agentmods.dev

nora CLAUDE.md

nora CLAUDE.md is an instructions file for Claude Code from solomon2773/nora. It costs 2,859 tokens per session, scanned A, original, Apache-2.0.

A repository guide for Nora, a self-hosted platform that manages and monitors AI agent runtimes using Docker and Kubernetes. It documents the main development commands, including starting services with Docker Compose and working with the database.

In plain words
What is it for?
Use it when developing, testing, rebuilding, inspecting logs, or accessing services in the Nora codebase.
Why use it?
It gives coding agents the project context and commands needed to work consistently in the repository.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md; mentions Claude Code; built for openclaw.

not rated 50 yesterday A scan 2,859 tokens original Apache-2.0
View the source file solomon2773/nora nora.solomontsao.com
Install

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.

agentmods
npx agentmods add instructions/solomon2773/nora/claude-md
Clone the repo
git clone --depth 1 https://github.com/solomon2773/nora

Made for: Claude Code.

Wrote 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.

agentmods badge for nora CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/solomon2773/nora/claude-md.svg)](https://agentmods.dev/instructions/solomon2773/nora/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/solomon2773/nora/claude-md"><img src="https://agentmods.dev/badge/instructions/solomon2773/nora/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 2,859 This file is loaded in full into every session.
When invoked 2,859 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.02859 $0.02859
Opus 5 $0.01430 $0.01430
Sonnet 5 $0.00572 $0.00572
Haiku 4.5 $0.00286 $0.00286

Measured 6d ago against content hash 4f2d5d715fe4, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

nora CLAUDE.md 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 6d 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.

CLAUDE.md · 167 lines

How it starts

The opening of the file, as written. The whole thing — 167 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

What This Repo Is

Nora is the self-hosted AI agent ops platform — an operator-facing control plane that manages, deploys, monitors, and operates agent runtimes across Docker and Kubernetes GA deploy targets. Runtime families are OpenClaw and Hermes; NemoClaw is an experimental sandbox profile layered onto supported deploy targets. Proxmox LXC placement is experimental for OpenClaw and prepared Hermes templates; NemoClaw on Proxmox remains blocked. Node 24 LTS across all services.

Development Commands

Docker Compose (primary path)

docker compose up -d                          # Start full stack (nginx on port 8080)
docker compose up -d --build <service>        # Rebuild a single service
docker compose logs -f backend-api            # Stream logs
docker compose exec postgres psql -U nora -d nora  # Access database

The base docker-compose.yml runs dev mode (hot-reload, volume mounts). Overlays:

  • docker-compose.override.yml — auto-loaded; switches to Dockerfile.prod and npm start for production-like runs
  • docker-compose.e2e.yml — E2E test stack
  • docker-compose.kubernetes.yml — generic Kubernetes kubeconfig mounts for Admin-registered clusters
  • docker-compose.kind.yml — Kind network helper layered with docker-compose.kubernetes.yml for local K8s smoke testing

One-liner installer: ./setup.sh (macOS/Linux/WSL2) or ./setup.ps1 (Windows). Verifies Docker/OpenSSL, generates secrets, creates admin account, starts stack.

Per-service dev (without Docker)

# Backend API (listens on 4000 inside container; host-exposed on 127.0.0.1:4100 via compose)
cd backend-api && npm install && npm start

# Worker provisioner (health on 4001)
cd workers/provisioner && npm install && npm start

# Any frontend (port 3000)
cd frontend-dashboard && npm install && npm run dev
# same pattern for admin-dashboard, frontend-marketing

Read the full file on GitHub · 167 lines

Changes

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.

  1. 6d ago First seen · 167 lines · 2,859 tokens per session scan A 4f2d5d715fe4

Subscribe to this mod's changes

nora CLAUDE.md is an instructions file published in the GitHub repository solomon2773/nora (50 stars, last pushed yesterday), licensed Apache-2.0. It adds 2,859 tokens to every session, about $0.0143 per session on Opus 5. 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 2026-08-30.

agent-orchestrationai-agentscontrol-planedockerkubernetesllmops
Related

Other instructions, from other repositories

netdata AGENTS.md

AGENTS.md instructions for netdata/netdata, covering agents.md, goals, requirement language, working with the user and development principles.

netdata/netdata · 11,007 tokens

warren AGENTS.md

AGENTS.md instructions for jayminwest/warren, covering agents.md, what this project is, runtime topology, the burrow absorption (plan pl-3007) and per-project config (.warren/config.yaml).

jayminwest/warren · 10,296 tokens

netdata CLAUDE.md

Claude Code instructions for netdata/netdata, a project described as: The fastest path to AI-powered full stack observability, even for lean teams.

netdata/netdata · 3 tokens

hal-9000 AGENTS.md

AGENTS.md instructions for vinta/hal-9000, covering agents.md, commands, gotchas, external tool documentation and context7 library ids.

vinta/hal-9000 · 786 tokens

claude-ai-spring-boot CLAUDE.md

Instructions for piomin/claude-ai-spring-boot, covering 1. plan mode default, 2. self-improvement loop, 3. verification before done, 4. demand elegance (balanced) and core principles.

piomin/claude-ai-spring-boot · 450 tokens

claworc CLAUDE.md

Claude Code instructions for gluk-w/claworc, covering claworc, repository structure, architecture, configuration and terminology.

gluk-w/claworc · 1,881 tokens