AI assistants working in this project.
mcp-all-in-one CLAUDE.md
Instructions for vtxf/mcp-all-in-one: These instructions are for AI assistants working in this project.
mockserver-monorepo AGENTS.md
AGENTS.md instructions for mock-server/mockserver-monorepo, covering mockserver — agent instructions, instruction priority, project overview, local development environment and project documentation.
plano CLAUDE.md
Instructions for katanemo/plano, covering claude.md, build & test commands, rust — wasm plugins (must target wasm32-wasip1), rust — brightstaff binary (native target) and rust — tests, format, lint.
GreenTunnel CLAUDE.md
Instructions for SadeghHayeri/GreenTunnel, covering greentunnel v3, commands, running the cli, ⚠️ npm run dev changes your real system proxy and layout.