NetworkOps_Platform CLAUDE.md

A project guide for NetworkOps, an AI network-automation platform with an MCP server and a web dashboard. The dashboard uses a Flask API, a React frontend, and gRPC telemetry.

In plain words
What is it for?
Use it to configure the environment, install dependencies, run the dashboard, connect the MCP server to Claude Desktop, and run all or selected pytest tests.
Why use it?
It documents setup, database migration, startup, and test commands for the platform's separate parts.

Instructions file

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/e-conners-lab/networkops_platform/claude-md
Clone the repo
git clone --depth 1 https://github.com/E-Conners-Lab/NetworkOps_Platform
Per session 1,284 This file is loaded in full into every session.
When invoked 1,284 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 $0.01284 $0.01284
Opus 5 $0.00642 $0.00642
Sonnet 5 $0.00257 $0.00257
Haiku 4.5 $0.00128 $0.00128

Measured 2d ago against content hash 4ec6fcb0320f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

NetworkOps_Platform 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 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.

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 · 107 lines

How it starts

The opening of the file, as written. The whole thing — 107 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.

Project Overview

NetworkOps is an AI-powered network automation platform with two primary entry points:

  1. MCP Server (network_mcp_async.py) — 178 tools for Claude integration
  2. Dashboard (dashboard/api_server.py) — Flask REST API + React 19 frontend + gRPC telemetry

Common Commands

# Setup
cp .env.example .env                    # Configure environment
uv venv --python 3.11                   # Create venv (downloads Python 3.11 if needed)
source .venv/bin/activate
uv pip install -r requirements.txt      # Install dependencies (or: pip install -r requirements.txt)
alembic upgrade head                    # Run database migrations

# Run
python dashboard/api_server.py          # Dashboard API (port 5001)
# For MCP: configure in Claude Desktop / claude_desktop_config.json

# Tests
pytest tests/ -v                        # All tests
pytest tests/test_api_contracts.py -v   # Fast API contract tests (no lab needed)
pytest tests/test_some_file.py::TestClass::test_method -v  # Single test
pytest -m "not slow"                    # Skip slow tests
pytest -m unit                          # Unit tests only
SKIP_DEVICE_TESTS=true pytest           # Skip tests requiring live devices

# Linting
ruff check .                            # Lint
ruff check . --fix                      # Lint with auto-fix
ruff format .                           # Format

# Pre-commit
pre-commit install                      # Install hooks
pre-commit run --all-files              # Run all hooks

# Docker
docker-compose up -d                    # Dev environment
docker-compose -f docker-compose.prod.yml up -d  # Production

Architecture

Core (core/) — 230+ modules

The engine layer. Key subsystems:

  • Network engines: impact_analyzer.py, dependency_graph.py, compliance_engine.py, bgp_discovery.py
  • Device connectivity: connection_pool.py, device_cache.py, containerlab.py, eve_ng_client.py
  • Automation: ansible_manager.py, nornir_manager.py, aetest_runner.py
  • Config management: config_tree.py, config_tree_db.py, config_tree_generator.py
  • Data layer: unified_db.py (singleton, thread-safe), db.py, event_logger.py

Read the full file on GitHub · 107 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. 2d ago First seen · 107 lines · 1,284 tokens per session scan A 4ec6fcb0320f

Subscribe to this mod's changes

NetworkOps_Platform CLAUDE.md is an instructions file published in the GitHub repository E-Conners-Lab/NetworkOps_Platform (9 stars, last pushed 2mo ago), licensed MIT. It adds 1,284 tokens to every session, about $0.0064 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 2026-08-31.