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/ncz-os/mnemos/agents-mdgit clone --depth 1 https://github.com/ncz-os/mnemosWrote 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/ncz-os/mnemos/agents-md)<a href="https://agentmods.dev/instructions/ncz-os/mnemos/agents-md"><img src="https://agentmods.dev/badge/instructions/ncz-os/mnemos/agents-md.svg" alt="Measured on agentmods" 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 | $0.02170 | $0.02170 |
| Opus 5 | $0.01085 | $0.01085 |
| Sonnet 5 | $0.00434 | $0.00434 |
| Haiku 4.5 | $0.00217 | $0.00217 |
Grade A, and why
mnemos 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 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -fsS http://localhost:5002/health # everything/core/enterprise How it starts
The opening of the file, as written. The whole thing — 144 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — machine-readable install guide for MNEMOS
This file lets an automated agent install/deploy MNEMOS for an operator given a requested set of modules, deterministically. Human guide: docs/INSTALL.md.
The pip package is mnemos-core. mnemos is an image name, not a pip
package — never run pip install mnemos or pip install mnemos-os.
Module registry
# id -> how to obtain it. Subsystems share the mnemos.* namespace and are
# runtime-gated: installing the dist mounts the routes; absence => HTTP 503.
modules:
core: { dist: mnemos-core, extra: null, kind: kernel, arch: [amd64, arm64] }
graeae: { dist: mnemos-graeae, extra: graeae, kind: router, arch: [amd64, arm64] }
pantheon: { dist: mnemos-pantheon, extra: pantheon, kind: router, arch: [amd64, arm64] }
knemon: { dist: mnemos-knemon, extra: knemon, kind: router, arch: [amd64, arm64] }
charon: { dist: mnemos-charon, extra: charon, kind: router, arch: [amd64, arm64] }
stiphos: { dist: mnemos-stiphos, extra: null, kind: service, arch: [amd64, arm64], port: 8080, note: "separate service, not in the everything image" }
backends: # selected at RUNTIME via MNEMOS_DATABASE_DSN, not by image
sqlite: { driver: bundled, dsn: "sqlite:////data/mnemos.db", arch: [amd64, arm64], default: true }
postgres: { driver: asyncpg, dsn: "postgres://USER:PASS@HOST:5432/DB", arch: [amd64, arm64] }
oracle: { driver: oracledb, extra: oracle, dsn: "oracle://USER:PASS@HOST:1521/SERVICE", arch: [amd64, arm64], thin: true }
db2: { driver: ibm_db, extra: db2, dsn: "db2://USER:PASS@HOST:50000/DB", arch: [amd64] }
mysql: { driver: aiomysql, extra: mysql, dsn: "mysql://USER:PASS@HOST:3306/DB", arch: [amd64, arm64] }
mariadb: { driver: aiomysql, extra: mysql, dsn: "mariadb://USER:PASS@HOST:3306/DB", arch: [amd64, arm64] }
accelerators: # OPTIONAL embedder accel; default is portable CPU llama-cpp
openvino: { extra: openvino, arch: [amd64] } # Intel x86-only
cuda: { extra: cuda, arch: [amd64, arm64] } # needs PyTorch CUDA index
amd: { extra: amd, arch: [amd64] } # ROCm, linux-only
images:
mnemos-core: { ref: "ghcr.io/ncz-os/mnemos-core", contains: [core], arch: [amd64, arm64], port: 5002 }
mnemos: { ref: "ghcr.io/ncz-os/mnemos", contains: [core, graeae, pantheon, knemon, charon], arch: [amd64, arm64], port: 5002, canonical_everything: true }
mnemos-enterprise: { ref: "ghcr.io/ncz-os/mnemos-enterprise", contains: [core, graeae, pantheon, knemon, charon, oracle, db2, mysql], arch: [amd64], port: 5002, note: "the mysql driver (aiomysql) also serves the mariadb backend" }
mnemos-stiphos: { ref: "ghcr.io/ncz-os/mnemos-stiphos", contains: [stiphos], arch: [amd64, arm64], port: 8080 }
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 First seen · 144 lines · 2,170 tokens per session scan A 2b77e9ff66b9
mnemos AGENTS.md is an instructions file published in the GitHub repository ncz-os/mnemos (31 stars, last pushed 6d ago), licensed Apache-2.0. It adds 2,170 tokens to every session, about $0.0109 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
saferskills CLAUDE.md
Claude Code instructions for OpenLatch/saferskills, covering claude.md — saferskills, quick start, backend, frontend and codegen.
Kokoro-FastAPI AGENTS.md
AGENTS.md instructions for remsky/Kokoro-FastAPI, covering agents.md, layout, commands, conventions and gotchas.
geolens CLAUDE.md
Claude Code instructions for geolens-io/geolens: This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
substack-gateway-oss CLAUDE.md
Claude Code instructions for jakub-k-slys/substack-gateway-oss, covering claude.md, commands, install dependencies (dev included, all workspace members), run the server (dev mode with reload) and lint.
Huntable-CTI-Studio AGENTS.md
AGENTS.md instructions for dfirtnt/Huntable-CTI-Studio, covering agents.md, orientation, local context, prompt-injection alerting and change-type quick reference.
dev-challenge CLAUDE.md
Claude Code instructions for micheltlutz/dev-challenge, covering claude.md, the one rule to internalise, slash commands, subagents and skills.